← Back to Archives
VOLUME 14, ISSUE 3, MARCH 2026
Wireless Charging of Electric Vehicle
Abhijeet Prakashrao Patil, Anuj Nanduji Kardbhajane, Vaishnavi Sunil Ahirkar, Jitisha Shailendra Bagde, Gunjan Snajayraoji Dhawade, Prof. Rajendra Bhombe, Prof. Saurabh Bagde
INTELLIGENT FAULT DETECTION AND ALERTING SYSTEM FOR UNDERSEA & UNDERGROUND CABLE NETWORK
MD.Amzad, L. Saikumar, MD. Adil Ahmed, S. Srivani, P. Shruthi
IOT BASED EV CHARGING AND PARKING SYSTEM
G. Saritha Reddy, Raisa Nuraan, K. Anudeep, K. Shruthi, D. Laxmi, Y. Rahul Raj
IOT Based Railway Track Structural Health Monitoring System
Y. Vijay Jawahar Paul, B. Shivateja, B. Sai Charan, M. Nandini, V. Sai Kumar
“Design and Implementation of a Low-Cost Hybrid Solar-Grid Charging Prototype for Electric Two Wheelers”
Aakansha Mall, Sweta Maraskolhe, Nandini Kushwaha, Gayatri Nagpure, Nisha Marthe, Prof. Dr. Rajendra Bhombe
Analysis of Different Algorithm of Numerical Relay Using Python
Arpit Sanjay Thakre, Atharv Moon, Arpit Mendhe, Pavan Harle, Om Bobde, Prof. Rajendra Bhombe, Prof. Priyanka Rajput
High Step Up DC-DC Convertor for Renewable Energy System
Yash Gajankushkar, Gaurav Barsagade, Shubhanshi Soni, Sargam Meshram, Vansh Bhute, Prof. Diksha Khare, Prof. Rajendra Bhombe
IoT-Based Temperature Humidity and Plants Monitoring and Precision Fertigation Enhanced by Drone-Assisted Crop Stress Detection
Sanskar Vijayrao Badhe, Vedant Chandraprakash Kambe, Alkesh Prashant Dahake, Ujwal Laxman Bhoyar, Prof. Rajendra Bhombe, Prof. Priyanka Rajput
UNDERGROUND CABLE FAULT DETECTION
Ankit Bawne, Apeksha Karosiya, Shruti Manwatkar, Rahul Gawande, Ganesh Belsare, Prof. Rajendra Bhombe, Prof Meena Gaurkar
Transmission Line Fault Safety Protection
Swarna Pramodrao Kadwe, Ashwini Arun Choure, Prachi Ramchandra Chopde, Nisha Wasudeo Choudhari, Gitika Snajayraoji Machhale, Prof. Rajendra Bhombe, Prof. Swati Gajbhiye
SOLAR-POWERED SMART IRRIGATION SYSTEM
Ratnadeep Raju Maske¹, Aadesh Babusing Rathod², Nagesh Shankar Koshkewar³, Dipali Bhagwan Athilkar´, Aditya Sidhharth Wankhadeµ, Prof. Rajendra Bhombe¶, Prof. Saurabh Bagde·
Design and Implementation of a Converter-Based Active Battery Cell Equalization System for Electric Vehicles
Binsy Joseph, Deepak V. Bhoir
Adaptive PID Control Algorithm for Intelligent Temperature Regulation in IoT Systems
Oluebube Nzube Ezenwankwo, Engr Dr Tochukwu Onyenyili
SMART ENERGY METER USING TELEGRAM BOT
Dr. M. Shanmugavalli, L Navaneetha Krishnan, T Sukisivam
ROBOTIC ARM INTEGRATED WITH SMART CLEANER FOR OBJECT CLASSIFICATION USING YOLO
Helan Sophia B, Sobhana Vidhyadharsini R S, Shanmugavalli M
TEMPRATURE, HUMIDITY & FIRE EXTINGUISHER MONITORING USING ESP32 WEBSERVER
Mohit Rahangde, Muneshwari Bhelave, Rakesh Varma, Saurabh Baghele, Yash Astunkar, Ujwala Dhumane, Prof. Rajendra Bhombe, Prof Meena Gaurkar
“DRONE BASED FIRE DETECTION AND EMERGENCY RESPONSE SYSTEM”
G. Saritha reddy, N. Goutham, G. Gopal, M. Srusti, MD. Adil
IOT BASED GAS LEAKAGE DETECTION AND AUTOMATION CONTROL
B. Suresh reddy, B. Rohith Kumar, Muskaan, G. Rufus, B. Vignan
IOT BASED SMART MEDICATION REMINDER AND HEALTH ALERT SYSTEM
MD.Amjad, K. Sushma, M. Rajesh, V. Sathvika, B. Anil
SMART RAILWAY SIGNAL AND GATE AUTOMATION FOR ROAD VEHICLE SAFETY
DR. B. Veeru, S. Meghana, K. Arun Kumar, P. Rahul, K. Pavan Kumar
Real Time Monitoring of Mining and Connected Workers
E. Sajjan, A. Shruthi, Ch. SaiTeja, G. Aakash, J. SaiKiran
INDUSTRIAL AIR QUALITY AND NOISE POLLUTION MONITORING SYSTEM
DR. K. Kumara Swamy, K. Vishnu Sahasru, B. Vamshi, M. Venkat Rama Krishna, MD. Aslam Mohiuddin
IOT – POWERED ADAPTIVE LIGHTING SYSTEM FOR INDUSTRIAL FACILITIES
Dr. S. Chandrashekhar Reddy, G. Vaishnavi, MD. Abdul Muqeet, R. Ram Charan, V. Hussain
IOT BASED SMART PARKING AND VEHICLE MANAGEMENT SYSTEM FOR INDUSTRIAL CAMPUS
Y. Vijay Jawahar Paul, A. Saikiran, K. Sagar, S. Sandhya Rani, S. Abhinay
IOT BASED WORKERS SAFETY HELMET WITH REAL TIME HEALTH MONITORING
P. Prabakar, Ch. Pravalika, K. Sravanthi, Y. Samatha, E. Deena, N. Kalyani
Sericulture Automation System Climate Control And Production Efficiency
B. Sandeep Kumar, P. Vyshnavi, Sana, Y. Rahul Kumar, N. Pranay
Smart Incubator for Poultry farming
B. Sandeep Kumar, P. Udayasri, P. Shivashankar, E. Saikumar, G. Vishal
Performance Assessment of Machine Learning Models for Network Anomaly Detection: A Case Study with CICIDS2017
Tawo Godwin A, Osahon Okoro, Aigberemhon Moses E, Ojomu Sunday A, Etim Bassey E
IOT BASED FAULT DETECTION SYSTEM IN TRANSMISSION LINES
V. ABHINAV, V MAHESH BABU, N. VEERA SIMHA REDDY, K. RAVI TEJA, Dr.G.GANTHAIAH SWAMY
Automated Factory Gate Control and Vehicle Counting System Using IOT
E. Sajjan, B. Ananya, S. Shiva Raj, B. Pawan Kalyan, S. Nalin Prabhath
Intelligent Bus Monitoring and Alert System Based on IoT
K. Amarender, K Raju, M Manoj, S. Manoj Kumar, S. Manu
SMART PARKING MANAGEMENT SYSTEM
E. Sajjan, M. Shivaleela, T. Priyanka, L. Praveen, S. Sanjay
EV DYNAMIC WIRELESS CHARGING ON ROADS
L. Karunakar, Y. Naveen Kumar
IOT BASED BOILER TEMPERATURE AND PRESSURE MONITORING SYSTEM
B. Hanumanthu, G. Ramya, G. Vanaja, K. Saipranay, T. Harshith Kumar
Thermoelectric Generator Module in Driving the Vehicle and Monitoring using IoT
Ms. B. Sruthi, K. Ganesh Kumar
IOT ASSISTED ELEVATOR AUTOMATION WITH REAL TIME STATUS VISUALIZATION
V. Phani Kumar, J. Ram Prasad, B. Shadrak, J. Kalyan, Mr. M. Rama Krishna
IoT Based Undervoltage and Overvoltage Protection System
Ms. B. Sruthi, Ch. Ajay
MorphosETL: A Schema-Grounded, Confidence-Gated LLM-Assisted No-Code ETL System
Mohan Raj R, Srinisha P, Mohamed Athfan D
SMART GARBAGE MONITORING AND MANHOLE OPEN ALERT SYSTEM
T. Krishna Mohan, P. Rakada Kumar, S. Tharun
Real-Time Water Purity Monitoring Using Arduino
Mr. Shahaji Sutar, Aarnav Lokhande, Ruturaj Jankar, Viraj Badadare, Sagar More, Jay Dhanawde
IOT BASED SMART PARKING SYSTEM
Dr. G. Gantaiah Swami, P. Sai Charan, S. Lakshmi Narasimha
Street Light Fault Detection And Energy Monitoring System
Mr. L. Karunakar, M.Tech, E. Divya Sai Teja
Railway Track Crack Detection and Automatic Gate Control System
Ch. Maheswara Rao, Sk. Mastan, P. Venkata Gandhi, Ms. Chandhni Sri Lakshmi M.Tech
IoT Accident Detection & Smart Emergency Response System
K. Amarender, P. Pavithra, B. Supriya, M. Navya, V. Srikanth
CONTACTLESS POWER TRANSFER FOR ROTATING APPLICATIONS USING MAGNETIC COUPLE
L. Karunakar, B. Chinnu Babu
IOT BASED ACCIDENT ALERT AND DETECTION SYSTEM
A. CHANDHNI SRI LAKSHMI, M.M.V.V. DURGA GANESH, P. NARENDRA
A Study Of Upper Arm Muscle Circumference Of Anthropometric Measurement Among Aged Group Tribal And Non-Tribal Sportsmen
Gaude Pralay Rohidas
SMART CHARGING STATION (PCB + IoT) WITH LOAD BALANCING & PREPAID BILLING
Dr. V. Anantha Lakshmi, T. Mounika
AI Based Audio Surveillance System
Ms. Aphasana Mulla, Vedanti Thakur, Anaya Kumbhar, Swanandi Sawant, Vanshika Vhatkar
Alcohol Sense Engine Locking System
Dr. G. Gantaiah Swamy, Shaik. Kodhan Saheb, P. Gowtham
Low-Cost IoT-Based Fault Detection & AI Prediction for Electric Vehicle
Dr. V. Anantha Lakshmi, Sri Naga Divya.A, Damareswari.G
IOT Based Smart Energy Theft Detection Using Current Imbalance Alerts And Prepaid Billing
Dr. V. Anantha Lakshmi, Y. Rajeshwari, G. Indumathi
Raspberry Pi Pico Hybrid HID Controller
Surya Sevak Singh, Siddharth Sonawane, Vineet Raipure, Siddhesh Gaikwad, Pranav Kamble, Om Sakpal
Intelligent IoT-Based Real-Time Industrial Effluent Monitoring System Using Machine Learning for Water Quality Classification
Dr. Gaayathry K, Kaviya C, Srivarshini S, Amritha J
IOT BASED SMART MOTOR PROTECTION AND CONTROL SYSTEM
L. Karunakar, V. Lokesh Sai
IoT Based Bluetooth Control Industrial Robotic Arm Gripper
G. Sivaraj Manikanta, T. Krishna Mohan
DUAL POWERED AUTONOMOUS OBSTACLE AVOIDING VEHICLE
Mr. V. Brahmeswara Rao, K. Chandu, P. Jagadeesh, T. Jaideep
3D COMSOL Simulation of TGS1820 Sensor: Acetone Detection in Human Breath Using Coupled Electric Currents and Transport Physics
Jelcy Chiristila P, Mahalakshmi K, Dr. M Shanmugavalli
Load Flow and Short Circuit Analysis for a Data Centre
Jeevananthan J, Dr. V. Prasanna Moorthy
An AI-Powered Learning and Business Support Platform for Women Entrepreneurs
Abinaya Sri M, M. Saravanakumar
AI-Assisted Art Critique Platform
SUSMITHA SRI P, MOHAMED ATHFAN D
AI-Powered Smart ISL Translator with Voice, Text & Gesture Recognition
Janasruthi N, Mohamed Athfan D
IOT-BASED SOLAR WIRELESS POWER TRANSFER SYSTEM FOR ELECTRIC VEHICLES
G. Harika, D. Ramu, R. Sushma Sri, Dr. M. Ajay Kumar
An Optimized Machine Learning Framework for Heart Failure Patient Classification and Risk Prediction
K. Dinesh, K. Harika, M. Rohith, Sandi Sunanda
IoT Based Electric Vehicle Battery Management System by Using Charge Monitor And Fire Protection
A Teja Sri, DR M Ajay Kumar
IOT-BASED SOLAR WIRELESS POWER TRANSFER SYSTEM FOR ELECTRIC VEHICLES
Ch. Srilatha, Dr. M. Ajay Kumar
DESIGN OF ENHANCED SMART GRIDS WITH A NEW IOT AND CLOUD BASED SMART METER TO PREDICT THE ENERGY CONSUMPTION
Naga Nandini, Dr. M. Ajay Kumar
SMART MONITORINNG OF TRANSFORMER PROTECTION SYSTEM
M. Bhavana, DR. M. Ajay Kumar
IMPLEMENTATION OF PREDICTIVE MODELLING OF PRESCRIPTION GROWTH THROUGH MARKETING MIX MODELLING
Selvapujith T, Mohamed Athfan D
EduCrate: AI-Powered Personalized Learning Kit Generator
Gopika D, Bharath Krishnan M, Ms. Maneesha
OBSTACLE AVOIDING ROBOT USING WIFI MODULE ESP 8266
Wrushali Deshmukh, Yash Gade, Suyog Ghatage, Shreyas Palav, Manthan Hire, Siddhi Borhade
DEVELOPMENT OF AUTONOMOUS VEHICLE SYSTEM USING ESP32 MICROCONTROLLER
Ch. Srilatha, Dr. M. Ajay Kumar
Piezoelectric Electricity Generator Using Footsteps
Mr. Rajendra Ghorpade, Deep Koli, Diksha Gaikwad, Tejaswini Patil, Bhakti Waghmare
Smart SIP for Teens: A Gamified and Explainable Machine Learning Framework for Early Investment Habit Formation
Maneesha P A, Saranya G
INTELLIGENT BATTERY THERMAL MANAGEMENT SYSTEM FOR SMART ELECTRIC VEHICLES
Ms. B. Sruthi, Mr. Talluri. Karthik
“AI-Based Multi-Sensor Fusion for Real-Time Heavy Metal Detection in Water Using IoT”
I Rakshan Darwin, M Gokul, K Sabarish, R Seetharaman
SMART HOME AUTOMATION WITH INTEGRATED SAFETY AND SECURITY USING STM32 AND WI-FI MODULE
S Dharani Sivapriya, M Bhuvaneshwari, R Seetharaman
NeuroVision AI: Multi-Device Eye Strain Detection Using Micro-Motion and Cognitive Behaviour
Vanitha A, Dr. K. Arunkumar, Keerthana S, Karthika V
An IoT-Integrated Multi-Sensor Framework for Continuous Vital Monitoring and Fall Detection
Madhumitha. M, Lakshmi Priya. S, Mr. R. Satheesh
Design Hybrid EV using Supercapacitor for Long Mileage and Durability
Ayur Sanjay Bhoge, Achal Sheshrao Chokhandre, Shreya Dilip Hekad, Aishwarya Ravish Kamble, Divesh Vilas Chittalwar, Prof. Rajendra Bhombe, Mr. Harshal Makde
QUANTUM SECURE BLOCKCHAIN ARCHITECTURE
Dr. Ashwini Kumar Jha, Kartik Patil, Abhishek Patil, Pramod Patil, Shreyansh Patel
Hybrid Edge-Based Predictive Health Monitoring Model using Statistical Trend and Anomaly Fusion
Suriyamoorthy S, Arul Victor Raj BM, Ragavan D
IOT BASED UNDER GROUND CABLE FAULT DETECTION
T. Krishna Mohan, G. Rohith, J. Rakesh
DETECTION OF THERMAL RUNAWAY IN EV BATTERY PACK USING MULTI-MODAL SENSOR FUSION (THERMAL IMAGING, GAS & CURRENT) AND NEURAL NETWORK
C Logapragash, S Muralidharan, R Sunil Raja
A Centralized AI Framework for Wildlife-Vehicle Collision Detection: Addressing Implementation Challenges in Real-World Deployment
Mr. Stanly Raj J, Ms. Maneesha P.A, Sami Abdulsalam
Intelligent Agriculture Platform for Precision Farming
Sharmila R.B, Varsha K, Saravana Kumar M
ANDRIOD-CONTROLLED HOME AUTOMATION WITH HC-05 BLUETOOTH AND ARDUINO FOR ENERGY – EFFICENT OPERATION
Mr. V. Brahmeswara Rao, P. Sai Vamsi Reddy
Computer Vision–Driven PPE Compliance and Safety Violation Detection
Vanitha A, Rithish B, Safna M
Power Quality Enhancement in a Motor Manufacturing Industry using SVC
Yasoda Kailasam, Gokulavarshini R
Hand Gesture Based Touchless Media Control System Using Computer Vision and Machine Learning
Ms. Subiksha R, Mr. Janarthanan S
Anemia Detection Through Nail Imaging: From Clinical Signs to AI Solutions
Mohamed Athfan D, Noorul Hasan Z, Deepa Sre A P
Smart Skill Gap Analyzer for Career Readiness
Mala Bharumathi M, Madhumitha MD, Kamil Arsath Ahammed A
Abstract
Wireless Charging of Electric Vehicle
Abhijeet Prakashrao Patil, Anuj Nanduji Kardbhajane, Vaishnavi Sunil Ahirkar, Jitisha Shailendra Bagde, Gunjan Snajayraoji Dhawade, Prof. Rajendra Bhombe, Prof. Saurabh Bagde
DOI: 10.17148/IJIREEICE.2026.14301
Abstract: Wireless power transfer (WPT) using magnetic resonance is the technology which could set human free from the annoying wires. In fact, the WPT adopts the same basic theory which has already been developed for at least 30 years with the term inductive power transfer. WPT technology is developing rapidly in recent years. At kilowatts power level, the transfer distance increases from several milli meters to several hundred milli meters with a grid to load efficiency above 90%. The advances make the WPT very attractive to the electric vehicle (EV) charging applications in both stationary and dynamic charging scenarios.
For energy, environment, and many other reasons, the electrification for transportation has been carrying out for many years. In railway systems, the electric locomotives have already been well developed for many years. A train runs on a fixed track. It is easy to get electric power from a conductor rail using pantograph sliders. However, for electric vehicles (EVs), the high flexibility makes it not easy to get power in a similar way. Instead, a high power and large capacity battery pack is usually equipped as an energy storage unit to make an EV to operate for a satisfactory distance. Until now, the EVs are not so attractive to consumers even with many government incentive programs. Government subsidy and tax incentives are one key to increase the market share of EV today. The problem for an electric vehicle is nothing else but the electricity storage technology, which requires a battery which is the bottleneck today due to its unsatisfactory energy density, limited life time and high cost.
For energy, environment, and many other reasons, the electrification for transportation has been carrying out for many years. In railway systems, the electric locomotives have already been well developed for many years. A train runs on a fixed track. It is easy to get electric power from a conductor rail using pantograph sliders. However, for electric vehicles (EVs), the high flexibility makes it not easy to get power in a similar way. Instead, a high power and large capacity battery pack is usually equipped as an energy storage unit to make an EV to operate for a satisfactory distance. Until now, the EVs are not so attractive to consumers even with many government incentive programs. Government subsidy and tax incentives are one key to increase the market share of EV today. The problem for an electric vehicle is nothing else but the electricity storage technology, which requires a battery which is the bottleneck today due to its unsatisfactory energy density, limited life time and high cost.
Abstract
INTELLIGENT FAULT DETECTION AND ALERTING SYSTEM FOR UNDERSEA & UNDERGROUND CABLE NETWORK
MD.Amzad, L. Saikumar, MD. Adil Ahmed, S. Srivani, P. Shruthi
DOI: 10.17148/IJIREEICE.2026.14302
Abstract: The fault detection and alerting system for undersea and underground cable networks is designed to monitor, detect, and report faults in long-distance industrial cable infrastructures such as power and communication lines. These networks are critical yet difficult to access and maintain, making timely fault detection essential to prevent energy loss, data disruption, and costly downtime.
The proposed system employs a combination of IOT-based sensors, microcontrollers, and real-time data transmission to continuously monitor key parameters such as voltage, current, temperature, and insulation resistance. When abnormalities indicating potential faults such as short circuits, open circuits, or insulation failures are detected, the system intelligently locates the fault position and sends instant alerts through a wi-fi or gsm module to a centralized monitoring platform or mobile application.
This smart fault detection and alerting system enhances the reliability and safety of industrial cable networks, minimizes maintenance time, and reduces operational costs by enabling early fault identification and rapid response. The solution can be applied in submarine communication cables, underground power grids, and industrial data networks where continuous monitoring is crucial.Therefore, there is a need for an intelligent, automated system that can continuously monitor, detect, and locate faults accurately in real time and send instant alerts to maintenance personnel through wireless communication. The proposed intelligent fault detection and alerting system for undersea and underground industrial cable networks aims to address these challenges by integrating iot sensors, microcontrollers, and communication modules to provide efficient, reliable, and timely fault detection and reporting.
Keywords: Flex Sensor, ESP32, Vibration sensor, Aurdino IDE.
The proposed system employs a combination of IOT-based sensors, microcontrollers, and real-time data transmission to continuously monitor key parameters such as voltage, current, temperature, and insulation resistance. When abnormalities indicating potential faults such as short circuits, open circuits, or insulation failures are detected, the system intelligently locates the fault position and sends instant alerts through a wi-fi or gsm module to a centralized monitoring platform or mobile application.
This smart fault detection and alerting system enhances the reliability and safety of industrial cable networks, minimizes maintenance time, and reduces operational costs by enabling early fault identification and rapid response. The solution can be applied in submarine communication cables, underground power grids, and industrial data networks where continuous monitoring is crucial.Therefore, there is a need for an intelligent, automated system that can continuously monitor, detect, and locate faults accurately in real time and send instant alerts to maintenance personnel through wireless communication. The proposed intelligent fault detection and alerting system for undersea and underground industrial cable networks aims to address these challenges by integrating iot sensors, microcontrollers, and communication modules to provide efficient, reliable, and timely fault detection and reporting.
Keywords: Flex Sensor, ESP32, Vibration sensor, Aurdino IDE.
Abstract
IOT BASED EV CHARGING AND PARKING SYSTEM
G. Saritha Reddy, Raisa Nuraan, K. Anudeep, K. Shruthi, D. Laxmi, Y. Rahul Raj
DOI: 10.17148/IJIREEICE.2026.14303
Abstract: We are currently experiencing difficulties due to a lack of fuel. As a result, we are heading towards electric vehicles. However, many are still hesitant to choose electric vehicles over present vehicles. It's due to a combination of high prices and a scarcity of charging outlets. Even if there are only a few charging stations accessible, extra time is required to charge the vehicle. Furthermore, in today's cities, car parking has become a serious concern. As a result, by considering these challenges, we can give smart parking with charging options to the majority of business buildings. This will reduce the time spent looking for a parking spot. Furthermore, there is no need to spend additional time looking for a charging station or charging at home.
Keywords: IoT (Internet of Things), Electric Vehicle (EV), Smart Parking, Charging Station, Automation, Real-Time Monitoring, Smart City.
Keywords: IoT (Internet of Things), Electric Vehicle (EV), Smart Parking, Charging Station, Automation, Real-Time Monitoring, Smart City.
Abstract
IOT Based Railway Track Structural Health Monitoring System
Y. Vijay Jawahar Paul, B. Shivateja, B. Sai Charan, M. Nandini, V. Sai Kumar
DOI: 10.17148/IJIREEICE.2026.14304
Abstract: The safety and reliability of railway transportation largely depend on the structural integrity of the rail tracks, which are continuously subjected to dynamic loads, environmental effects, and material fatigue. Conventional manual inspection methods are inefficient, time-consuming, and often unable to identify hidden or developing faults in real time. To address these limitations, this project presents an Internet of Things (IoT)-based Railway Track Structural Health Monitoring System designed to ensure continuous, automated surveillance of track conditions using intelligent sensing and data communication technologies.
The proposed system employs a network of sensors such as strain gauges, vibration sensors, and ultrasonic sensors strategically installed along the railway tracks to measure strain, vibration, and surface irregularities. These analog signals are conditioned and processed by an ESP32 microcontroller, which serves as the central processing and communication unit. The system analyzes sensor data to detect deviations beyond predefined safety thresholds and transmits the results wirelessly via GSM or Wi-Fi modules to a central monitoring station or cloud-based dashboard. In the event of any abnormal condition, the system automatically generates real-time alerts through Telegram or SMS notifications, enabling prompt maintenance action and preventing potential derailments or failures.
The entire setup is powered through a low-power supply unit, with provisions for solar-based operation to enhance reliability in remote field environments. The collected data can be logged and analyzed on cloud platforms such as Thing Speak or Blynk, enabling visualization, trend analysis, and predictive maintenance using artificial intelligence
This project demonstrates a comprehensive integration of Electrical and Electronics Engineering (EEE) concepts, including sensor interfacing, signal conditioning, power electronics embedded systems, communication protocols, and automation control. By combining these technologies within an IoT framework, the proposed system offers a cost- effective, scalable, and sustainable solution for intelligent railway infrastructure monitoring. The developed prototype emphasizes the transition from conventional maintenance to smart, predictive, and data-driven maintenance, contributing significantly to improved safety, reliability, and operational efficiency in modern railway systems.
Keywords: Railway, cracks, Thing speak, Internet technology and IoT.
The proposed system employs a network of sensors such as strain gauges, vibration sensors, and ultrasonic sensors strategically installed along the railway tracks to measure strain, vibration, and surface irregularities. These analog signals are conditioned and processed by an ESP32 microcontroller, which serves as the central processing and communication unit. The system analyzes sensor data to detect deviations beyond predefined safety thresholds and transmits the results wirelessly via GSM or Wi-Fi modules to a central monitoring station or cloud-based dashboard. In the event of any abnormal condition, the system automatically generates real-time alerts through Telegram or SMS notifications, enabling prompt maintenance action and preventing potential derailments or failures.
The entire setup is powered through a low-power supply unit, with provisions for solar-based operation to enhance reliability in remote field environments. The collected data can be logged and analyzed on cloud platforms such as Thing Speak or Blynk, enabling visualization, trend analysis, and predictive maintenance using artificial intelligence
This project demonstrates a comprehensive integration of Electrical and Electronics Engineering (EEE) concepts, including sensor interfacing, signal conditioning, power electronics embedded systems, communication protocols, and automation control. By combining these technologies within an IoT framework, the proposed system offers a cost- effective, scalable, and sustainable solution for intelligent railway infrastructure monitoring. The developed prototype emphasizes the transition from conventional maintenance to smart, predictive, and data-driven maintenance, contributing significantly to improved safety, reliability, and operational efficiency in modern railway systems.
Keywords: Railway, cracks, Thing speak, Internet technology and IoT.
Abstract
“Design and Implementation of a Low-Cost Hybrid Solar-Grid Charging Prototype for Electric Two Wheelers”
Aakansha Mall, Sweta Maraskolhe, Nandini Kushwaha, Gayatri Nagpure, Nisha Marthe, Prof. Dr. Rajendra Bhombe
DOI: 10.17148/IJIREEICE.2026.14305
Abstract: The rapid adoption of electric two-wheelers has created an urgent need for sustainable and cost-effective charging solutions. Conventional grid-based charging stations not only increase the load on the power network but also contribute indirectly to carbon emissions. To address these challenges, this project proposes the design and implementation of a lowcost hybrid solar-grid charging prototype for electric two-wheelers.
The system integrates a photovoltaic (PV) array with an. MPPT-based charge controller, a battery storage unit, and a power management circuit that enables seamless switching between solar and grid power. Under optimal conditions, the solar energy serves as the primary source of charging, while the grid acts as a reliable backup in case of insufficient solar generation.
The prototype is designed to ensure efficiency, affordability, and scalability for urban and rural applications. Simulation studies in MATLAB/Simulink validate the system's performance under varying load and weather conditions, while preliminary experimental analysis confirms its feasibility. Hybrid approach not only reduces dependency on grid electricity but also promotes the use of renewable energy in the electric mobility sector.
The system integrates a photovoltaic (PV) array with an. MPPT-based charge controller, a battery storage unit, and a power management circuit that enables seamless switching between solar and grid power. Under optimal conditions, the solar energy serves as the primary source of charging, while the grid acts as a reliable backup in case of insufficient solar generation.
The prototype is designed to ensure efficiency, affordability, and scalability for urban and rural applications. Simulation studies in MATLAB/Simulink validate the system's performance under varying load and weather conditions, while preliminary experimental analysis confirms its feasibility. Hybrid approach not only reduces dependency on grid electricity but also promotes the use of renewable energy in the electric mobility sector.
Abstract
Analysis of Different Algorithm of Numerical Relay Using Python
Arpit Sanjay Thakre, Atharv Moon, Arpit Mendhe, Pavan Harle, Om Bobde, Prof. Rajendra Bhombe, Prof. Priyanka Rajput
DOI: 10.17148/IJIREEICE.2026.14306
Abstract: Numerical relays play a vital role in modern power system protection by providing fast, reliable, and accurate fault detection. Unlike conventional electromechanical and static relays, numerical relays use microprocessors and digital signal processing techniques to analyze electrical parameters and generate trip signals during abnormal conditions. This paper presents a comparative analysis of different algorithms used in numerical relays, implemented using Python. The study focuses on commonly used protection algorithms such as overcurrent, distance, and differential protection techniques. Each algorithm is modeled and tested under various fault conditions including line-to-ground, line-to-line, and three-phase faults.
Key performance parameters such as response time, detection accuracy, sensitivity, and reliability are evaluated. Simulation results demonstrate that digital implementation of relay algorithms improves fault detection speed and accuracy while reducing computational complexity. Among the analyzed techniques, differential protection shows superior performance in terms of fast response and precision, while distance protection provides effective zonebased fault identification. The use of Python enables flexible modeling, easy simulation, and efficient comparison of relay characteristics. The findings of this study contribute to better understanding and practical implementation of numerical relay algorithms in modern smart grid and power system protection applications.
Keywords: Numerical Relay, Overcurrent Protection, Distance Protection, Differential Protection, Python, Power System Protection.
Key performance parameters such as response time, detection accuracy, sensitivity, and reliability are evaluated. Simulation results demonstrate that digital implementation of relay algorithms improves fault detection speed and accuracy while reducing computational complexity. Among the analyzed techniques, differential protection shows superior performance in terms of fast response and precision, while distance protection provides effective zonebased fault identification. The use of Python enables flexible modeling, easy simulation, and efficient comparison of relay characteristics. The findings of this study contribute to better understanding and practical implementation of numerical relay algorithms in modern smart grid and power system protection applications.
Keywords: Numerical Relay, Overcurrent Protection, Distance Protection, Differential Protection, Python, Power System Protection.
Abstract
High Step Up DC-DC Convertor for Renewable Energy System
Yash Gajankushkar, Gaurav Barsagade, Shubhanshi Soni, Sargam Meshram, Vansh Bhute, Prof. Diksha Khare, Prof. Rajendra Bhombe
DOI: 10.17148/IJIREEICE.2026.14307
Abstract: The rapid depletion of fossil fuels and the increasing demand for clean energy have promoted the use of renewable sources such as solar PV systems, fuel cells, and wind turbines. However, these sources usually produce low- voltage DC output, which is insufficient for applications like grid integration, battery charging, and electric vehicles. Therefore, an efficient step-up DC-DC converter is required to increase the voltage to the desired level.
This project presents the design of a High Step-Up DC-DC Converter with high voltage gain, improved efficiency, and reduced switching stress. The proposed converter uses a coupled inductor and voltage multiplier technique to achieve high voltage conversion with reduced power losses. Simulation using MATLAB/Simulink and hardware implementation will be used to validate the performance for renewable energy applications.
This project presents the design of a High Step-Up DC-DC Converter with high voltage gain, improved efficiency, and reduced switching stress. The proposed converter uses a coupled inductor and voltage multiplier technique to achieve high voltage conversion with reduced power losses. Simulation using MATLAB/Simulink and hardware implementation will be used to validate the performance for renewable energy applications.
Abstract
IoT-Based Temperature Humidity and Plants Monitoring and Precision Fertigation Enhanced by Drone-Assisted Crop Stress Detection
Sanskar Vijayrao Badhe, Vedant Chandraprakash Kambe, Alkesh Prashant Dahake, Ujwal Laxman Bhoyar, Prof. Rajendra Bhombe, Prof. Priyanka Rajput
DOI: 10.17148/IJIREEICE.2026.14308
Abstract: Agriculture plays a vital role in the Indian economy, yet traditional farming methods often lack real-time monitoring and efficient resource utilization. The IoT Based Smart Agriculture Monitoring System aims to overcome these challenges by integrating Internet of Things (IoT) technology with modern sensor networks. The system continuously monitors critical environmental parameters such as soil moisture, temperature, humidity, light intensity, air quality, and rainfall. Using an ESP32 microcontroller and long-range Lora WAN communication, the collected data is transmitted to a centralized monitoring platform where farmers can access real-time information remotely.
This system helps farmers make data-driven decisions, optimize irrigation and fertilizer usage, reduce manual labour, and improve crop productivity. The use of renewable energy sources such as solar power further enhances sustainability. The proposed solution promotes precision agriculture and supports smart farming initiatives.
This system helps farmers make data-driven decisions, optimize irrigation and fertilizer usage, reduce manual labour, and improve crop productivity. The use of renewable energy sources such as solar power further enhances sustainability. The proposed solution promotes precision agriculture and supports smart farming initiatives.
Abstract
UNDERGROUND CABLE FAULT DETECTION
Ankit Bawne, Apeksha Karosiya, Shruti Manwatkar, Rahul Gawande, Ganesh Belsare, Prof. Rajendra Bhombe, Prof Meena Gaurkar
DOI: 10.17148/IJIREEICE.2026.14309
Abstract: Underground power cables are widely used in power distribution systems because they are safer and more reliable than overhead lines. However, detecting faults in underground cables is difficult due to limited accessibility and high repair costs.
This project proposes an efficient underground cable fault detection system that can identify faults such as short circuit, open circuit, and earth fault. The system works on the principle of impedance measurement and voltage drop analysis to determine the distance of the fault from the source end using Ohm’s law.
A microcontroller-based circuit continuously monitors the cable parameters. When a fault occurs, the system calculates the fault distance and displays it on a digital display. This helps in quickly locating the fault, reducing downtime, and improving the reliability of the power distribution system
This project proposes an efficient underground cable fault detection system that can identify faults such as short circuit, open circuit, and earth fault. The system works on the principle of impedance measurement and voltage drop analysis to determine the distance of the fault from the source end using Ohm’s law.
A microcontroller-based circuit continuously monitors the cable parameters. When a fault occurs, the system calculates the fault distance and displays it on a digital display. This helps in quickly locating the fault, reducing downtime, and improving the reliability of the power distribution system
Abstract
Transmission Line Fault Safety Protection
Swarna Pramodrao Kadwe, Ashwini Arun Choure, Prachi Ramchandra Chopde, Nisha Wasudeo Choudhari, Gitika Snajayraoji Machhale, Prof. Rajendra Bhombe, Prof. Swati Gajbhiye
DOI: 10.17148/IJIREEICE.2026.14310
Abstract: The transmission line is a vital component of the power system that carries electricity from generating stations to distributions networks. However, these lines are often exposed to various faults such as short circuits, line-to-ground faults, and open circuits caused by environmental conditions or equipment failure. Faults in transmission lines can lead to severe damages, power outages, and safety hazards. To ensure system stability and reliability, a fast and accurate fault detection and protection system is essential. This project aims to design and implement a Transmission line fault safety protection system that can detect faults promptly and isolate the faulty section to prevent further damage. The system utilizes current and voltage sensing techniques, along with relay mechanisms, to identify abnormal conditions and trigger protective actions automatically. The project enhances the reliability and safety of power system by minimizing downtime the protecting electrical equipment. The proposed system is efficient, cost-effective, and suitable for integration into modern smart grid applications.
Abstract
SOLAR-POWERED SMART IRRIGATION SYSTEM
Ratnadeep Raju Maske¹, Aadesh Babusing Rathod², Nagesh Shankar Koshkewar³, Dipali Bhagwan Athilkar´, Aditya Sidhharth Wankhadeµ, Prof. Rajendra Bhombe¶, Prof. Saurabh Bagde·
DOI: 10.17148/IJIREEICE.2026.14311
Abstract: The increasing demand for sustainable agricultural practices has highlighted the importance of renewable energy in irrigation systems. Traditional irrigation methods that depend on grid electricity or diesel engines are often costly, environmentally harmful, and inaccessible in rural areas with limited power supply. A solar-powered irrigation system provides a clean, economical, and reliable alternative by utilizing photovoltaic (PV) panels to convert solar energy into electricity. This energy is used to operate a water pump that supplies water to the fields through drip or sprinkler irrigation methods. The system reduces dependency on fossil fuels, lowers operational costs, and ensures continuous water supply during critical farming seasons. Additionally, solar irrigation systems are eco-friendly, require minimal maintenance, and support sustainable agricultural development in remote and off-grid regions. This project demonstrates the integration of renewable energy technology in agriculture, contributing to energy conservation, food security, and rural empowerment.
Abstract
Design and Implementation of a Converter-Based Active Battery Cell Equalization System for Electric Vehicles
Binsy Joseph, Deepak V. Bhoir
DOI: 10.17148/IJIREEICE.2026.14312
Abstract: Battery cell balancing is one of the key functions of the Battery Management System (BMS) used in Electric Vehicles (EVs), as it enhances the battery performance while prolonging the battery life as well as providing safety. Battery cells connected in series have different parameters like internal resistance, temperature, and aging effects, which cause the state of charge to be different. This results in the battery capacity being less efficient and can cause battery degradation or safety issues. This paper discusses the different battery cell balancing techniques used in the battery management system. These techniques include passive balancing, switched capacitor equalizers, inductive equalizers, transformer equalizers, and DC–DC converter equalizers. A MATLAB/Simulink model is used to implement the different battery cell balancing techniques and their simulation results compared. A battery cell equalization system based on the Ćuk converter is designed for the battery cells of the Electric Vehicle. Simulation results show that the proposed system balances the charge of the battery cells efficiently with the least time and highest efficiency compared to the other battery balancing techniques.
Keywords: Battery Management System (BMS), Electric Vehicle Batteries, Cell Balancing, Active Balancing, Passive Balancing, Ćuk Converter, Battery Equalization, MATLAB/Simulink.
Keywords: Battery Management System (BMS), Electric Vehicle Batteries, Cell Balancing, Active Balancing, Passive Balancing, Ćuk Converter, Battery Equalization, MATLAB/Simulink.
Abstract
Adaptive PID Control Algorithm for Intelligent Temperature Regulation in IoT Systems
Oluebube Nzube Ezenwankwo, Engr Dr Tochukwu Onyenyili
DOI: 10.17148/IJIREEICE.2026.14313
Abstract: Precision and stability have a direct impact on productivity, safety, and product quality in industrial automation, HVAC systems, food preservation, and environmental monitoring. Despite being widely used because of their ease of use and efficiency, conventional PID controllers have limitations in dynamic contexts due to their fixed parameters and lack of flexibility. These flaws frequently lead to overshoot, sluggish reaction times, higher energy usage, and the requirement for regular manual retuning. The design, simulation, and assessment of an adaptive PID algorithm incorporated into an Internet of Things-enabled temperature control framework are presented in this research. The suggested system makes use of ESP32 microcontroller implementation for real-time control and Python-based modeling for algorithm creation, guaranteeing smooth interface with IoT protocols for data logging and remote monitoring. The adaptive PID algorithm improves system responsiveness and stability by dynamically modifying control gains in response to disturbances and changes in the environment. Response time, overshoot reduction, steady-state accuracy, and energy economy are all significantly improved as compared to traditional PID controllers. By providing predictive maintenance and remote accessibility via lightweight communication protocols like MQTT, IoT integration further improves scalability. The results demonstrate how adaptive PID systems can improve user comfort, sustainability, and dependability in contemporary IoT-based automation. This study adds to the expanding corpus of information on intelligent control systems and lays the groundwork for future research in large-scale industrial deployment and machine learning-driven predictive control.
Keywords: Adaptive PID Controller, IoT-enabled Temperature Control, ESP32 Microcontroller, Python Simulation, Real-time Monitoring, Energy Efficiency, Overshoot Reduction, Steady-State Accuracy, Smart Control Systems, Industrial Automation.
Keywords: Adaptive PID Controller, IoT-enabled Temperature Control, ESP32 Microcontroller, Python Simulation, Real-time Monitoring, Energy Efficiency, Overshoot Reduction, Steady-State Accuracy, Smart Control Systems, Industrial Automation.
Abstract
SMART ENERGY METER USING TELEGRAM BOT
Dr. M. Shanmugavalli, L Navaneetha Krishnan, T Sukisivam
DOI: 10.17148/IJIREEICE.2026.14314
Abstract: The Smart Energy Meter is an IoT-based system that tracks and controls electricity use in real time. This project features a Wi-Fi enabled microcontroller (ESP32) to measure electrical parameters like voltage, current, power, and energy consumption. The collected data is sent to the mobile app Blynk, allowing users to check their electricity usage from anywhere. A notification system uses Telegram Bot to inform the user when power consumption goes over a set limit. A relay module is included to automatically cut off the power supply, helping to prevent overload or excessive energy use. This system enables users to manage electricity consumption effectively and cut down on energy waste. The proposed system is low-cost, easy to use, and suitable for homes and small industrial settings. It promotes better energy management through IoT technology.
Abstract
ROBOTIC ARM INTEGRATED WITH SMART CLEANER FOR OBJECT CLASSIFICATION USING YOLO
Helan Sophia B, Sobhana Vidhyadharsini R S, Shanmugavalli M
DOI: 10.17148/IJIREEICE.2026.14315
Abstract: The integration of computer vision with robotic arm manipulation significantly improves the efficiency, accuracy, and autonomy of modern robotic systems. This project focuses on the design and implementation of a robotic arm integrated with real-time object classification using the YOLO (You Only Look Once) algorithm. The system is developed to identify, classify, and manipulate objects accurately through a vision-guided mechanism, enabling intelligent pick-and-place operations in dynamic and unstructured environments.
A camera mounted above the workspace continuously captures live video streams. These frames are processed using a YOLO-based object detection model, selected for its high speed and single-stage detection architecture, which ensures real-time performance. The algorithm detects multiple objects simultaneously, providing bounding box coordinates, class labels, and confidence scores for each object. Based on the detected object’s position and category, control signals are generated and transmitted to the robotic arm controller for precise movement and gripping actions. The model is trained using a custom dataset to improve classification accuracy for specific target objects. Experimental results demonstrate reliable detection and successful manipulation under varying lighting conditions and object orientations. Overall, integrating YOLO with robotic arm control enhances system speed, adaptability, and operational accuracy compared to conventional vision-based robotic systems.
Keywords: Smart Cleaner, Object Classification, USB Camera, YOLO
A camera mounted above the workspace continuously captures live video streams. These frames are processed using a YOLO-based object detection model, selected for its high speed and single-stage detection architecture, which ensures real-time performance. The algorithm detects multiple objects simultaneously, providing bounding box coordinates, class labels, and confidence scores for each object. Based on the detected object’s position and category, control signals are generated and transmitted to the robotic arm controller for precise movement and gripping actions. The model is trained using a custom dataset to improve classification accuracy for specific target objects. Experimental results demonstrate reliable detection and successful manipulation under varying lighting conditions and object orientations. Overall, integrating YOLO with robotic arm control enhances system speed, adaptability, and operational accuracy compared to conventional vision-based robotic systems.
Keywords: Smart Cleaner, Object Classification, USB Camera, YOLO
Abstract
TEMPRATURE, HUMIDITY & FIRE EXTINGUISHER MONITORING USING ESP32 WEBSERVER
Mohit Rahangde, Muneshwari Bhelave, Rakesh Varma, Saurabh Baghele, Yash Astunkar, Ujwala Dhumane, Prof. Rajendra Bhombe, Prof Meena Gaurkar
DOI: 10.17148/IJIREEICE.2026.14316
Abstract: Industrial environments such as warehouses, chemical plants, and manufacturing units require continuous monitoring to prevent fire accidents and ensure safety. Traditional fire detection systems often provide limited real-time monitoring and lack remote accessibility. This research proposes an IoT-based industrial fire safety monitoring system using the ESP32 microcontroller. The system integrates multiple sensors including a DHT11 temperature and humidity sensor, flame detection sensor, and infrared (IR) sensors for monitoring fire extinguisher status at different pillars. The ESP32 processes sensor data and hosts an embedded web server that displays real-time environmental conditions through a browser-based dashboard.
When abnormal temperature or flame detection occurs, the system activates a buzzer alarm and generates visual alerts on the monitoring interface. The proposed system offers a low-cost, scalable, and real-time monitoring solution that improves industrial safety and enables early fire detection.
When abnormal temperature or flame detection occurs, the system activates a buzzer alarm and generates visual alerts on the monitoring interface. The proposed system offers a low-cost, scalable, and real-time monitoring solution that improves industrial safety and enables early fire detection.
Abstract
“DRONE BASED FIRE DETECTION AND EMERGENCY RESPONSE SYSTEM”
G. Saritha reddy, N. Goutham, G. Gopal, M. Srusti, MD. Adil
DOI: 10.17148/IJIREEICE.2026.14317
Abstract: Fire accidents in forests, industrial zones, and urban areas cause severe damage to life, property, and the environment. Early detection and rapid response are critical to minimizing losses, but conventional fire monitoring systems are limited by fixed coverage, delayed response, and human dependency. This project presents a drone-based fire detection and emergency response system that utilizes a quadcopter equipped with flame, temperature, and smoke sensors along with GPS and wireless communication modules. The system continuously monitors large and inaccessible areas, detects fire conditions in real time, and transmits alert notifications with precise location details to authorities through an IoT platform. A live camera feed further assists in fire verification. The proposed system offers improved accuracy, rapid response, mobility, and reduced risk to human life, making it an effective solution for modern fire monitoring and disaster management applications.
Quadcopter drone frame: The physical structure or chassis of the drone that holds all other components. Brushless DC motor with propellers: Provides the necessary thrust and propulsion for the drone to fly. Electronic speed controllers (ESC's): Regulates the speed and direction of the motors based on signals from the flight controller. Flight controller (Pixhawk/KK/NAZA): The "brain" of the drone, processing inputs from sensors and the user to stabilize and control flight. Microcontroller (Arduino/Raspberry Pi): An additional small computer used for processing sensor data or managing specific payloads. Thermal camera or flame sensor: Detects heat signatures or the presence of a flame to identify fire locations. Smoke/Gas sensor, Temperature Sensor: Detects smoke, specific gases, or abnormal temperatures to confirm fire or hazardous conditions. GPS module: Provides location data (latitude, longitude, altitude) for navigation and mapping fire locations. Wi-Fi/RF/-GSM Communication module: Enables wireless communication between the drone and a ground control station or emergency services. Li-Po battery: The power source for all drone components. Power distribution board: Distributes power from the battery to the various electronic components efficiently. Camera module: Captures visual data for monitoring and assessment. Buzzer LED indicators: Provides audible and visual alert
Keywords: Internet of things, UAV (Unmanned Aerial Vehicle), sensors, real time monitering.
Quadcopter drone frame: The physical structure or chassis of the drone that holds all other components. Brushless DC motor with propellers: Provides the necessary thrust and propulsion for the drone to fly. Electronic speed controllers (ESC's): Regulates the speed and direction of the motors based on signals from the flight controller. Flight controller (Pixhawk/KK/NAZA): The "brain" of the drone, processing inputs from sensors and the user to stabilize and control flight. Microcontroller (Arduino/Raspberry Pi): An additional small computer used for processing sensor data or managing specific payloads. Thermal camera or flame sensor: Detects heat signatures or the presence of a flame to identify fire locations. Smoke/Gas sensor, Temperature Sensor: Detects smoke, specific gases, or abnormal temperatures to confirm fire or hazardous conditions. GPS module: Provides location data (latitude, longitude, altitude) for navigation and mapping fire locations. Wi-Fi/RF/-GSM Communication module: Enables wireless communication between the drone and a ground control station or emergency services. Li-Po battery: The power source for all drone components. Power distribution board: Distributes power from the battery to the various electronic components efficiently. Camera module: Captures visual data for monitoring and assessment. Buzzer LED indicators: Provides audible and visual alert
Keywords: Internet of things, UAV (Unmanned Aerial Vehicle), sensors, real time monitering.
Abstract
IOT BASED GAS LEAKAGE DETECTION AND AUTOMATION CONTROL
B. Suresh reddy, B. Rohith Kumar, Muskaan, G. Rufus, B. Vignan
DOI: 10.17148/IJIREEICE.2026.14318
Abstract: Industrial gas leakage poses serious risks to human life, industrial assets, and the environment. Accidental leakage of toxic or combustible gases can lead to catastrophic events such as explosions, fires, equipment damage, and severe health hazards to workers. Therefore, early detection, continuous monitoring, and rapid control of gas leaks are essential to ensure industrial safety and minimize potential losses. This project, titled “IoT-Based Industrial Gas Leakage Detection & Automated Control,” proposes an intelligent, automated, and reliable system for real-time detection and management of hazardous gas leakage in industrial environments.
The proposed system employs sensitive gas sensors to continuously monitor the presence and concentration of harmful gases in the surrounding atmosphere. The sensor data is processed by a microcontroller equipped with internet connectivity. When the detected gas concentration exceeds a predefined safety threshold, the system immediately initiates automated safety actions. These actions include activating audible and visual alarms to alert nearby personnel and closing the gas supply through a servo motor-controlled valve to prevent further leakage. This automated response significantly reduces the dependency on manual intervention and minimizes reaction time during emergency situations.
In addition to local safety measures, the system integrates Internet of Things (IoT) technology to provide real-time monitoring and remote accessibility. Gas concentration data, system status, and emergency alerts are transmitted to a cloud-based IoT platform and can be accessed through a web or mobile application. This enables industry operators and safety authorities to monitor conditions remotely, analyze data trends, and take timely preventive or corrective actions even from distant locations.
The proposed system is designed to be cost-effective, energy-efficient, and easy to implement, making it suitable for both small-scale and large-scale industrial setups. By combining sensing, automation, and IoT-based communication, the system enhances workplace safety, reduces the risk of industrial accidents, and improves overall operational reliability. The solution can be effectively deployed in chemical plants, oil refineries, gas pipelines, storage facilities, manufacturing industries, and other hazardous environments where gas leakage detection and control are critical.
The proposed system employs sensitive gas sensors to continuously monitor the presence and concentration of harmful gases in the surrounding atmosphere. The sensor data is processed by a microcontroller equipped with internet connectivity. When the detected gas concentration exceeds a predefined safety threshold, the system immediately initiates automated safety actions. These actions include activating audible and visual alarms to alert nearby personnel and closing the gas supply through a servo motor-controlled valve to prevent further leakage. This automated response significantly reduces the dependency on manual intervention and minimizes reaction time during emergency situations.
In addition to local safety measures, the system integrates Internet of Things (IoT) technology to provide real-time monitoring and remote accessibility. Gas concentration data, system status, and emergency alerts are transmitted to a cloud-based IoT platform and can be accessed through a web or mobile application. This enables industry operators and safety authorities to monitor conditions remotely, analyze data trends, and take timely preventive or corrective actions even from distant locations.
The proposed system is designed to be cost-effective, energy-efficient, and easy to implement, making it suitable for both small-scale and large-scale industrial setups. By combining sensing, automation, and IoT-based communication, the system enhances workplace safety, reduces the risk of industrial accidents, and improves overall operational reliability. The solution can be effectively deployed in chemical plants, oil refineries, gas pipelines, storage facilities, manufacturing industries, and other hazardous environments where gas leakage detection and control are critical.
Abstract
IOT BASED SMART MEDICATION REMINDER AND HEALTH ALERT SYSTEM
MD.Amjad, K. Sushma, M. Rajesh, V. Sathvika, B. Anil
DOI: 10.17148/IJIREEICE.2026.14319
Abstract: Many patients forget to take medicines on time due to busy schedules, aging, or memory problems. Missing medication doses can lead to serious health complications and ineffective treatment. The Smart Medication Reminder and Health Alert System is designed to assist patients in maintaining their medication schedule using IoT technology. The system uses a microcontroller with sensors, buzzer alerts, and IoT communication to notify patients when it is time to take their medicine. If the patient ignores the alert, notifications can be sent to caregivers. The system also monitors health parameters such as body temperature or heart rate and generates emergency alerts if abnormal conditions are detected. This solution improves medication adherence, enhances patient safety, and enables real-time monitoring through IoT platforms
Keywords: IoT (Internet of Things), Smart Medication Reminder, Health Monitoring System, Microcontroller, Sensors, Buzzer Alert, Real-Time Monitoring, Smart Healthcare, Automation, Patient Safety.
Keywords: IoT (Internet of Things), Smart Medication Reminder, Health Monitoring System, Microcontroller, Sensors, Buzzer Alert, Real-Time Monitoring, Smart Healthcare, Automation, Patient Safety.
Abstract
SMART RAILWAY SIGNAL AND GATE AUTOMATION FOR ROAD VEHICLE SAFETY
DR. B. Veeru, S. Meghana, K. Arun Kumar, P. Rahul, K. Pavan Kumar
DOI: 10.17148/IJIREEICE.2026.14320
Abstract: The Smart Railway Signal and Gate Automation System for Road Vehicle Safety is designed to reduce accidents at railway level crossings and improve safety for both trains and road vehicles. Many railway crossing accidents occur due to human error, delayed gate operation, or lack of proper warning systems. This project aims to solve these problems by using automated technology to control railway signals and crossing gates.
The system uses sensors and a microcontroller to detect the arrival and departure of a train near the railway crossing. When a train approaches the crossing, the sensors send a signal to the control unit, which automatically activates warning lights and alarms for road vehicles and closes the gate to stop traffic. After the train safely passes the crossing, the system automatically opens the gate and resets the signals, allowing road vehicles to move again.
This automation helps to eliminate manual operation, reduce delays, and prevent accidents caused by negligence or miscommunication. The system ensures timely gate closure and opening, providing a safer environment for road users and railway operations.
The system uses sensors and a microcontroller to detect the arrival and departure of a train near the railway crossing. When a train approaches the crossing, the sensors send a signal to the control unit, which automatically activates warning lights and alarms for road vehicles and closes the gate to stop traffic. After the train safely passes the crossing, the system automatically opens the gate and resets the signals, allowing road vehicles to move again.
This automation helps to eliminate manual operation, reduce delays, and prevent accidents caused by negligence or miscommunication. The system ensures timely gate closure and opening, providing a safer environment for road users and railway operations.
Abstract
Real Time Monitoring of Mining and Connected Workers
E. Sajjan, A. Shruthi, Ch. SaiTeja, G. Aakash, J. SaiKiran
DOI: 10.17148/IJIREEICE.2026.14321
Abstract: Mining operations are inherently hazardous, requiring continuous monitoring of both environmental conditions and worker safety. This paper presents a real-time monitoring framework that integrates IoT-enabled sensors, wireless communication, and cloud-based analytics to ensure the safety and productivity of connected workers in mining environments. The proposed system captures critical parameters such as gas concentration, temperature, vibration, and worker location, transmitting data to a centralized platform for immediate analysis. Alerts and predictive insights are generated to prevent accidents, optimize resource allocation, and enhance decision-making. By leveraging real-time connectivity, the framework not only improves occupational safety but also contributes to sustainable mining practices. The results demonstrate that integrating smart monitoring technologies can significantly reduce risks, increase operational efficiency, and establish a reliable safety network for workers in complex mining scenarios.
Abstract
INDUSTRIAL AIR QUALITY AND NOISE POLLUTION MONITORING SYSTEM
DR. K. Kumara Swamy, K. Vishnu Sahasru, B. Vamshi, M. Venkat Rama Krishna, MD. Aslam Mohiuddin
DOI: 10.17148/IJIREEICE.2026.14322
Abstract: Environmental pollution has become one of the most critical challenges in modern society due to rapid industrialization, urban expansion, population growth, and increased use of fossil fuels. Among the various forms of pollution, air pollution and noise pollution are the most prevalent and harmful, as they directly affect human health, workplace safety, and environmental sustainability. Poor air quality caused by the presence of toxic gases and particulate matter can lead to serious health issues such as respiratory diseases, asthma, and cardiovascular disorders. Similarly, prolonged exposure to high noise levels in industrial environments can result in hearing impairment, mental stress, fatigue, and reduced productivity. Therefore, continuous monitoring of air quality and sound levels is essential to ensure safe and healthy working conditions. The Industrial Air Quality and Noise Pollution Monitoring System is designed to provide an efficient and reliable solution for detecting harmful environmental conditions in real time. The system is built using the ESP32 microcontroller, which serves as the central processing unit responsible for acquiring, processing, and analyzing sensor data. An MQ-2 gas sensor is used to detect the presence of combustible and hazardous gases such as LPG, smoke, and other volatile gases, while a sound sensor continuously measures ambient noise levels. These sensors collect environmental data and send it to the ESP32 for analysis and comparison with predefined safety threshold
Abstract
IOT – POWERED ADAPTIVE LIGHTING SYSTEM FOR INDUSTRIAL FACILITIES
Dr. S. Chandrashekhar Reddy, G. Vaishnavi, MD. Abdul Muqeet, R. Ram Charan, V. Hussain
DOI: 10.17148/IJIREEICE.2026.14323
Abstract: Industrial facilities require continuous lighting for safe and efficient operations. Traditional lighting systems usually rely on manual switches or fixed schedules, which often leads to unnecessary energy consumption and inefficient lighting utilization. To overcome these limitations, an IoT-powered adaptive lighting system can be implemented.
The proposed system uses sensors such as occupancy sensors and ambient light sensors to detect human presence and natural lighting conditions. Based on this real-time data, a microcontroller automatically adjusts the brightness of industrial LED lights. The system also enables remote monitoring and control through IoT platforms and cloud services.
This approach significantly reduces energy consumption, improves safety, and enhances operational efficiency in industrial environments. Additionally, the system supports data analytics and centralized monitoring, making it suitable for smart industrial facilities.
Keywords: IoT, Adaptive Lighting, Industrial Automation, Energy Efficiency, Sensors, Smart Lighting.
The proposed system uses sensors such as occupancy sensors and ambient light sensors to detect human presence and natural lighting conditions. Based on this real-time data, a microcontroller automatically adjusts the brightness of industrial LED lights. The system also enables remote monitoring and control through IoT platforms and cloud services.
This approach significantly reduces energy consumption, improves safety, and enhances operational efficiency in industrial environments. Additionally, the system supports data analytics and centralized monitoring, making it suitable for smart industrial facilities.
Keywords: IoT, Adaptive Lighting, Industrial Automation, Energy Efficiency, Sensors, Smart Lighting.
Abstract
IOT BASED SMART PARKING AND VEHICLE MANAGEMENT SYSTEM FOR INDUSTRIAL CAMPUS
Y. Vijay Jawahar Paul, A. Saikiran, K. Sagar, S. Sandhya Rani, S. Abhinay
DOI: 10.17148/IJIREEICE.2026.14324
Abstract: Parking has become a major issue in modern smart cities due to the rapid increase in the number of vehicles. Drivers often spend a significant amount of time searching for available parking spaces, especially in busy commercial areas, shopping complexes, and educational institutions. This situation leads to traffic congestion, fuel wastage, environmental pollution, and driver frustration. Traditional parking systems mostly depend on manual monitoring and do not provide real-time information about parking availability. Because of this, the process of finding parking spaces becomes inefficient and time-consuming for both users and parking management authorities.
Keywords: IoT (Internet of Things), Smart Parking and vehicle management system for industrial campus
Keywords: IoT (Internet of Things), Smart Parking and vehicle management system for industrial campus
Abstract
IOT BASED WORKERS SAFETY HELMET WITH REAL TIME HEALTH MONITORING
P. Prabakar, Ch. Pravalika, K. Sravanthi, Y. Samatha, E. Deena, N. Kalyani
DOI: 10.17148/IJIREEICE.2026.14325
Abstract: The safety of workers in hazardous environments such as mining, construction, and manufacturing industries is a major concern. Traditional helmets provide only physical protection and cannot monitor the worker’s health condition or environmental hazards. This project proposes an IoT-based smart safety helmet that continuously monitors the worker’s health parameters and surrounding environment using sensors and IoT communication. Sensors such as heart rate sensor, temperature sensor, gas sensor, and motion sensor are integrated with a microcontroller like ESP32. The collected data is transmitted to an IoT cloud platform for real-time monitoring.
Keywords: IoT, Smart Helmet, Worker Safety, Health Monitoring, Gas Sensor, Real-Time Monitoring
Keywords: IoT, Smart Helmet, Worker Safety, Health Monitoring, Gas Sensor, Real-Time Monitoring
Abstract
Sericulture Automation System Climate Control And Production Efficiency
B. Sandeep Kumar, P. Vyshnavi, Sana, Y. Rahul Kumar, N. Pranay
DOI: 10.17148/IJIREEICE.2026.14326
Abstract: Sericulture denotes to the rearing of silkworm to produce silk. Parameters like Temperature, Humidity and Light intensity are the important factors in the progression of silkworms and suitable encouraging must to be done according to the requisites in every stage. Sericulture is the process of nurturing silkworm to produce silk. Many biotic and abiotic factors are responsible for growth and development of silkworm and successful crop harvest. Modernization with introduction of new technologies is the only alternative to mitigate the limitations of traditional labour intensive sericulture practices and to enhance silk production. Artificial intelligence with IoT will benefit the progress of silkworm and host plant sector by maintaining temperature, humidity and other related factors. Remote sensing technique is arising as a suitable tool for identification of favourable sites for plantation. Environmental variations assume as the important part in the growth and development of silkworm. Sericulture is the important occupation in India and the techniques used by the agriculturists are yet outdated. Hereafter there is the need of developing modernization in sericulture cultivate. This endeavor gives a thought of providing automation in sericulture cultivate. The model goals at making use of developing technology that is IOT and smart Sericulture using automation
Keywords: Nodemcu ESP8266 Microcontroller, Relay, DHT11 sensor, Fan, Bulb, Water pump.
Keywords: Nodemcu ESP8266 Microcontroller, Relay, DHT11 sensor, Fan, Bulb, Water pump.
Abstract
Smart Incubator for Poultry farming
B. Sandeep Kumar, P. Udayasri, P. Shivashankar, E. Saikumar, G. Vishal
DOI: 10.17148/IJIREEICE.2026.14327
Abstract: The Smart Incubator for Poultry Farming is designed exclusively for raising chicks, providing a controlled environment that ensures their healthy growth and survival. Unlike conventional incubators or brooding methods, this system focuses solely on post-hatch chick care by maintaining precise temperature and humidity levels, which are critical factors for chick development. Equipped with temperature and humidity sensors, the incubator continuously monitors the internal environment. The NodeMCU microcontroller processes the sensor data and automatically adjusts the heating, cooling, and ventilation systems to maintain optimal conditions. Proper temperature control prevents chilling or overheating, while maintaining humidity ensures hydration and reduces stress, improving the overall health and immunity of chicks.
Keywords: Power supply, Arduino Uno, L293D, LCD, BO motor, Buzzer, MQ3
Keywords: Power supply, Arduino Uno, L293D, LCD, BO motor, Buzzer, MQ3
Abstract
Performance Assessment of Machine Learning Models for Network Anomaly Detection: A Case Study with CICIDS2017
Tawo Godwin A, Osahon Okoro, Aigberemhon Moses E, Ojomu Sunday A, Etim Bassey E
DOI: 10.17148/IJIREEICE.2026.14328
Abstract: Detecting anomalies in network traffic is critical for mitigating zero-day attacks and unauthorized intrusions in real-time. This study presents a comparative evaluation of four unsupervised machine learning models—Isolation Forest, One-Class Support Vector Machine (SVM), K-Means Clustering, and Local Outlier Factor (LOF)—using the benchmark CICIDS2017 dataset comprising over 2.8 million labeled records. To address memory constraints and ensure scalability, a batch-wise processing approach was adopted. The models were assessed based on standard classification metrics: precision, recall, F1-score, and accuracy. Results show that Isolation Forest achieved the most balanced performance with an F1-score of 0.59, while One-Class SVM recorded high precision (0.41) but lower recall. K-Means demonstrated strong recall (0.77) but at the expense of precision (0.14), whereas LOF underperformed across all metrics. Visual analytics, including PCA projections and anomaly score distributions, further supported the quantitative findings. This work contributes a practical framework for evaluating unsupervised models under resource constraints and offers insights for deploying anomaly detection systems in real-world network environments.
Keywords: Anomaly detection, Machine learning, CICIDS2017, Isolation Forest, One-Class SVM, K-Means, LOF, Network intrusion detection
Keywords: Anomaly detection, Machine learning, CICIDS2017, Isolation Forest, One-Class SVM, K-Means, LOF, Network intrusion detection
Abstract
IOT BASED FAULT DETECTION SYSTEM IN TRANSMISSION LINES
V. ABHINAV, V MAHESH BABU, N. VEERA SIMHA REDDY, K. RAVI TEJA, Dr.G.GANTHAIAH SWAMY
DOI: 10.17148/IJIREEICE.2026.14330
Abstract: The project's main objective is to design and implement automatic problem detection and location identification in transmission lines, as well as monitoring using the internet of things. Two single phase 230V transmission lines are being built for demonstration purposes, with continuous monitoring of the microcontroller's fault sensing. A sophisticated GSM-based defect detection and localization system was deployed to quickly and accurately pinpoint the precise spot where the problem had developed. The system provides precise fault location information, significantly cutting down on the time required to locate a flaw.
Keywords: Microcontroller (Arduino UNO / Nano / ESP32), Current Sensor (CT + burden / ACS712), Voltage Sensor Module, Fault Simulation Switches (L–G, L–L, L–L–G), Relay Module (Load isolation), LCD (16×2) / OLED, Buzzer (optional), GSM / IoT Module (SIM800 / ESP8266), Power Supply (12V → 5V regulated), Connecting wires & breadboard / PCB.
Keywords: Microcontroller (Arduino UNO / Nano / ESP32), Current Sensor (CT + burden / ACS712), Voltage Sensor Module, Fault Simulation Switches (L–G, L–L, L–L–G), Relay Module (Load isolation), LCD (16×2) / OLED, Buzzer (optional), GSM / IoT Module (SIM800 / ESP8266), Power Supply (12V → 5V regulated), Connecting wires & breadboard / PCB.
Abstract
Automated Factory Gate Control and Vehicle Counting System Using IOT
E. Sajjan, B. Ananya, S. Shiva Raj, B. Pawan Kalyan, S. Nalin Prabhath
DOI: 10.17148/IJIREEICE.2026.14331
Abstract: The Automated Factory Gate Control and Vehicle Counting System using Internet of Things (IoT) is designed to enhance security, efficiency, and monitoring in industrial environments. The system automates the opening and closing of factory gates based on vehicle detection and simultaneously counts the number of vehicles entering and exiting the premises. It utilizes sensors such as IR sensors to detect vehicle movement and a NodeMCU (ESP8266) microcontroller to process the data. The collected information is transmitted to a cloud platform via Wi-Fi, enabling real-time monitoring and data access through a mobile application or web interface. This system reduces the need for manual supervision, minimizes human error, and improves operational efficiency. Additionally, it provides accurate vehicle count data, which can be used for analysis, security management, and traffic control within the factory premises. The proposed solution is cost-effective, scalable, and suitable for modern smart industrial applications.
Abstract
Intelligent Bus Monitoring and Alert System Based on IoT
K. Amarender, K Raju, M Manoj, S. Manoj Kumar, S. Manu
DOI: 10.17148/IJIREEICE.2026.14332
Abstract: In the era of smart transportation, ensuring the safety, efficiency, and accountability of public transit systems has become a critical challenge. This project introduces an Intelligent Bus Monitoring and Alert System that leverages advanced Internet of Things (IoT) technologies to provide real-time surveillance, a anomaly detection, and automated alerting for public buses. The system is designed to address key issues such as unauthorized access, route deviations, overcrowding, and emergency response delays— common problems in conventional bus operations. The proposed solution integrates multiple sensors including GPS modules for location tracking, infrared (IR)sensors for passenger movement detection, and vibration sensors for accident or tampering detection. These sensors are interfaced with a Raspberry Pi microcontroller, which performs edge-level data processing and communicates with a cloud-based dashboard for centralized monitoring. In case of any irregular activity—such as a sudden stop, excessive vibration, or deviation from the assigned route.
The architecture supports scalability, low power consumption, and modular integration with existing fleet management systems. It also enables remote diagnostics, data logging, and predictive analytics for maintenance and operational optimization. Experimental Simulations demonstrate the system’s ability to detect anomalies with high accuracy, minimize false positives, and maintain robust performance under varied environmental and traffic conditions.
The architecture supports scalability, low power consumption, and modular integration with existing fleet management systems. It also enables remote diagnostics, data logging, and predictive analytics for maintenance and operational optimization. Experimental Simulations demonstrate the system’s ability to detect anomalies with high accuracy, minimize false positives, and maintain robust performance under varied environmental and traffic conditions.
Abstract
SMART PARKING MANAGEMENT SYSTEM
E. Sajjan, M. Shivaleela, T. Priyanka, L. Praveen, S. Sanjay
DOI: 10.17148/IJIREEICE.2026.14333
Abstract: The Smart Parking Management System using IoT is a transformative solution aimed at revolutionizing urban mobility and infrastructure. By deploying a network of IoT sensors across parking lots, the system continuously monitors the occupancy status of each bay and transmits this data to a cloud-based server. This enables real-time updates that users can access through a mobile application, helping them identify available spots, reserve them, and navigate directly to the location. The system also incorporates automated payment gateways, license plate recognition, and dynamic pricing models to streamline the entire parking experience. On the backend, administrators can analyze usage trends, peak hours, and maintenance needs through data analytics dashboards, allowing for smarter decision- making and resource allocation. Beyond convenience, the system contributes to environmental sustainability by reducing fuel consumption and emissions caused by vehicles idling or circling for parking. It also alleviates traffic congestion and enhances safety by minimizing roadside chaos. As cities evolve into smart ecosystems, this IoT-based parking solution stands as a critical component in building efficient, responsive, and user-centric urban environments.
Keywords: Power supply, ESP32 Microcontroller, IR Sensor, OLED Display, Servo MotorⅠ.
Keywords: Power supply, ESP32 Microcontroller, IR Sensor, OLED Display, Servo MotorⅠ.
Abstract
EV DYNAMIC WIRELESS CHARGING ON ROADS
L. Karunakar, Y. Naveen Kumar
DOI: 10.17148/IJIREEICE.2026.14334
Abstract: The dynamic wireless charging roads project focuses on the development and implementation of an innovative infrastructure to enable electric vehicles (EVs) to charge while in motion. Traditional stationary charging methods present challenges such as long charging times and limited range, especially for heavy- duty and long-distance EVs. This project proposes a solution based on dynamic inductive wireless charging (DWIC) systems embedded in roadways, allowing continuous power transfer to vehicles without the need for frequent stops. The system uses electromagnetic fields generated by inductive charging pads embedded in road surfaces to charge vehicles while they drive. This technology reduces the dependency on large onboard batteries, promotes sustainable transportation, and potentially reduces grid load by enabling efficient energy use. The research also explores the integration of smart technologies for managing power distribution, ensuring safety, and enhancing energy efficiency. Furthermore, this project assesses the feasibility, economic implications, environmental benefits, and scalability of dynamic wireless charging for future transportation systems. The project could revolutionize transportation infrastructure, making electric vehicles more practical, reducing environmental impact, and supporting the transition to sustainable energy sources.
Keywords: Dynamic Wireless Charging, Inductive Charging, Electric Vehicles (EVs), Wireless Power Transfer (WPT), Smart Infrastructure, Sustainable Transportation, Energy Efficiency, Road Electrification, Infrastructure Integration, Vehicle-to-Grid (V2G).
Keywords: Dynamic Wireless Charging, Inductive Charging, Electric Vehicles (EVs), Wireless Power Transfer (WPT), Smart Infrastructure, Sustainable Transportation, Energy Efficiency, Road Electrification, Infrastructure Integration, Vehicle-to-Grid (V2G).
Abstract
IOT BASED BOILER TEMPERATURE AND PRESSURE MONITORING SYSTEM
B. Hanumanthu, G. Ramya, G. Vanaja, K. Saipranay, T. Harshith Kumar
DOI: 10.17148/IJIREEICE.2026.14335
Abstract: Boilers are widely used in industries such as The proposed system integrates temperature and pressure sensors with a microcontroller unit connected to the internet. Sensor data is continuously collected and transmitted to a cloud platform such as ThingSpeak for storage, visualization, and analysis. Users can monitor boiler parameters remotely through a web or mobile interface, enabling early detection of faults and abnormal variations. The system also supports alert notifications when the parameters exceed predefined safety thresholds.
power plants, food processing, and manufacturing, where maintaining safe temperature and pressure levels is critical for efficient operation and accident prevention. Traditional boiler monitoring methods often rely on manual inspection, which can lead to delays in detecting abnormal conditions. This paper presents an Internet of Things (IoT) based boiler temperature and pressure monitoring system designed to provide real-time data monitoring, remote access, and improved safety.
Traditional boiler monitoring relied on manual checks and analog gauges, which were prone to delays and errors. Modern IoT-based systems overcome these limitations by enabling continuous tracking, remote access, and instant alerts. This project builds on these advancements, combining proven components into a compact, cost-effective solution for smart boiler monitoring.
power plants, food processing, and manufacturing, where maintaining safe temperature and pressure levels is critical for efficient operation and accident prevention. Traditional boiler monitoring methods often rely on manual inspection, which can lead to delays in detecting abnormal conditions. This paper presents an Internet of Things (IoT) based boiler temperature and pressure monitoring system designed to provide real-time data monitoring, remote access, and improved safety.
Traditional boiler monitoring relied on manual checks and analog gauges, which were prone to delays and errors. Modern IoT-based systems overcome these limitations by enabling continuous tracking, remote access, and instant alerts. This project builds on these advancements, combining proven components into a compact, cost-effective solution for smart boiler monitoring.
Abstract
Thermoelectric Generator Module in Driving the Vehicle and Monitoring using IoT
Ms. B. Sruthi, K. Ganesh Kumar
DOI: 10.17148/IJIREEICE.2026.14336
Abstract: This paper presents a thermoelectric generator (TEG)-based system for driving a vehicle and monitoring performance using IoT technology. A significant portion of energy in automobiles is lost as waste heat, which can be converted into useful electrical energy using TEG modules based on the Seebeck effect.
Keywords: Thermoelectric Generator (TEG), Waste Heat Recovery, Seebeck Effect, IoT Monitoring, ESP32, DC–DC Boost Converter, Energy Efficiency
Keywords: Thermoelectric Generator (TEG), Waste Heat Recovery, Seebeck Effect, IoT Monitoring, ESP32, DC–DC Boost Converter, Energy Efficiency
Abstract
IOT ASSISTED ELEVATOR AUTOMATION WITH REAL TIME STATUS VISUALIZATION
V. Phani Kumar, J. Ram Prasad, B. Shadrak, J. Kalyan, Mr. M. Rama Krishna
DOI: 10.17148/IJIREEICE.2026.14337
Abstract: This project presents an IoT-based elevator automation system with three control modes: manual buttons, mobile application control using MIT App Inventor, and voice command operation. An Arduino Uno and HC-05 Bluetooth module enable communication and control. The system uses IR sensors for floor detection and an LCD for real-time status display. It is cost-effective, user-friendly, and improves accessibility through multiple control methods.
Keywords: IoT Elevator Automation, Arduino Uno, MIT App Inventor, Voice Control, Bluetooth Module.
Keywords: IoT Elevator Automation, Arduino Uno, MIT App Inventor, Voice Control, Bluetooth Module.
Abstract
IoT Based Undervoltage and Overvoltage Protection System
Ms. B. Sruthi, Ch. Ajay
DOI: 10.17148/IJIREEICE.2026.14338
Abstract: Electrical equipment is highly sensitive to voltage variations such as overvoltage and undervoltage, which may cause severe damage, reduced efficiency, and safety risks. To overcome this problem, this project proposes an IoT-based voltage monitoring and protection system using the ESP32 microcontroller. In the proposed system, an AC voltage sensor and AC current sensor continuously measure the electrical parameters of the supply.
Keywords: IoT, ESP32, Overvoltage Protection, Undervoltage Protection, Voltage Monitoring, Relay Module
Keywords: IoT, ESP32, Overvoltage Protection, Undervoltage Protection, Voltage Monitoring, Relay Module
Abstract
MorphosETL: A Schema-Grounded, Confidence-Gated LLM-Assisted No-Code ETL System
Mohan Raj R, Srinisha P, Mohamed Athfan D
DOI: 10.17148/IJIREEICE.2026.14339
Abstract: This paper presents MorphosETL, a schema- grounded, confidence-gated LLM-assisted no-code ETL automa- tion platform designed to convert natural language transfor- mation instructions into secure and executable data pipelines. Traditional ETL systems require programming expertise and manual configuration, creating a barrier for non-technical users. MorphosETL addresses this limitation through a dual-pipeline architecture that supports both structured data (CSV, Excel, and database extracts) and unstructured data (web URLs and API responses) within a unified framework. The system integrates schema-aware transformation planning, multi-language code generation (Python/Polars, SQL/DuckDB, PySpark), and a four-dimensional confidence scoring mechanism that validates correctness, safety, and logical completeness before execution. Experimental evaluation demonstrates high transformation accu- racy, linear performance scalability, and complete prevention of unsafe execution. The proposed architecture enables reliable, accessible, and intelligent ETL automation suitable for data analysts, engineers, and domain experts.
Keywords: ETL Automation, No-Code ETL, Large Language Models, Schema-Aware Transformation, Confidence Scoring, Data Profiling, Polars, DuckDB, Natural Language Processing, Web Data Extraction
Keywords: ETL Automation, No-Code ETL, Large Language Models, Schema-Aware Transformation, Confidence Scoring, Data Profiling, Polars, DuckDB, Natural Language Processing, Web Data Extraction
Abstract
SMART GARBAGE MONITORING AND MANHOLE OPEN ALERT SYSTEM
T. Krishna Mohan, P. Rakada Kumar, S. Tharun
DOI: 10.17148/IJIREEICE.2026.14340
Abstract: The Smart Dustbin tool is a modern, Internet of Things-based waste management answer meant to enhance urban sanitation and maximize garbage collection techniques. An ESP32 microcontroller, ultrasonic sensors, and an SMTP server are all incorporated into the system to show waste tiers in actual time and send out notifications while boxes need to be emptied. This goal contributes to a higher hygienic surroundings through automating trash tracking, which lowers manual tough paints, decreases overflow issues, and guarantees well timed disposal. Conventional waste series adheres to set timetables, which regularly result in inefficiencies, pointless round trips, or late pickups. One option to the troubles is the Smart Dustbin technology, which lowers working prices by using dynamically notifying waste control authorities while a bin fills up. And the effect at the surroundings. Furthermore, the gadget's modular design permits seamless scalability and interaction with imaginitive town sports. Future traits may also include sun-powered operation for extended sustainability, cell software integration for realtime tracking, and AI-primarily based absolutely predictive analytics for most advantageous waste collection making plans. This tool is a step forward in growing higher, purer, and extra green nearby trash manipulation techniques by utilising IoT era. Keywords: ESP32, waste management, automation, clever dustbins, IoT, and ultrasonic sensors
Keywords: Car park system, intelligent transportation system, parking technology, smart parking system
Keywords: Car park system, intelligent transportation system, parking technology, smart parking system
Abstract
Real-Time Water Purity Monitoring Using Arduino
Mr. Shahaji Sutar, Aarnav Lokhande, Ruturaj Jankar, Viraj Badadare, Sagar More, Jay Dhanawde
DOI: 10.17148/IJIREEICE.2026.14341
Abstract: Water quality monitoring is essential for ensuring safe drinking water and protecting public health. Traditional methods of testing water quality are often time-consuming and require laboratory analysis. This paper presents a real- time water purity monitoring system using an Arduino-based embedded platform. The system employs a Total Dissolved Solids (TDS) sensor to measure the concentration of dissolved particles in water and assess its purity level.The measured TDS values are displayed on an LCD screen and also transmitted via a Bluetooth module for remote monitoring. An alert mechanism using LEDs and a buzzer is incorporated to indicate safe and unsafe water conditions based on predefined threshold levels. The system continuously monitors water quality and provides instant feedback to the user.The proposed system is cost-effective, portable, and easy to use, making it suitable for household and environmental monitoring applications.
Keywords: Water Quality Monitoring, Arduino, TDS Sensor, Real-Time Monitoring, Water Purity, Embedded System, Bluetooth Communication, IoT
Keywords: Water Quality Monitoring, Arduino, TDS Sensor, Real-Time Monitoring, Water Purity, Embedded System, Bluetooth Communication, IoT
Abstract
IOT BASED SMART PARKING SYSTEM
Dr. G. Gantaiah Swami, P. Sai Charan, S. Lakshmi Narasimha
DOI: 10.17148/IJIREEICE.2026.14342
Abstract: Due to the proliferation in the number of vehicles on the road, traffic problems are bound to exist. This is due to the fact that the current transportation infrastructure and car park facility developed are unable to cope with the influx of vehicles on the road. To alleviate the aforementioned problems, the smart parking system has been developed. With the implementation of the smart parking system, patrons can easily locate and secure a vacant parking space at any car park deemed convenient to them. Vehicle ingress and egress are also made more convenient with the implementation of hassle free payment mechanism. With vehicle detection sensors aplenty on the market, the choices made may defer due to the different requirements in addition to the its pros and cons. Subsequently, the various sensor systems used in developing the systems in addition to the recent research and commercial system on the market are examined as vehicle detection plays a crucial role in the smart parking system.
Keywords: Car park system, intelligent transportation system, parking technology, smart parking system
Keywords: Car park system, intelligent transportation system, parking technology, smart parking system
Abstract
Street Light Fault Detection And Energy Monitoring System
Mr. L. Karunakar, M.Tech, E. Divya Sai Teja
DOI: 10.17148/IJIREEICE.2026.14343
Abstract: Street lighting plays a vital role in modern urban infrastructure by improving road visibility, ensuring pedestrian safety, and supporting nighttime transportation activities. However, traditional street lighting systems operate with limited automation and lack proper monitoring mechanisms, which often leads to excessive energy consumption, delayed fault detection, and increased maintenance costs.
Keywords: IoT, ESP32, Street Light Fault Detection, Energy Monitoring, Smart Street Lighting, Fault Detection System
Keywords: IoT, ESP32, Street Light Fault Detection, Energy Monitoring, Smart Street Lighting, Fault Detection System
Abstract
Railway Track Crack Detection and Automatic Gate Control System
Ch. Maheswara Rao, Sk. Mastan, P. Venkata Gandhi, Ms. Chandhni Sri Lakshmi M.Tech
DOI: 10.17148/IJIREEICE.2026.14344
Abstract: Railway transportation is a vital mode of transport, but safety remains a major concern due to track failures and manual gate operations. This paper presents the design and implementation of a Railway Track Crack Detection and Automatic Gate Control System using embedded technology. The proposed system uses sensors to continuously monitor the condition of railway tracks and detect cracks in real time. When a crack is detected, an alert is generated to prevent possible accidents. Additionally, the system incorporates automatic gate control using IR sensors to detect the arrival and departure of trains, thereby reducing human intervention. An Arduino-based microcontroller is used to process sensor data and control the entire system efficiently. The system is cost-effective, reliable, and suitable for real- time applications. Experimental results demonstrate that the system provides accurate crack detection and timely gate operation, significantly improving railway safety and operational efficiency.
Abstract
IoT Accident Detection & Smart Emergency Response System
K. Amarender, P. Pavithra, B. Supriya, M. Navya, V. Srikanth
DOI: 10.17148/IJIREEICE.2026.14345
Abstract: The rapid increase in road accidents has become a major global concern, often resulting in severe injuries or fatalities due to delayed emergency response and drunk driving. To address these challenges, this project proposes an IoT-based Accident Detection and Smart Emergency Response System integrated with Alcohol Detection. The system uses a vibration sensor to detect sudden vehicle impacts or tilts that may indicate an accident. Simultaneously, an MQ3 alcohol sensor monitors the driver’s breath for alcohol concentration.
If the detected level exceeds a preset threshold, the system automatically disables the vehicle ignition and sends an alert message to registered contacts, preventing the driver from operating the vehicle under the influence. In the event of a collision, the GPS module determines the exact location, and the GSM module sends an SMS alert containing the coordinates to emergency services and family members. The system can also be integrated with IoT cloud platforms for real-time monitoring.
This combination of accident detection, alcohol prevention, and automated emergency response ensures faster medical assistance and enhances road safety. The proposed system is cost-effective, reliable, and suitable for integration in both personal and commercial vehicles.
If the detected level exceeds a preset threshold, the system automatically disables the vehicle ignition and sends an alert message to registered contacts, preventing the driver from operating the vehicle under the influence. In the event of a collision, the GPS module determines the exact location, and the GSM module sends an SMS alert containing the coordinates to emergency services and family members. The system can also be integrated with IoT cloud platforms for real-time monitoring.
This combination of accident detection, alcohol prevention, and automated emergency response ensures faster medical assistance and enhances road safety. The proposed system is cost-effective, reliable, and suitable for integration in both personal and commercial vehicles.
Abstract
CONTACTLESS POWER TRANSFER FOR ROTATING APPLICATIONS USING MAGNETIC COUPLE
L. Karunakar, B. Chinnu Babu
DOI: 10.17148/IJIREEICE.2026.14346
Abstract: Contactless power transfer systems are increasingly used in rotating and sealed applications where traditional wired connections and slip rings suffer from wear, sparking, and maintenance issues. This project presents a Contactless Power Transfer System for Rotating Applications using Magnetic Coupling, designed using an Arduino-based control unit. The system employs inductive magnetic coupling between a stationary transmitter coil and a rotating receiver coil separated by a small air gap. The Arduino generates a high-frequency switching signal that drives a power electronic circuit connected to the transmitter coil, producing an alternating magnetic field that enables wireless power transfer.
Keywords: Contactless Power Transfer, Magnetic Coupling, Wireless Energy Transfer, Electromagnetic Induction, Rotating Systems
Keywords: Contactless Power Transfer, Magnetic Coupling, Wireless Energy Transfer, Electromagnetic Induction, Rotating Systems
Abstract
IOT BASED ACCIDENT ALERT AND DETECTION SYSTEM
A. CHANDHNI SRI LAKSHMI, M.M.V.V. DURGA GANESH, P. NARENDRA
DOI: 10.17148/IJIREEICE.2026.14347
Abstract: This project demonstrates the effective use of embedded systems and IoT in improving vehicle safety and reducing accident-related risks. This system includes Arduino UNO, accelerometer, ultrasonic sensor, IR sensor, GPS module, WIFI module which is used to detect the occurance whether colliion is happened. if happen and abnormal disturbance the info is shared to monitoring unit and cloud platform.
Keywords: IoT, WIFI module, GPS, Accelerometer, Ultrasonic Sensor, Real-Time Monitoring, Think speak.
Keywords: IoT, WIFI module, GPS, Accelerometer, Ultrasonic Sensor, Real-Time Monitoring, Think speak.
Abstract
A Study Of Upper Arm Muscle Circumference Of Anthropometric Measurement Among Aged Group Tribal And Non-Tribal Sportsmen
Gaude Pralay Rohidas
DOI: 10.17148/IJIREEICE.2026.14348
Abstract: Anthropometric characteristics are important indicators of physical fitness and sports performance. Among these variables, upper arm muscle circumference reflects muscular development and strength of the upper limbs, which are essential for many sports activities. The purpose of the present study was to compare upper arm muscle circumference between tribal and non-tribal sportsmen of Goa with reference to age groups. A total of 100 male sportsmen were selected as subjects for the study, including 50 tribal and 50 non-tribal players from different sports disciplines in Goa. The subjects were further categorized into two age groups, namely 21–25 years and 26–30 years. Upper arm muscle circumference was measured using a standard measuring tape following accepted anthropometric procedures. The collected data were analyzed using mean, standard deviation, and independent t-test. The results indicated that non-tribal sportsmen showed slightly higher mean values of upper arm muscle circumference compared to tribal sportsmen in both age groups; however, the differences were not statistically significant at the 0.05 level of significance. The findings suggest that regular participation in sports activities contributes to similar muscular development among tribal and non- tribal athletes regardless of age group.
Keywords: Anthropometry, Upper arm circumference, Tribal athletes, Non-tribal athletes, Age groups, Sports science
Keywords: Anthropometry, Upper arm circumference, Tribal athletes, Non-tribal athletes, Age groups, Sports science
Abstract
SMART CHARGING STATION (PCB + IoT) WITH LOAD BALANCING & PREPAID BILLING
Dr. V. Anantha Lakshmi, T. Mounika
DOI: 10.17148/IJIREEICE.2026.14349
Abstract: The rapid growth of electric and electronic devices has increased the demand for efficient, safe, and intelligent charging solutions. Conventional wired charging systems suffer from limitations such as cable degradation, energy losses, and lack of user authentication, leading to inefficient power utilization. To overcome these challenges, this paper presents the design and implementation of a Smart Wireless Charging Station integrated with RFID-based prepaid billing, load balancing, and IoT-enabled monitoring.
The proposed system utilizes an Arduino Uno as the main controller and a NodeMCU module for real-time data communication with cloud platforms. Wireless power transfer is achieved using inductive coupling between transmitter and receiver coils, enabling contactless energy transfer. An RFID module ensures secure user authentication and controlled access based on prepaid balance. Additionally, an IR sensor detects device presence to prevent idle power consumption, while a voltage sensor continuously monitors system conditions to enable efficient load balancing and protection.
The system also incorporates IoT technology to provide real-time monitoring of parameters such as voltage levels, charging duration, and user activity through platforms like ThingSpeak. Experimental results demonstrate reliable authentication, efficient wireless power transfer, effective load management, and accurate data logging.
The proposed Smart Charging Station offers enhanced safety, improved energy efficiency, and user convenience, making it a suitable solution for applications in smart cities, public charging stations, and IoT-based energy management systems.
Keywords: RFID, Arduino uno Microcontroller, LCD Display, PCB, Node MCU, Wireless charging station, power transmission coils.
The proposed system utilizes an Arduino Uno as the main controller and a NodeMCU module for real-time data communication with cloud platforms. Wireless power transfer is achieved using inductive coupling between transmitter and receiver coils, enabling contactless energy transfer. An RFID module ensures secure user authentication and controlled access based on prepaid balance. Additionally, an IR sensor detects device presence to prevent idle power consumption, while a voltage sensor continuously monitors system conditions to enable efficient load balancing and protection.
The system also incorporates IoT technology to provide real-time monitoring of parameters such as voltage levels, charging duration, and user activity through platforms like ThingSpeak. Experimental results demonstrate reliable authentication, efficient wireless power transfer, effective load management, and accurate data logging.
The proposed Smart Charging Station offers enhanced safety, improved energy efficiency, and user convenience, making it a suitable solution for applications in smart cities, public charging stations, and IoT-based energy management systems.
Keywords: RFID, Arduino uno Microcontroller, LCD Display, PCB, Node MCU, Wireless charging station, power transmission coils.
Abstract
AI Based Audio Surveillance System
Ms. Aphasana Mulla, Vedanti Thakur, Anaya Kumbhar, Swanandi Sawant, Vanshika Vhatkar
DOI: 10.17148/IJIREEICE.2026.14350
Abstract: The intelligent "AI-based audio surveillance system" is very good at listening to the sounds around us. It can hear what is going on and figure out what is important. This system can tell the difference between sounds and sounds that are not normal. Even sounds like gunshots, screams, or an alarm going off can be picked up by it. The audio surveillance system works well even when we cannot see what is happening. When it hears something it will send out an alert right away. This means that people do not have to sit and listen all the time. The audio surveillance system helps us respond quickly when something bad happens. It is really helpful, during emergencies. The audio surveillance system is very useful because it can detect sound events and send alerts. Overall, AI-based audio surveillance enhances security and public safety
Abstract
Alcohol Sense Engine Locking System
Dr. G. Gantaiah Swamy, Shaik. Kodhan Saheb, P. Gowtham
DOI: 10.17148/IJIREEICE.2026.14351
Abstract: Road accidents caused by drunk driving are a major public safety concern worldwide. The Alcohol Sense Engine Locking System is designed to prevent such incidents by detecting alcohol levels in a driver’s breath and automatically disabling the vehicle’s ignition system if alcohol is detected beyond a safe limit. The system uses an MQ- 3 alcohol sensor to measure the presence of alcohol from the driver’s breath.
The sensor output is processed by a microcontroller such as Arduino Uno, which compares the detected value with a preset threshold level. If the alcohol concentration exceeds the permissible limit, the controller activates a relay module that locks the engine ignition system and triggers an alert through a buzzer and display unit. If no alcohol is detected, the engine is allowed to start normally
This system enhances road safety by preventing intoxicated individuals from operating vehicles. It is cost effective, reliable, and suitable for integration into modern vehicles as a preventive safety mechanism.
Keywords: Sensors, Real-Time Monitoring, Safety,
The sensor output is processed by a microcontroller such as Arduino Uno, which compares the detected value with a preset threshold level. If the alcohol concentration exceeds the permissible limit, the controller activates a relay module that locks the engine ignition system and triggers an alert through a buzzer and display unit. If no alcohol is detected, the engine is allowed to start normally
This system enhances road safety by preventing intoxicated individuals from operating vehicles. It is cost effective, reliable, and suitable for integration into modern vehicles as a preventive safety mechanism.
Keywords: Sensors, Real-Time Monitoring, Safety,
Abstract
Low-Cost IoT-Based Fault Detection & AI Prediction for Electric Vehicle
Dr. V. Anantha Lakshmi, Sri Naga Divya.A, Damareswari.G
DOI: 10.17148/IJIREEICE.2026.14352
Abstract: The increasing adoption of electric vehicles (EVs) requires reliable and cost-effective solutions for fault detection to ensure safe operation. This paper presents a low-cost IoT-based prototype system for fault detection and basic AI-based condition analysis of electric vehicle motors. The proposed system continuously monitors key parameters such as current and temperature using sensors, and the collected data is transmitted to the ThingSpeak platform for real- time visualization and storage. A simple machine learning approach is implemented to analyze the data and classify the motor condition as normal or abnormal based on predefined patterns. Unlike complex predictive models, the proposed system focuses on practical implementation using limited data, making it suitable for low-cost applications. The integration of IoT enables remote monitoring, while the AI-based classification helps in early identification of potential faults. Experimental results from the prototype demonstrate effective detection of abnormal conditions, improving system safety and reducing the risk of unexpected failures. This work highlights a simple, scalable, and affordable approach for smart monitoring of electric vehicle motors.
Keywords: Electric Vehicles (EV), Internet of Things (IoT), Motor Fault Detection, ThingSpeak Cloud, Machine Learning, Real-Time Monitoring, Low-Cost Prototype.
Keywords: Electric Vehicles (EV), Internet of Things (IoT), Motor Fault Detection, ThingSpeak Cloud, Machine Learning, Real-Time Monitoring, Low-Cost Prototype.
Abstract
IOT Based Smart Energy Theft Detection Using Current Imbalance Alerts And Prepaid Billing
Dr. V. Anantha Lakshmi, Y. Rajeshwari, G. Indumathi
DOI: 10.17148/IJIREEICE.2026.14353
Abstract: Electricity theft remains a significant challenge in modern power distribution systems, leading to substantial economic losses, reduced system efficiency, and degraded power quality. Traditional metering systems lack real-time monitoring and fail to detect unauthorized consumption effectively. This paper proposes an Internet of Things (IoT)- based smart energy theft detection system that utilizes the principle of current imbalance combined with a prepaid billing mechanism.
The system employs dual current sensing points at the input and output sides of the energy meter to continuously monitor current flow. Any discrepancy between these values indicates potential theft. The Arduino-based controller processes the sensor data and triggers immediate actions such as visual alerts on an LCD, audible warnings through a buzzer, SMS notifications via a GSM module, and automatic power disconnection using a relay. Additionally, an RFID-based prepaid billing system ensures controlled energy consumption by allowing users to utilize electricity based on available balance.
The proposed system offers a cost-effective, scalable, and efficient solution for real-time monitoring, theft detection, and energy management, making it suitable for residential and small-scale industrial applications.
Keywords: IoT, Energy Theft Detection, Current Imbalance, Arduino, GSM, RFID, Smart Energy Meter, Prepaid Billing.
The system employs dual current sensing points at the input and output sides of the energy meter to continuously monitor current flow. Any discrepancy between these values indicates potential theft. The Arduino-based controller processes the sensor data and triggers immediate actions such as visual alerts on an LCD, audible warnings through a buzzer, SMS notifications via a GSM module, and automatic power disconnection using a relay. Additionally, an RFID-based prepaid billing system ensures controlled energy consumption by allowing users to utilize electricity based on available balance.
The proposed system offers a cost-effective, scalable, and efficient solution for real-time monitoring, theft detection, and energy management, making it suitable for residential and small-scale industrial applications.
Keywords: IoT, Energy Theft Detection, Current Imbalance, Arduino, GSM, RFID, Smart Energy Meter, Prepaid Billing.
Abstract
Raspberry Pi Pico Hybrid HID Controller
Surya Sevak Singh, Siddharth Sonawane, Vineet Raipure, Siddhesh Gaikwad, Pranav Kamble, Om Sakpal
DOI: 10.17148/IJIREEICE.2026.14354
Abstract: This paper presents the complete design, hardware implementation, and firmware development of a low-cost, multi-mode USB Human Interface Device (HID) controller built around the Raspberry Pi Pico (RP2040) microcontroller. The proposed system integrates a dual-axis analog joystick HW-504 and eleven programmable tactile buttons into a single platform capable of simultaneously emulating both a USB keyboard and a USB mouse without requiring any custom driver installation on the host system. The controller is implemented using the TinyUSB stack via the Pico C++ SDK and communicates over USB Full-Speed using standard HID class descriptors. Hardware was iteratively refined across three breadboard revisions, with Version 3 representing the most stable configuration. The system was successfully demonstrated and validated on Windows 11 with commercial game titles including Grand Theft Auto V and Red Dead Redemption 1, and was exhibited at the college Techfest. This work demonstrates that a sub-$5 microcontroller platform can implement a fully functional, re-programmable dual-mode HID peripheral suitable for gaming, desktop productivity, robotics teleoperation, and custom human-computer interaction.
Keywords: Raspberry Pi Pico, RP2040, USB HID, TinyUSB, analog joystick, embedded systems, HID composite device, C++ SDK, game controller, KiCad 9.0.
Keywords: Raspberry Pi Pico, RP2040, USB HID, TinyUSB, analog joystick, embedded systems, HID composite device, C++ SDK, game controller, KiCad 9.0.
Abstract
Intelligent IoT-Based Real-Time Industrial Effluent Monitoring System Using Machine Learning for Water Quality Classification
Dr. Gaayathry K, Kaviya C, Srivarshini S, Amritha J
DOI: 10.17148/IJIREEICE.2026.14355
Abstract: Industrialization has significantly contributed to economic growth; however, it has also intensified environmental pollution, particularly through the discharge of untreated or partially treated industrial effluents into natural water bodies. These effluents contain chemical contaminants, suspended solids, organic matter, and toxic compounds that severely degrade water quality and threaten ecological balance and human health. Traditional monitoring techniques depend on manual sampling and laboratory-based chemical analysis, which are periodic, labour intensive and incapable of detecting sudden pollution spikes in real time. This research proposes an Intelligent IoT-Based Real-Time Industrial Effluent Monitoring System integrated with Machine Learning (ML) for automated classification of effluent quality. The system continuously measures critical water quality parameters such as Total Dissolved Solids (TDS), Turbidity, Electrical Conductivity and Temperature using calibrated sensors connected to an ESP32 microcontroller. The sensor data are transmitted through wireless communication to a cloud server where preprocessing and classification are performed using a Random Forest model. The classification thresholds are derived from environmental discharge standards established by the Central Pollution Control Board and the World Health Organization. The proposed system not only enables real-time monitoring but also provides intelligent pollution categorization and automated alerts. Experimental results demonstrate high classification accuracy, reduced response time and improved reliability compared to conventional threshold-based systems.
Keywords: IoT, Industrial Effluent Monitoring, Machine Learning, Random Forest, Water Quality Classification, Environmental Pollution and Smart Monitoring Systems
Keywords: IoT, Industrial Effluent Monitoring, Machine Learning, Random Forest, Water Quality Classification, Environmental Pollution and Smart Monitoring Systems
Abstract
IOT BASED SMART MOTOR PROTECTION AND CONTROL SYSTEM
L. Karunakar, V. Lokesh Sai
DOI: 10.17148/IJIREEICE.2026.14356
Abstract: The increasing use of electric motors in industrial and domestic applications has made motor monitoring and protection an important requirement for ensuring safe and efficient operation. Motors often operate under varying loads and environmental conditions, which may lead to faults such as overheating, excessive vibration, and overcurrent. If these conditions are not detected early, they can result in severe motor damage, reduced efficiency, unexpected downtime, and increased maintenance costs. Therefore, continuous monitoring of motor operating parameters is essential for preventing failures and improving system reliability.
This project presents the design and implementation of an IoT-based Motor Safety Monitoring System that continuously monitors important motor parameters and provides automatic protection against abnormal operating conditions. The system is built using the ESP32 microcontroller, which serves as the central processing unit for collecting sensor data and controlling system operations.
The proposed system utilizes multiple sensors to monitor critical parameters of the motor. A current sensor is used to measure the electrical current drawn by the motor, which helps detect overload conditions. A vibration sensor is used to identify mechanical abnormalities such as imbalance or loose components. A temperature sensor (DS18B20) is used to monitor the thermal condition of the motor to prevent overheating. These sensors continuously send data to the ESP32 microcontroller, where the values are processed and compared with predefined threshold limits.
If any parameter exceeds its safe threshold value, the system identifies it as a fault condition and automatically shuts down the motor using a relay module. This immediate response helps protect the motor from severe damage and ensures safe operation. In addition to local protection, the system also provides remote monitoring capabilities through the Blynk IoT platform.
The ESP32 connects to a WiFi network and transmits real-time sensor data to the Blynk cloud server. A mobile dashboard displays parameters such as current, vibration level, temperature, and motor status. The user can monitor the system remotely and receive alerts whenever abnormal conditions occur.
For demonstration purposes, a DC Johnson motor is used as a prototype to simulate the behavior of an industrial motor. Experimental testing shows that the system successfully detects abnormal conditions such as overcurrent, excessive vibration, and overheating, and automatically stops the motor to prevent damage.
This project presents the design and implementation of an IoT-based Motor Safety Monitoring System that continuously monitors important motor parameters and provides automatic protection against abnormal operating conditions. The system is built using the ESP32 microcontroller, which serves as the central processing unit for collecting sensor data and controlling system operations.
The proposed system utilizes multiple sensors to monitor critical parameters of the motor. A current sensor is used to measure the electrical current drawn by the motor, which helps detect overload conditions. A vibration sensor is used to identify mechanical abnormalities such as imbalance or loose components. A temperature sensor (DS18B20) is used to monitor the thermal condition of the motor to prevent overheating. These sensors continuously send data to the ESP32 microcontroller, where the values are processed and compared with predefined threshold limits.
If any parameter exceeds its safe threshold value, the system identifies it as a fault condition and automatically shuts down the motor using a relay module. This immediate response helps protect the motor from severe damage and ensures safe operation. In addition to local protection, the system also provides remote monitoring capabilities through the Blynk IoT platform.
The ESP32 connects to a WiFi network and transmits real-time sensor data to the Blynk cloud server. A mobile dashboard displays parameters such as current, vibration level, temperature, and motor status. The user can monitor the system remotely and receive alerts whenever abnormal conditions occur.
For demonstration purposes, a DC Johnson motor is used as a prototype to simulate the behavior of an industrial motor. Experimental testing shows that the system successfully detects abnormal conditions such as overcurrent, excessive vibration, and overheating, and automatically stops the motor to prevent damage.
Abstract
IoT Based Bluetooth Control Industrial Robotic Arm Gripper
G. Sivaraj Manikanta, T. Krishna Mohan
DOI: 10.17148/IJIREEICE.2026.14357
Abstract: Robotic arms are extensively used in industrial automation to perform repetitive and accurate operations such as picking, placing, and assembling components. However, traditional robotic systems are generally expensive, complex to operate, and require specialized infrastructure. This project focuses on the design and development of a low-cost robotic arm fabricated using 3D printing technology and controlled through a mobile device. The system utilizes an ESP32 microcontroller as the central controller, which communicates with a mobile application through Bluetooth or Wi-Fi to control the movements of the robotic arm.
Keywords: Thermoelectric Generator (TEG), Waste Heat Recovery, Seebeck Effect, IoT Monitoring, ESP32, DC–DC Boost Converter, Energy Efficiency
Keywords: Thermoelectric Generator (TEG), Waste Heat Recovery, Seebeck Effect, IoT Monitoring, ESP32, DC–DC Boost Converter, Energy Efficiency
Abstract
DUAL POWERED AUTONOMOUS OBSTACLE AVOIDING VEHICLE
Mr. V. Brahmeswara Rao, K. Chandu, P. Jagadeesh, T. Jaideep
DOI: 10.17148/IJIREEICE.2026.14358
Abstract: The Dual Powered Autonomous Vehicle is designed to demonstrate a smart and energy-efficient transportation system using solar energy and wireless power transfer. An Arduino micro controller controls the vehicle, while ultrasonic and IR sensors detect obstacles and enable automatic navigation. The system represents a sustainable and autonomous solution for future smart transportation.
Keywords: Dual Powered Vehicle, Solar Energy, Wireless Power Transfer, Arduino, Obstacle Avoidance, Smart Transportation.
Keywords: Dual Powered Vehicle, Solar Energy, Wireless Power Transfer, Arduino, Obstacle Avoidance, Smart Transportation.
Abstract
3D COMSOL Simulation of TGS1820 Sensor: Acetone Detection in Human Breath Using Coupled Electric Currents and Transport Physics
Jelcy Chiristila P, Mahalakshmi K, Dr. M Shanmugavalli
DOI: 10.17148/IJIREEICE.2026.14359
Abstract: In this article, a thorough 3D numerical simulation using COMSOL Multiphysics of a TGS1820 gas sensor for acetone detection in human breath is presented. The sensor works on the basis that acetone adsorption causes a change in the conductivity of tin dioxide (SnO₂). The model simulates gas diffusion and electrical reaction by combining the mechanics of electric currents with transport of diluted species. A three-dimensional architecture was created that included an air domain, platinum electrodes, and a SnO₂ sensing layer. A breath pulse (one to three seconds) was used to apply acetone concentrations ranging from 0.5 to 3.0 ppm. According to the results, the concentration of acetone on the SnO₂ surface peaks at 0.022 mol/m³, which results in a voltage drop at the output electrode from 2.3 V to 1.8 V, With a sensitivity of 500 mV/ppm and R2 = 1.00, the sensor displays a linear response. Acetone diffusion from the inlet to the sensor surface is visible in the 3D visualization, with streamlines displaying flow patterns. The TGS1820 sensor design for non-invasive diabetes monitoring applications is validated by this COMSOL-based simulation.
Keywords: COMSOL Multiphysics, TGS1820, Acetone Detection, Gas Sensor, Breath Analysis, Diabetes Monitoring, Numerical Simulation, SnO₂ Sensor, Electric Currents, Transport Physics.
Keywords: COMSOL Multiphysics, TGS1820, Acetone Detection, Gas Sensor, Breath Analysis, Diabetes Monitoring, Numerical Simulation, SnO₂ Sensor, Electric Currents, Transport Physics.
Abstract
Load Flow and Short Circuit Analysis for a Data Centre
Jeevananthan J, Dr. V. Prasanna Moorthy
DOI: 10.17148/IJIREEICE.2026.14360
Abstract: For industrial buildings like Data centres maintaining power outages is a crucial role. Even a power outage for 1-minute leads to loss of huge numbers of Data. So, completely relying on grid for power supply is not efficient. In this paper load flow and short circuit analysis are performed for a Data Centre under different operating scenarios to ensure the system reliability. As a result, it checks whether all bus voltages are within the limit.
Keywords: Different operating scenarios, Load flow analysis, Reliable power supply.
Keywords: Different operating scenarios, Load flow analysis, Reliable power supply.
Abstract
An AI-Powered Learning and Business Support Platform for Women Entrepreneurs
Abinaya Sri M, M. Saravanakumar
DOI: 10.17148/IJIREEICE.2026.14361
Abstract: Women entrepreneurs often face difficulties such as lack of proper guidance, limited skill evaluation, and poor access to digital branding support. Many women have business ideas but do not know how to start or improve them using technology. This paper presents an AI-powered learning and business support platform designed to guide women entrepreneurs from beginner level toward business readiness. The platform provides structured learning modules, course selection based on category and skill level, skill evaluation, progress tracking, and AI-based suggestions to improve their work. It also supports early-stage business growth by offering branding and social media improvement suggestions. The platform helps women gain confidence, improve skills, and prepare for digital entrepreneurship.
Keywords: Women Entrepreneurship, AI Learning Platform, Skill Evaluation, Flask, Business Support.
Keywords: Women Entrepreneurship, AI Learning Platform, Skill Evaluation, Flask, Business Support.
Abstract
AI-Assisted Art Critique Platform
SUSMITHA SRI P, MOHAMED ATHFAN D
DOI: 10.17148/IJIREEICE.2026.14362
Abstract: The current art critique platforms present two main problems which stem from their absence of AI-driven feedback system and their inability to assess all available media formats and their basic analytical capabilities and their lack of community features and personalization options. Accessibility and complete artist progress tracking systems receive insufficient attention from numerous organizations. The project seeks to develop an innovative art critique platform which uses AI-generated feedback to assess artistic progress through its ability to analyze multiple multimedia artwork formats which include images and videos and 3D models. The platform uses React.js for its frontend development and Node.js with Express.js for backend operations while employing MongoDB for database functions and Python (Flask) or external APIs to deliver AI-based assessments. The platform enables artists to create accounts which allow them to upload different artwork types while receiving immediate automated feedback through the integrated AI system. Users can engage in peer assessment activities, participate in collaborative critique discussions, and discover mentors who will assist them in their growth process. The system provides users with advanced analysis tools which enable them to track their development and skill growth throughout different periods, while the system's personalized critique matching, which works with its strong accessibility features, creates a welcoming space that accommodates artists from all backgrounds and skill levels.
Keywords: AI-assisted feedback, Multimedia artworks, In-depth analytics, Group critique sessions, Progress tracking, Personalized critique matching, Inclusive environment
Keywords: AI-assisted feedback, Multimedia artworks, In-depth analytics, Group critique sessions, Progress tracking, Personalized critique matching, Inclusive environment
Abstract
AI-Powered Smart ISL Translator with Voice, Text & Gesture Recognition
Janasruthi N, Mohamed Athfan D
DOI: 10.17148/IJIREEICE.2026.14363
Abstract: Communication barriers remain one of the major challenges faced by the deaf and hard-of-hearing community in India. Indian Sign Language (ISL) is their primary medium of communication; however, most of the population does not understand ISL. To bridge this gap, this paper presents a web-based AI-powered ISL to multilingual translator with offline support and reverse translation features. The system converts ISL gestures into multiple Indian regional languages in both text and voice formats, while also providing reverse translation of text or voice back to ISL using a 3D avatar simulation.
The application accepts multiple input formats—typed text, uploaded audio files, microphone recordings, and gesture images. It integrates gesture recognition, speech-to-text via AssemblyAI, text-to-speech using gTTS, and multilingual NLP translation using a hybrid translation framework. A unique feature of the system is its custom vocabulary expansion module, allowing users to add domain-specific ISL signs with translations. Furthermore, a chatbot interface based on Google Gemini AI enables real-time language learning and practice.
Initial results show that the system achieves reliable translation accuracy and significantly improves communication accessibility. By combining AI, NLP, gesture recognition, and digital avatars, this project contributes to inclusive communication, digital accessibility, and language learning support for the deaf and hearing-impaired community.
Keywords: Indian Sign Language (ISL), Gesture Recognition, NLP Translation, 3D Avatar, Chatbot, Accessibility, Speech-to-Text, Text-to-Speech, Multilingual Translation, Offline Support.
The application accepts multiple input formats—typed text, uploaded audio files, microphone recordings, and gesture images. It integrates gesture recognition, speech-to-text via AssemblyAI, text-to-speech using gTTS, and multilingual NLP translation using a hybrid translation framework. A unique feature of the system is its custom vocabulary expansion module, allowing users to add domain-specific ISL signs with translations. Furthermore, a chatbot interface based on Google Gemini AI enables real-time language learning and practice.
Initial results show that the system achieves reliable translation accuracy and significantly improves communication accessibility. By combining AI, NLP, gesture recognition, and digital avatars, this project contributes to inclusive communication, digital accessibility, and language learning support for the deaf and hearing-impaired community.
Keywords: Indian Sign Language (ISL), Gesture Recognition, NLP Translation, 3D Avatar, Chatbot, Accessibility, Speech-to-Text, Text-to-Speech, Multilingual Translation, Offline Support.
Abstract
IOT-BASED SOLAR WIRELESS POWER TRANSFER SYSTEM FOR ELECTRIC VEHICLES
G. Harika, D. Ramu, R. Sushma Sri, Dr. M. Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14364
Abstract: An IoT- based solar wireless power transfer (WPT) system designed to enable efficient, cable-free charging for electric vehicles (EVs). It is an innovative solution that combines renewable energy with wireless charging technology. In this system, a solar panel captures sunlight and converts it into electrical energy, which is regulated using a charge controller and stored in a battery. The stored energy is then supplied to an Arduino Uno, which manages system operations and controls the wireless transmitter coil through a relay module. Power is transferred wirelessly via electromagnetic induction from the transmitter coil to the receiver coil mounted on the vehicle side. The received energy is stored in a battery and monitored using sensors, while an ESP32 module enables IoT-based data monitoring and control. The system also integrates street light automation using IR and LDR sensors for energy efficiency. Overall, this paper provides an eco-friendly, efficient, and smart charging solution for electric vehicles with reduced wiring and enhanced automation.
Keywords: Solar Energy, Electric Vehicles, Wireless Power Transfer, TX and RX Coils, ESP32, Wifi Module, IoT
Keywords: Solar Energy, Electric Vehicles, Wireless Power Transfer, TX and RX Coils, ESP32, Wifi Module, IoT
Abstract
An Optimized Machine Learning Framework for Heart Failure Patient Classification and Risk Prediction
K. Dinesh, K. Harika, M. Rohith, Sandi Sunanda
DOI: 10.17148/IJIREEICE.2026.14365
Abstract: Heart failure is a major global health problem, and early prediction of patient risk can significantly improve treatment outcomes. This project presents a machine learning-based system for classifying heart failure patients into high-risk and low-risk survival categories using clinical data. The dataset consists of approximately 5000 patient records with important medical features such as age, ejection fraction, serum creatinine, and blood pressure. Data preprocessing techniques including feature scaling, feature selection using SelectKBest, and class balancing using SMOTE were applied to improve model performance. Multiple machine learning algorithms were evaluated, including Logistic Regression and XGBoost. Among them, the XGBoost model demonstrated the best performance, achieving an accuracy of 99.70% with high precision and recall. A Flask-based web application was also developed to allow users to input patient data and obtain real-time risk predictions.
Abstract
IoT Based Electric Vehicle Battery Management System by Using Charge Monitor And Fire Protection
A Teja Sri, DR M Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14366
Abstract: This paper presents the development of an IoT-based Electric Vehicle Battery Management System with charge monitoring and fire protection. The main aim of this system is to improve the safety, performance, and life of the battery used in electric vehicles. In this system, important battery parameters such as voltage, current, and temperature are continuously monitored using sensors. The collected data is processed using a microcontroller and displayed on an LCD for local monitoring. At the same time, the data is sent to an IoT platform, which allows users to monitor the battery status remotely in real time. The system also includes safety features. If any abnormal condition such as high temperature, over-current, or low-voltage is detected, the system automatically takes protective actions. These actions include turning OFF the motor, stopping charging, activating a cooling fan, and giving alerts through LED indicators and a buzzer. This helps in preventing battery damage and reduces the risk of fire hazards. Overall, this paper provides a simple, low-cost, and effective solution for battery monitoring and protection in electric vehicles. It improves battery reliability, ensures safe operation, and supports efficient energy management.
Keywords: Electric Vehicles (EV’S), Internet of things (IOT), Thingspeak cloud, Real-time monitoring, wifi module.
Keywords: Electric Vehicles (EV’S), Internet of things (IOT), Thingspeak cloud, Real-time monitoring, wifi module.
Abstract
IOT-BASED SOLAR WIRELESS POWER TRANSFER SYSTEM FOR ELECTRIC VEHICLES
Ch. Srilatha, Dr. M. Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14367
Abstract: An autonomous robotic vehicle system is developed using the ESP32 microcontroller to enable intelligent, sensor-based navigation without human intervention. This smart vehicle is designed to detect obstacles, make real-time decisions, and navigate automatically based on sensor input. The system integrates various components such as ultrasonic sensors, IR sensors, and a motor driver module to control motion and avoid collisions.
The ESP32 processes the sensor data and sends control signals to drive the motors through the L298N motor driver. It also supports IoT capabilities by transmitting data wirelessly for remote monitoring and control. A GPS module is incorporated for real-time location tracking, enhancing the system's mobility features. Power is supplied via a rechargeable battery, enabling wireless and portable operation.
Additionally, automation features such as obstacle detection, motor control, and potential wireless communication make this system scalable for integration with future technologies like AI and cloud-based navigation.
Keywords: Autonomous Vehicle, ESP32, Ultrasonic Sensor, IR Sensor, Motor Driver, GPS Module, IoT, Obstacle Avoidance, Smart Navigation
The ESP32 processes the sensor data and sends control signals to drive the motors through the L298N motor driver. It also supports IoT capabilities by transmitting data wirelessly for remote monitoring and control. A GPS module is incorporated for real-time location tracking, enhancing the system's mobility features. Power is supplied via a rechargeable battery, enabling wireless and portable operation.
Additionally, automation features such as obstacle detection, motor control, and potential wireless communication make this system scalable for integration with future technologies like AI and cloud-based navigation.
Keywords: Autonomous Vehicle, ESP32, Ultrasonic Sensor, IR Sensor, Motor Driver, GPS Module, IoT, Obstacle Avoidance, Smart Navigation
Abstract
DESIGN OF ENHANCED SMART GRIDS WITH A NEW IOT AND CLOUD BASED SMART METER TO PREDICT THE ENERGY CONSUMPTION
Naga Nandini, Dr. M. Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14368
Abstract: Energy monitoring and management have become essential for improving efficiency and reducing power wastage in industrial environments. Traditional energy meters provide limited monitoring capabilities and do not support real-time remote access to electrical parameters.
This paper presents the design and implementation of an IoT-based smart energy monitoring system using the ESP32 and the PZEM-004T Energy Meter Module. The system continuously measures important electrical parameters such as voltage, current, power, energy consumption, frequency, and power factor with high accuracy. The measured data is processed by the ESP32 microcontroller and transmitted through Wi-Fi for remote monitoring.
The real-time electrical data can be viewed through the Blynk application, enabling users to monitor energy usage from anywhere using a mobile device. This system provides an efficient and cost-effective solution for industrial energy monitoring and management.
Experimental testing with different electrical loads demonstrates that the system provides accurate and reliable measurement results. The proposed system can be applied in industrial environments for smart energy monitoring and improved power management.
Keywords: IoT, Smart Energy Meter, ESP32, PZEM-004T, Energy Monitoring.
This paper presents the design and implementation of an IoT-based smart energy monitoring system using the ESP32 and the PZEM-004T Energy Meter Module. The system continuously measures important electrical parameters such as voltage, current, power, energy consumption, frequency, and power factor with high accuracy. The measured data is processed by the ESP32 microcontroller and transmitted through Wi-Fi for remote monitoring.
The real-time electrical data can be viewed through the Blynk application, enabling users to monitor energy usage from anywhere using a mobile device. This system provides an efficient and cost-effective solution for industrial energy monitoring and management.
Experimental testing with different electrical loads demonstrates that the system provides accurate and reliable measurement results. The proposed system can be applied in industrial environments for smart energy monitoring and improved power management.
Keywords: IoT, Smart Energy Meter, ESP32, PZEM-004T, Energy Monitoring.
Abstract
SMART MONITORINNG OF TRANSFORMER PROTECTION SYSTEM
M. Bhavana, DR. M. Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14369
Abstract: The Smart Monitoring of Transformer Protection System is designed to enhance the safety and reliability of power transformers by continuously monitoring important parameters such as temperature, voltage, and current using advanced sensors. The system employs a microcontroller to process real-time data and detect any abnormal conditions or faults instantly, enabling quick protective actions. With the integration of IoT technology, it allows remote monitoring and control through wireless communication. The collected data is transmitted to a cloud platform for storage and analysis, which helps in implementing predictive maintenance and reducing unexpected failures. This system improves overall efficiency, minimizes downtime, and provides a cost-effective and intelligent solution for modern power system protection.
Keywords: Smart monitoring, transformer protection system, IoT, real-time data, fault detection, condition monitoring, temperature monitoring, voltage monitoring, current monitoring, embedded systems, microcontroller.
Keywords: Smart monitoring, transformer protection system, IoT, real-time data, fault detection, condition monitoring, temperature monitoring, voltage monitoring, current monitoring, embedded systems, microcontroller.
Abstract
IMPLEMENTATION OF PREDICTIVE MODELLING OF PRESCRIPTION GROWTH THROUGH MARKETING MIX MODELLING
Selvapujith T, Mohamed Athfan D
DOI: 10.17148/IJIREEICE.2026.14370
Abstract: The pharmaceutical assiduity is faced with a grueling question moment how can they effectively spend their marketing budget while adding the number of prescriptions? This exploration proposes a result to this problem by using data- driven prognostications to identify which marketing sweats are actually effective. We’ve designed a system that analyzes different marketing sweats similar as deals representatives visiting croakers, free samples, online advertising, medical conferences, and special juggernauts to identify their factual effectiveness on the number of conventions written. Our system uses statistical analysis and intelligent features that consider delayed goods( since marketing doesn’t work incontinently) and long- term goods( since moment’s advertising can impact hereafter’s opinions). The system analyzes the literal data of conventions and marketing spending, cleans the data, and generates prophetic models that can actually tell marketers what works. We’ve enforced our system and created visual interfaces that help interpret the results. The analysis demonstrates that online marketing is a crucial factor affecting and direct marketing to croakers are the most effective, and more intelligent budget allocation can increase returns by 15 – 20 chance points. This system provides a foundation for pharmaceutical marketers to make informed opinions grounded on real substantiation.
Keywords: Market Mix Modeling, Prescription Growth, Regression Analysis, Adstock, ROI Optimization, Feature Engineering, Pharmaceutical Marketing, Predictive Analytics.
Keywords: Market Mix Modeling, Prescription Growth, Regression Analysis, Adstock, ROI Optimization, Feature Engineering, Pharmaceutical Marketing, Predictive Analytics.
Abstract
EduCrate: AI-Powered Personalized Learning Kit Generator
Gopika D, Bharath Krishnan M, Ms. Maneesha
DOI: 10.17148/IJIREEICE.2026.14371
Abstract: Modern e-learning platforms often follow a one- size-fits-all approach, delivering the same content to all learners without considering individual preferences, learning styles, or emotional states. This lack of personalization can reduce learner engagement, motivation, and overall learning effectiveness. To address these limitations, this paper presents EduCrate, an AI- powered personalized learning kit generator designed to create adaptive and user-centered educational experiences.
The proposed system allows users to select prebuilt courses or create custom topics by uploading learning materials. Based on user preferences such as learning style, language, and mood, the system generates personalized study plans, summaries, flashcards, audio lessons, and visual content. The study plan dynamically adjusts its duration and workload according to the learner’s mental state, providing longer plans for focused or curious moods and shorter plans for tired or distracted moods. In addition, a real-time AI chatbot is integrated to provide instant assistance and explanations during the learning process.
The system is implemented using a React-based frontend and a FastAPI backend, integrated with AI models for content generation and text-to-speech conversion. Experimental results show that the platform effectively delivers personalized, multi- format learning content and improves user engagement.
EduCrate provides a flexible, adaptive, and scalable solution for modern digital education by combining artificial intelligence with personalized learning strategies.
Keywords: Artificial Intelligence, Personalized Learning, Adaptive Learning, E-learning, Chatbot, Multilingual Learning, Educational Technology
The proposed system allows users to select prebuilt courses or create custom topics by uploading learning materials. Based on user preferences such as learning style, language, and mood, the system generates personalized study plans, summaries, flashcards, audio lessons, and visual content. The study plan dynamically adjusts its duration and workload according to the learner’s mental state, providing longer plans for focused or curious moods and shorter plans for tired or distracted moods. In addition, a real-time AI chatbot is integrated to provide instant assistance and explanations during the learning process.
The system is implemented using a React-based frontend and a FastAPI backend, integrated with AI models for content generation and text-to-speech conversion. Experimental results show that the platform effectively delivers personalized, multi- format learning content and improves user engagement.
EduCrate provides a flexible, adaptive, and scalable solution for modern digital education by combining artificial intelligence with personalized learning strategies.
Keywords: Artificial Intelligence, Personalized Learning, Adaptive Learning, E-learning, Chatbot, Multilingual Learning, Educational Technology
Abstract
OBSTACLE AVOIDING ROBOT USING WIFI MODULE ESP 8266
Wrushali Deshmukh, Yash Gade, Suyog Ghatage, Shreyas Palav, Manthan Hire, Siddhi Borhade
DOI: 10.17148/IJIREEICE.2026.14372
Abstract: The rapid advancement of robotics and Internet of Things (IoT) technologies has enabled the development of intelligent systems that can perform tasks both autonomously and remotely. Robotics is widely used in industries, smart homes, and security systems. One of the major challenges in robotics is ensuring safe navigation in environments where obstacles are present.This project focuses on designing a WiFi-controlled obstacle-avoiding robot using the ESP8266 microcontroller. The system combines wireless communication, embedded programming, and sensor-based obstacle detection. The ESP8266 allows the robot to be controlled remotely through a web interface, where users can send commands like forward, backward, left, right, and stop using devices such as smartphones or laptops. In addition to manual control, the robot operates in an automatic mode where it detects obstacles using an ultrasonic sensor. When an obstacle is detected, the robot stops and uses a servo motor to scan its surroundings and choose the safest path. A 16×2 LCD with I2C interface displays real-time data like distance and movement status, making the system efficient, cost- effective, and suitable for educational and basic automation applications.
Abstract
DEVELOPMENT OF AUTONOMOUS VEHICLE SYSTEM USING ESP32 MICROCONTROLLER
Ch. Srilatha, Dr. M. Ajay Kumar
DOI: 10.17148/IJIREEICE.2026.14373
Abstract: An autonomous robotic vehicle system is developed using the ESP32 microcontroller to enable intelligent, sensor-based navigation without human intervention. This smart vehicle is designed to detect obstacles, make real-time decisions, and navigate automatically based on sensor input. The system integrates various components such as ultrasonic sensors, IR sensors, and a motor driver module to control motion and avoid collisions.
The ESP32 processes the sensor data and sends control signals to drive the motors through the L298N motor driver. It also supports IoT capabilities by transmitting data wirelessly for remote monitoring and control. A GPS module is incorporated for real-time location tracking, enhancing the system's mobility features. Power is supplied via a rechargeable battery, enabling wireless and portable operation.
Additionally, automation features such as obstacle detection, motor control, and potential wireless communication make this system scalable for integration with future technologies like AI and cloud-based navigation.
Keywords: Autonomous Vehicle, ESP32, Ultrasonic Sensor, IR Sensor, Motor Driver, GPS Module, IoT, Obstacle Avoidance, Smart Navigation
The ESP32 processes the sensor data and sends control signals to drive the motors through the L298N motor driver. It also supports IoT capabilities by transmitting data wirelessly for remote monitoring and control. A GPS module is incorporated for real-time location tracking, enhancing the system's mobility features. Power is supplied via a rechargeable battery, enabling wireless and portable operation.
Additionally, automation features such as obstacle detection, motor control, and potential wireless communication make this system scalable for integration with future technologies like AI and cloud-based navigation.
Keywords: Autonomous Vehicle, ESP32, Ultrasonic Sensor, IR Sensor, Motor Driver, GPS Module, IoT, Obstacle Avoidance, Smart Navigation
Abstract
Piezoelectric Electricity Generator Using Footsteps
Mr. Rajendra Ghorpade, Deep Koli, Diksha Gaikwad, Tejaswini Patil, Bhakti Waghmare
DOI: 10.17148/IJIREEICE.2026.14374
Abstract: The growing demand for sustainable and decentralized energysources has encouraged the exploration of energy harvesting fromeveryday human activities. This project focuses on the design anddevelopment of a piezoelectric electricity generator that convertsmechanical energy from human footsteps into usable electricalenergy. When pressure is applied to piezoelectric materials embedded beneath a walking surface, they generate an electric charge due to the piezoelectric effect. The produced alternating voltage is conditioned using rectification and energy storage circuits to obtain stable electrical output. The harvested energy can be used to power low-energy devices such as LED lighting,sensors, or charging units in public areas. This system is particularly suitable for high-footfall locations like railway stations, shopping malls, and sidewalks, offering a clean,renewable, and cost- effective supplementary power source. The proposed approach demonstrates the potential of piezoelectric technology in promoting energy efficiency and sustainability through smart infrastructure integration.
Abstract
Smart SIP for Teens: A Gamified and Explainable Machine Learning Framework for Early Investment Habit Formation
Maneesha P A, Saranya G
DOI: 10.17148/IJIREEICE.2026.14375
Abstract: Early financial literacy plays a crucial role in shaping long-term economic well-being. However, most digital investment platforms are designed for adult users and they lacks in educational, motivational, and transparency features suitable for teenagers. This paper presents Smart SIP for Teens, a comprehensive, gamified, and explainable financial learning platform aimed at fostering disciplined saving and early investment habits among teenagers. The proposed system combines machine learning-based personalization using the XGBoost algorithm to recommend suitable Systematic Investment Plan (SIP) strategies based on user-specific attributes such as age, savings behavior, financial goals, and risk tolerance. To address trust and transparency concerns, Explainable Artificial Intelligence (XAI) techniques using SHAP values are employed to interpret model decisions. Gamification elements such as reward points, streaks, badges, and milestones are incorporated to improve engagement and investment habit formation. Experimental evaluation demonstrates improved user engagement, consistency in saving behavior, and enhanced understanding of investment concepts. The results validate the effectiveness of combining personalization, explainability, and gamification in delivering impactful financial education solutions for teenage users.
Keywords: Systematic Investment Plan, Financial Literacy, Teenagers, Gamification, Machine Learning, XGBoost, Explainable AI, SHAP Values
Keywords: Systematic Investment Plan, Financial Literacy, Teenagers, Gamification, Machine Learning, XGBoost, Explainable AI, SHAP Values
Abstract
INTELLIGENT BATTERY THERMAL MANAGEMENT SYSTEM FOR SMART ELECTRIC VEHICLES
Ms. B. Sruthi, Mr. Talluri. Karthik
DOI: 10.17148/IJIREEICE.2026.14376
Abstract: Technology is an ever-evolving process. Designing systems using advanced technology that improve energy efficiency and safety in electric vehicles is a valuable contribution to society. This paper presents the design and implementation of an intelligent, low-cost, and efficient battery thermal management system (BTMS) for smart electric vehicles. The system is built using a microcontroller-based control unit, with temperature sensors and cooling mechanisms connected through control circuits.
Communication between sensors and the controller is carried out in real-time to monitor battery temperature continuously. The system is designed to be cost-effective and scalable, allowing integration with various electric vehicle battery packs. To ensure safety, automated control strategies are implemented to prevent overheating and maintain optimal battery performance.
Keywords: Battery Thermal Management; Electric Vehicles; ESP32; Sensors; Cooling System
Communication between sensors and the controller is carried out in real-time to monitor battery temperature continuously. The system is designed to be cost-effective and scalable, allowing integration with various electric vehicle battery packs. To ensure safety, automated control strategies are implemented to prevent overheating and maintain optimal battery performance.
Keywords: Battery Thermal Management; Electric Vehicles; ESP32; Sensors; Cooling System
Abstract
“AI-Based Multi-Sensor Fusion for Real-Time Heavy Metal Detection in Water Using IoT”
I Rakshan Darwin, M Gokul, K Sabarish, R Seetharaman
DOI: 10.17148/IJIREEICE.2026.14377
Abstract: Water contamination by heavy metals poses a serious threat to human health and aquatic ecosystems. Conventional laboratory-based techniques such as Atomic Absorption Spectroscopy and Inductively Coupled Plasma Mass Spectrometry provide accurate results but are expensive and unsuitable for real-time field monitoring. This paper presents an enhanced IoT-enabled heavy metal detection system that combines colorimetric sensing using a TCS3200 color sensor with UV–Visible spectroscopic analysis for improved quantitative accuracy. Selective chemical reagents are used to induce characteristic color changes in the presence of zinc (Zn²⁺), copper (Cu²⁺), and nickel (Ni²⁺) ions. The RGB responses are captured using the TCS3200 sensor for rapid screening, while spectral absorbance data obtained from a compact UV–Visible spectrometer enables wavelength-based concentration estimation using the Beer–Lambert principle. An ESP32 microcontroller performs edge-level processing and transmits results to the ThingSpeak cloud platform for real-time monitoring and visualization. Experimental validation demonstrates improved sensitivity, selectivity, and concentration estimation capability compared to RGB-only detection. The proposed hybrid system offers a low-cost, portable, and scalable solution bridging IoT-based monitoring and spectroscopic analytical techniques.
Keywords: Heavy metal detection, UV–Visible Spectroscopy, TCS3200, IoT, Colorimetric analysis, Water quality monitoring, ESP32, Spectral absorbance.
Keywords: Heavy metal detection, UV–Visible Spectroscopy, TCS3200, IoT, Colorimetric analysis, Water quality monitoring, ESP32, Spectral absorbance.
Abstract
SMART HOME AUTOMATION WITH INTEGRATED SAFETY AND SECURITY USING STM32 AND WI-FI MODULE
S Dharani Sivapriya, M Bhuvaneshwari, R Seetharaman
DOI: 10.17148/IJIREEICE.2026.14378
Abstract: This paper presents a smart home automation system designed using the STM32F103C8T6 microcontroller and ESP8266 Wi-Fi module for efficient monitoring and control of household appliances. The system integrates multiple sensors such as an LDR for automatic lighting control, an MQ-2 gas sensor for gas leakage detection, and a DHT11 temperature and humidity sensor for monitoring ambient temperature. A 3.4 V lithium-ion battery and dual power supply units are used to distribute power to components including IR sensors, a servo motor, and other modules. The LDR detects day and night conditions and automatically controls lighting through a relay based on programmed threshold values in the microcontroller. The MQ-2 sensor identifies gas leakage and provides an alert indication, while the DHT11 sensor activates an air- conditioning relay when the temperature exceeds a predefined threshold. Additionally, two IR sensors and a servo motor are used to implement an automatic door system that opens when a person approaches and closes after passing through. A capacitive touch module is also included to allow manual door operation for safety. The proposed system provides a low- cost, efficient, and intelligent solution for home automation, improving convenience, safety, and energy management.
Keywords: Smart Home Automation, STM32F103C8T6 microcontroller, ESP8266 Wi-Fi module, MQ-2 gas sensor, DHT11 temperature and humidity sensor, LDR Sensor, IR Sensor, Servo Motor, Gas Leakage Detection, Temperature Monitoring, Automatic Door System, IoT-based Monitoring, Energy Management.
Keywords: Smart Home Automation, STM32F103C8T6 microcontroller, ESP8266 Wi-Fi module, MQ-2 gas sensor, DHT11 temperature and humidity sensor, LDR Sensor, IR Sensor, Servo Motor, Gas Leakage Detection, Temperature Monitoring, Automatic Door System, IoT-based Monitoring, Energy Management.
Abstract
NeuroVision AI: Multi-Device Eye Strain Detection Using Micro-Motion and Cognitive Behaviour
Vanitha A, Dr. K. Arunkumar, Keerthana S, Karthika V
DOI: 10.17148/IJIREEICE.2026.14379
Abstract: Digital devices such as laptops, smartphones, and tablets have become essential tools for communication, nd professional work. As people increasingly depend on these devices, the amount of time spent looking at screens has grown significantly. Long hours of screen exposure can cause a condition commonly known as digital eye strain. Symptoms of digital eye strain include tired eyes, dryness, blurred vision, headaches, and reduced ability to focus. Many individuals experience these symptoms after extended periods of screen usage, but they often ignore them until the discomfort becomes severe.
Traditional solutions that attempt to reduce eye strain mainly rely on simple screen-time reminders or break notifications. These systems usually prompt users to rest their eyes after a fixed amount of time. However, these reminders do not evaluate the actual condition of the user’s eyes. Eye fatigue depends on several factors, such as blinking behaviour, gaze stability, posture, and the intensity of interaction with digital devices. Therefore, time-based reminders alone are not sufficient to detect or prevent eye strain effectively.
This research proposes an AI-based eye strain detection system that monitors eye behaviour in real time using a standard webcam. The system analyses several indicators, including blink rate, gaze movement, ocular micro-motions, head posture, and user interaction patterns such as typing and scrolling activity. These indicators are combined to calculate an eye strain score that represents the fatigue level of the user.
When the strain score crosses a predefined threshold, the system alerts the user and suggests taking a short break or adjusting posture. The proposed system also supports multi-user identification and multi-device environments, making it suitable for shared computers and modern workspaces. Because the system relies only on webcam input and computer vision techniques, it does not require specialised hardware. This makes the solution affordable, scalable, and suitable for everyday use in homes, offices, and educational institutions.
Keywords: Digital Eye Strain, Ocular Micro-Motion,Cognitive Load, Multi-Device Monitoring, Computer Vision.
Traditional solutions that attempt to reduce eye strain mainly rely on simple screen-time reminders or break notifications. These systems usually prompt users to rest their eyes after a fixed amount of time. However, these reminders do not evaluate the actual condition of the user’s eyes. Eye fatigue depends on several factors, such as blinking behaviour, gaze stability, posture, and the intensity of interaction with digital devices. Therefore, time-based reminders alone are not sufficient to detect or prevent eye strain effectively.
This research proposes an AI-based eye strain detection system that monitors eye behaviour in real time using a standard webcam. The system analyses several indicators, including blink rate, gaze movement, ocular micro-motions, head posture, and user interaction patterns such as typing and scrolling activity. These indicators are combined to calculate an eye strain score that represents the fatigue level of the user.
When the strain score crosses a predefined threshold, the system alerts the user and suggests taking a short break or adjusting posture. The proposed system also supports multi-user identification and multi-device environments, making it suitable for shared computers and modern workspaces. Because the system relies only on webcam input and computer vision techniques, it does not require specialised hardware. This makes the solution affordable, scalable, and suitable for everyday use in homes, offices, and educational institutions.
Keywords: Digital Eye Strain, Ocular Micro-Motion,Cognitive Load, Multi-Device Monitoring, Computer Vision.
Abstract
An IoT-Integrated Multi-Sensor Framework for Continuous Vital Monitoring and Fall Detection
Madhumitha. M, Lakshmi Priya. S, Mr. R. Satheesh
DOI: 10.17148/IJIREEICE.2026.14380
Abstract: The rapid growth of elderly populations and patients requiring continuous medical supervision has created a demand for intelligent healthcare monitoring systems. This paper presents an IoT-integrated multi-sensor framework for continuous monitoring of vital parameters and fall detection with an automated SMS alert system using Twilio cloud services. The proposed system integrates sensors such as heart rate, SpO₂, temperature, and an accelerometer to continuously monitor the patient’s physiological condition and detect sudden fall events. Sensor data is processed using a microcontroller and transmitted through Wi-Fi to a cloud platform for real-time monitoring. When abnormal vital signs or a fall is detected, the system automatically sends an SMS alert to caregivers using the Twilio messaging API. The proposed system offers a low-cost, portable, and real-time monitoring solution for elderly care and remote patient monitoring. Experimental testing demonstrates reliable sensor readings, accurate fall detection, and rapid alert delivery through SMS notifications.
Keywords: Vital signs, IoT healthcare, MAX30100, fall detection, ESP32, temperature monitoring, wearable system.
Keywords: Vital signs, IoT healthcare, MAX30100, fall detection, ESP32, temperature monitoring, wearable system.
Abstract
Design Hybrid EV using Supercapacitor for Long Mileage and Durability
Ayur Sanjay Bhoge, Achal Sheshrao Chokhandre, Shreya Dilip Hekad, Aishwarya Ravish Kamble, Divesh Vilas Chittalwar, Prof. Rajendra Bhombe, Mr. Harshal Makde
DOI: 10.17148/IJIREEICE.2026.14381
Abstract: The "Hybrid Vehicle Supercapacitor" system is an advanced energy management solution designed to enhance the performance, efficiency, and sustainability of hybrid vehicles by integrating high-capacity supercapacitors with traditional battery systems. This project leverages the rapid charge–discharge characteristics, high power density, and long lifecycle of supercapacitors to optimize power distribution during acceleration, regenerative braking, and varying load conditions. Supported by sensors, an Arduino Nano microcontroller, and power electronics such as MOSFET drivers and voltage regulators, the system ensures precise control, real-time monitoring, and seamless coordination between energy sources. The inclusion of an LCD interface, buzzer, and interactive controls further enhances usability and operational transparency. By improving energy efficiency, boosting vehicle responsiveness, and reducing strain on batteries, the proposed system contributes to extended component lifespan, enhanced user satisfaction, and reduced environmental impact—advancing the goal of sustainable and intelligent hybrid vehicle technology.
Abstract
QUANTUM SECURE BLOCKCHAIN ARCHITECTURE
Dr. Ashwini Kumar Jha, Kartik Patil, Abhishek Patil, Pramod Patil, Shreyansh Patel
DOI: 10.17148/IJIREEICE.2026.14382
Abstract: We live in a world where billions of devices are connected to the internet from smart home gadgets to hospital monitors to factory machines. All of these devices rely on security systems built with traditional encryption (methods for scrambling data so only the right person can read it). These encryption methods have protected us well for decades. But a new type of computer, called a quantum computer, is on the horizon and it could break most of today's encryption in a matter of seconds. That's a very serious problem.
This review paper brings together findings from several research studies to explain the problem clearly and to explore the solutions being developed. We look at how quantum computers threaten our current systems. what new types of encryption(called post-quantum cryptography, or PQC) are being created to replace them, and how blockchain technology the same technology behind cryptocurrencies can be made quantum-safe. We also explore how a technique called Quantum Key Distribution (QKD) can share secret keys in a way that is guaranteed to be safe by the laws of physics. Finally, we look at how Artificial Intelligence (AI) can both help protect systems and, in the wrong hands, help attack them. The paper ends with an honest look at what still needs to be solved and where researchers should focus their efforts next.
Keywords: Quantum Computers, Post-Quantum Cryptography (PQC),Blockchain Security, Internet of Things (IoT), Quantum Key Distribution (QKD), 6G Networks, Artificial Intelligence Security
This review paper brings together findings from several research studies to explain the problem clearly and to explore the solutions being developed. We look at how quantum computers threaten our current systems. what new types of encryption(called post-quantum cryptography, or PQC) are being created to replace them, and how blockchain technology the same technology behind cryptocurrencies can be made quantum-safe. We also explore how a technique called Quantum Key Distribution (QKD) can share secret keys in a way that is guaranteed to be safe by the laws of physics. Finally, we look at how Artificial Intelligence (AI) can both help protect systems and, in the wrong hands, help attack them. The paper ends with an honest look at what still needs to be solved and where researchers should focus their efforts next.
Keywords: Quantum Computers, Post-Quantum Cryptography (PQC),Blockchain Security, Internet of Things (IoT), Quantum Key Distribution (QKD), 6G Networks, Artificial Intelligence Security
Abstract
Hybrid Edge-Based Predictive Health Monitoring Model using Statistical Trend and Anomaly Fusion
Suriyamoorthy S, Arul Victor Raj BM, Ragavan D
DOI: 10.17148/IJIREEICE.2026.14383
Abstract: A lightweight and transparent approach for predicting maintenance of pump systems at the edge is outlined via statistical modeling of time series data, an alternative to other supervised learning techniques that typically require a large labeled data sets (usually tens of thousands) and substantial computational resources. The methodology consists of using Exponential Moving Average, Trend Strength Detection, and Z-score-based anomaly scores to assess the health of pump systems on-line, rather than relying on off-line processing techniques primarily based on deep-learning methodologies. Multi-sensor data including vibration, sound and temperature will be processed in real-time at the edge using a Raspberry Pi computing platform. Exponential Moving Average reduces data noise while retaining and displaying slow degradation trends; Trend Strength Analysis can identify gradual trends in machine health; and the Z-scores serve to quantify deviations from an expected or healthy condition. By combining these outputs into a single Health Index, an easy-to-understand measurement of machine health can be generated. Experimental validation performed under both healthy and simulated degraded conditions demonstrated successful identification of mechanical imbalance, acoustic disturbance and thermal overload. The model will not require the use of supervised learning, therefore providing lower latency, transparency and applicability to lower resourced industrial settings along with offering a cost effective, scalable and less computationally intensive alternative to existing predictive maintenance methodologies.
Keywords: Predictive Maintenance, Edge Computing, Statistical Anomaly Detection, Exponential Moving Average (EMA), Trend Analysis, Industrial Pump Monitoring
Keywords: Predictive Maintenance, Edge Computing, Statistical Anomaly Detection, Exponential Moving Average (EMA), Trend Analysis, Industrial Pump Monitoring
Abstract
IOT BASED UNDER GROUND CABLE FAULT DETECTION
T. Krishna Mohan, G. Rohith, J. Rakesh
DOI: 10.17148/IJIREEICE.2026.14384
Abstract: Underground cable systems are widely used in modern power distribution networks due to their reliability, safety, and reduced exposure to environmental disturbances. However, detecting faults in underground cables is a challenging task, often leading to prolonged power outages and increased maintenance costs. This paper presents an Internet of Things (IoT)-based underground cable fault detection system designed to accurately identify and locate faults in real time.
The proposed system utilizes sensors and microcontroller-based circuitry to monitor electrical parameters such as voltage and current variations along the cable. When a fault occurs, the system analyzes deviations in these parameters and calculates the fault distance using predefined algorithms. The integration of IoT technology enables continuous remote monitoring, allowing fault data to be transmitted to a cloud platform or mobile application for instant access by maintenance personnel.
The system enhances fault detection accuracy, reduces manual inspection efforts, and significantly minimizes downtime. Additionally, real-time alerts and data logging improve decision-making and preventive maintenance strategies. The implementation demonstrates a cost-effective, efficient, and scalable solution for modern smart grid applications.
Keywords: Internet of Things (IoT), Underground Cable Fault Detection, Fault Localization, Smart Grid, Remote Monitoring, Microcontroller, Voltage and Current Sensors, Real-Time Monitoring, Power Distribution System, Wireless Communication, Fault Analysis, Predictive Maintenance
The proposed system utilizes sensors and microcontroller-based circuitry to monitor electrical parameters such as voltage and current variations along the cable. When a fault occurs, the system analyzes deviations in these parameters and calculates the fault distance using predefined algorithms. The integration of IoT technology enables continuous remote monitoring, allowing fault data to be transmitted to a cloud platform or mobile application for instant access by maintenance personnel.
The system enhances fault detection accuracy, reduces manual inspection efforts, and significantly minimizes downtime. Additionally, real-time alerts and data logging improve decision-making and preventive maintenance strategies. The implementation demonstrates a cost-effective, efficient, and scalable solution for modern smart grid applications.
Keywords: Internet of Things (IoT), Underground Cable Fault Detection, Fault Localization, Smart Grid, Remote Monitoring, Microcontroller, Voltage and Current Sensors, Real-Time Monitoring, Power Distribution System, Wireless Communication, Fault Analysis, Predictive Maintenance
Abstract
DETECTION OF THERMAL RUNAWAY IN EV BATTERY PACK USING MULTI-MODAL SENSOR FUSION (THERMAL IMAGING, GAS & CURRENT) AND NEURAL NETWORK
C Logapragash, S Muralidharan, R Sunil Raja
DOI: 10.17148/IJIREEICE.2026.14385
Abstract: In electric vehicles (EVs), battery safety is very important, and thermal runaway (TR) is due to multi-physics failure mechanism that begins with electrical failure followed by chemical reactions. Traditional battery management systems only detect TR after there is a significant rise in temperature. This article proposes a novel multi-modal monitoring system of the safety of the battery, which detects thermal runaway precursors in EVs using thermal, gas and current sensing. The thermal image is segmented into hot spots using a U-Net Convolutional Neural Network (CNN) which is a type of semantic segmentation network. Gases are sensed by MQ-135 and current is sensed using ACS712 Hall Effect current sensors. A novel Fusion Index is introduced as the weighted sum of the thermal, gas and current anomaly score. The Fusion Index also determines when to cool the battery and isolate the battery cell using a MOSFET. The efficacy of the proposed multi-modal battery safety monitoring system was validated using a MATLAB simulation, which was an electro-thermal digital twin. The simulation demonstrated that thermal runaway was detected 30 to 90 seconds earlier using the proposed system compared to the existing thermal/gas systems. The multi-modal battery safety monitoring system has successfully delivered a significant improvement over traditional thermal/gas battery management systems.
Keywords: Thermal runaway, Electrolyte Decomposition, Convolutional Neural Networks, U-Net, Semantic segmentation, Active cooling, Anomaly, Battery pack Isolation, Fusion Index.
Keywords: Thermal runaway, Electrolyte Decomposition, Convolutional Neural Networks, U-Net, Semantic segmentation, Active cooling, Anomaly, Battery pack Isolation, Fusion Index.
Abstract
A Centralized AI Framework for Wildlife-Vehicle Collision Detection: Addressing Implementation Challenges in Real-World Deployment
Mr. Stanly Raj J, Ms. Maneesha P.A, Sami Abdulsalam
DOI: 10.17148/IJIREEICE.2026.14386
Abstract: Wildlife-vehicle collisions (WVCs) represent a significant global challenge, leading to millions of animal fatalities annually, substantial economic losses, and posing threats to biodiversity. Traditional mitigation strategies, such as fencing, wildlife crossings, and static signage, have demonstrated localized effectiveness but often face limitations in scalability, cost-effectiveness, and long-term efficacy across extensive road networks. This study investigates a novel centralized artificial intelligence (AI) detection system designed to provide real-time wildlife alerts to drivers. The proposed framework integrates thermal and RGB imaging with the YOLOv8 object detection model, consolidating video processing at a central hub rather than distributing computational resources to numerous roadside units. This architectural choice aims to reduce deployment costs and simplify maintenance, particularly in remote or challenging environments. Preliminary evaluations indicate that dual-spectrum imaging enhances detection robustness under varying environmental conditions, though challenges related to false positive rates and the acquisition of species-specific training data persist. The system incorporates an adaptive learning mechanism that continuously augments the training dataset based on verified field detections, thereby improving model generalization over time. While initial results demonstrate the potential for WVC reduction in controlled settings, real-world deployment necessitates addressing critical obstacles, including reliable power infrastructure, robust data transmission, and unpredictable driver behavioral responses. This research contributes to the evolving field of intelligent transportation systems for wildlife conservation, highlighting the complex transition from laboratory-based performance to practical, operational deployment.
Keywords: Wildlife-vehicle collisions, YOLOv8, thermal imaging, centralized AI framework, intelligent transportation systems, real-time detection, wildlife conservation, computer vision, deep learning, road ecology
Keywords: Wildlife-vehicle collisions, YOLOv8, thermal imaging, centralized AI framework, intelligent transportation systems, real-time detection, wildlife conservation, computer vision, deep learning, road ecology
Abstract
Intelligent Agriculture Platform for Precision Farming
Sharmila R.B, Varsha K, Saravana Kumar M
DOI: 10.17148/IJIREEICE.2026.14387
Abstract: Agriculture plays a vital role in the economic development of many countries, especially India, where a significant portion of the population depends on farming for their livelihood. Despite this importance, many farmers still rely on traditional methods and personal experience to decide which crops to grow. These methods often ignore critical factors such as soil nutrient levels, weather conditions, and historical crop performance, which can lead to poor yield, financial losses, and inefficient use of land. With the rapid growth of Artificial Intelligence and Machine Learning, there is a strong opportunity to improve agricultural decision-making through data-driven systems. This project presents an AI-Based Smart Crop Recommendation and Yield Prediction System developed using Machine Learning and web technologies. The primary objective of the system is to recommend the most suitable crops for cultivation based on soil characteristics, weather parameters, and farm-related inputs. The system also predicts the expected crop yield, helping farmers plan their resources and investments more effectively. A Random Forest machine learning algorithm is used to analyze agricultural datasets and generate accurate crop recommendations. The model provides the top three crop suggestions along with model accuracy, improving reliability and transparency. The application is implemented as a Flask-based web platform with secure user authentication. Farmers can register, log in, manage their farm profiles, view crop recommendations, analyze soil health, review weather history, and predict crop yield. An admin module is included to allow dataset upload and model retraining, ensuring that the system can adapt to new data over time. The system uses a SQLite database for efficient data storage and retrieval. Overall, this project demonstrates how artificial intelligence can be effectively applied in agriculture to support informed decision- making, increase productivity, and promote sustainable farming practices.
Keywords: Agriculture, Machine Learning, Crop Recommendation, Yield Prediction, Random Forest, Precision Farming, Flask Web App
Keywords: Agriculture, Machine Learning, Crop Recommendation, Yield Prediction, Random Forest, Precision Farming, Flask Web App
Abstract
ANDRIOD-CONTROLLED HOME AUTOMATION WITH HC-05 BLUETOOTH AND ARDUINO FOR ENERGY – EFFICENT OPERATION
Mr. V. Brahmeswara Rao, P. Sai Vamsi Reddy
DOI: 10.17148/IJIREEICE.2026.14388
Abstract: Technology is an ever-evolving process. Designing products using current technology that improve people’s lives is a valuable contribution to society. This paper presents the design and implementation of a low-cost, flexible, and secure mobile phone-based home automation system. The system is built using a standalone Arduino BT board, with home appliances connected to its input/output ports through relays.
Communication between the mobile phone and the Arduino BT board is carried out wirelessly. The system is designed to be cost-effective and scalable, allowing multiple devices to be controlled with minimal modifications to the core structure. To ensure security, password authentication is implemented so that only authorized users can access and control the home appliances.
Keywords: Home Automation; Smartphone; Arduino; Bluetooth; Home Appliances
Communication between the mobile phone and the Arduino BT board is carried out wirelessly. The system is designed to be cost-effective and scalable, allowing multiple devices to be controlled with minimal modifications to the core structure. To ensure security, password authentication is implemented so that only authorized users can access and control the home appliances.
Keywords: Home Automation; Smartphone; Arduino; Bluetooth; Home Appliances
Abstract
Computer Vision–Driven PPE Compliance and Safety Violation Detection
Vanitha A, Rithish B, Safna M
DOI: 10.17148/IJIREEICE.2026.14389
Abstract: If you’ve ever spent even a few minutes at an active construction site, you will know it’s rarely quiet or predictable.There’s constant movement materials being shifted, machines running, people coordinating tasks, and often someone working several feet above the ground. In that kind of setting, even a minor lapse in attention can lead to a serious incident. Most accidents don’t happen because the work itself is impossible. More often, they occur because basic precautions like wearing Personal Protective Equipment (PPE) — are ignored or treated casually.
On most sites, safety is mainly handled by supervisors who walk around and keep an eye on things, or sit and watch CCTV footage. It definitely helps, but it’s not flawless. After all, no person can keep track of several workers and multiple camera screens for hours without feeling tired or losing focus. Over time, small violations can slip through simply because human attention isn’t unlimited. As construction projects grow larger and more complex, this gap becomes more noticeable.
This project looks at the problem from a slightly different angle. Instead of entirely relying on manual oversight, it introduces an automated safety monitoring system based on computer vision and deep learning. The system analyses live video streams from site cameras to detect workers and verify whether required PPE is being worn. Once a worker is identified, an object tracking module continues to follow that individual across frames. In other words, the system doesn’t just detect once and move on it keeps observing, which helps avoid missing unsafe actions during movement. Seeing a worker in the frame isn’t enough to judge their behaviour. So, pose estimation helps interpret their body position and movement during work.For example,if someone climbs without stable support or works at height without a harness, the system can interpret that posture as potentially unsafe. A rule-based alert mechanism further checks predefined safety conditions, such as entering restricted areas or remaining without protective equipment beyond an acceptable duration. When a violation is identified, the system generates a visible warning and notifies the supervisor. The intention is not to replace human decision- making, but to strengthen it and ensure quicker responses when needed.
By combining PPE detection, worker tracking, behaviour analysis, and real-time alerts within a single framework, the system improves overall site monitoring. It eases the burden on supervisors, supports early risk detection, and encourages more consistent compliance with safety standards. Ultimately, the goal is straightforward: reduce preventable accidents and create a work environment where safety is actively supported rather than assumed.
Keywords: Computer vision, deep learning, personal protective equipment (PPE), safety monitoring, YOLO, CNN, OpenCV, object tracking, pose estimation, real-time alerting.
On most sites, safety is mainly handled by supervisors who walk around and keep an eye on things, or sit and watch CCTV footage. It definitely helps, but it’s not flawless. After all, no person can keep track of several workers and multiple camera screens for hours without feeling tired or losing focus. Over time, small violations can slip through simply because human attention isn’t unlimited. As construction projects grow larger and more complex, this gap becomes more noticeable.
This project looks at the problem from a slightly different angle. Instead of entirely relying on manual oversight, it introduces an automated safety monitoring system based on computer vision and deep learning. The system analyses live video streams from site cameras to detect workers and verify whether required PPE is being worn. Once a worker is identified, an object tracking module continues to follow that individual across frames. In other words, the system doesn’t just detect once and move on it keeps observing, which helps avoid missing unsafe actions during movement. Seeing a worker in the frame isn’t enough to judge their behaviour. So, pose estimation helps interpret their body position and movement during work.For example,if someone climbs without stable support or works at height without a harness, the system can interpret that posture as potentially unsafe. A rule-based alert mechanism further checks predefined safety conditions, such as entering restricted areas or remaining without protective equipment beyond an acceptable duration. When a violation is identified, the system generates a visible warning and notifies the supervisor. The intention is not to replace human decision- making, but to strengthen it and ensure quicker responses when needed.
By combining PPE detection, worker tracking, behaviour analysis, and real-time alerts within a single framework, the system improves overall site monitoring. It eases the burden on supervisors, supports early risk detection, and encourages more consistent compliance with safety standards. Ultimately, the goal is straightforward: reduce preventable accidents and create a work environment where safety is actively supported rather than assumed.
Keywords: Computer vision, deep learning, personal protective equipment (PPE), safety monitoring, YOLO, CNN, OpenCV, object tracking, pose estimation, real-time alerting.
Abstract
Power Quality Enhancement in a Motor Manufacturing Industry using SVC
Yasoda Kailasam, Gokulavarshini R
DOI: 10.17148/IJIREEICE.2026.14390
Abstract: Power quality is a significant concern in motor manufacturing industry because of the widespread use of inductive loads. These include induction motors, welding machines, variable frequency drives and testing equipment. These loads can cause poor power factor, voltage fluctuations, excessive reactive power demand and harmonic distortion. As a result this leads to increased energy losses and reduced equipment lifespan. This study presents a detailed examination of how to improve power quality in a motor manufacturing industry using a Static Var Compensator (SVC).The proposed system uses a SVC which includes Thyristor Switched Capacitors (TSC) and Thyristor Controlled Reactors (TCR) to provide reactive power compensation.By continuously monitoring system parameters such as voltage, current, and reactive power the SVC responds in real time to load variations thereby maintaining the power factor close to unity and stabilizing the bus voltage. The performance of the SVC-based compensation plan is assessed through simulation studies conducted under different operating conditions. The results demonstrate significant improvement in power factor and enhanced voltage regulation at the point of common coupling (PCC). Additionally overall system efficiency is improved and compliance with IEEE power quality standards is achieved. According to the study's findings SVC is a practical and affordable way to enhance power quality in motor manufacturing sectors with highly variable and inductive loads.
Keywords: Static Var Compensation, Total Harmonic Distortion, IEEE 519 Standards, Reactive Power Compensation, Power Factor Improvement.
Keywords: Static Var Compensation, Total Harmonic Distortion, IEEE 519 Standards, Reactive Power Compensation, Power Factor Improvement.
Abstract
Hand Gesture Based Touchless Media Control System Using Computer Vision and Machine Learning
Ms. Subiksha R, Mr. Janarthanan S
DOI: 10.17148/IJIREEICE.2026.14391
Abstract: Recent advancements in computer vision and artificial intelligence have significantly improved the way humans interact with machines, enabling alternatives to traditional input devices such as keyboards and touchscreens. This study introduces a real-time, touchless media control system that operates entirely through hand gestures, using only a standard webcam without the need for specialized hardware.
The system utilizes the MediaPipe Hands framework to detect and track 21 three-dimensional hand landmarks in each frame. These landmarks are converted into a 63-dimensional feature vector that represents the hand’s spatial structure. A supervised machine learning pipeline was developed using five different algorithms: Random Forest, Support Vector Machine, Multilayer Perceptron, K-Nearest Neighbours, and Gradient Boosting. The models were trained on a custom dataset consisting of 2,700 labelled samples across nine distinct gesture classes.
Among the evaluated models, the Random Forest classifier delivered the best performance, achieving a test accuracy of 97.4% and a macro F1-score of 0.971. The system maintains real-time responsiveness, operating at approximately 28.6 frames per second on a standard laptop without requiring GPU support. Recognized gestures are translated into system- level media commands such as play/pause, volume control, track switching, mute, and full screen mode through a cross- platform interface.
The system was also tested under different lighting conditions, showing only a minor drop in accuracy of about 3.3% in low-light environments. Overall, the proposed approach is efficient, accessible, and platform-independent, making it a promising solution for touchless interaction in applications such as smart environments, healthcare systems, and assistive technologies.
Keywords: Hand Gesture Recognition, Computer Vision, Human-Computer Interaction, Touchless Interface, MediaPipe, Real-Time Gesture Detection, Random Forest, OpenCV, Machine Learning, Accessibility Technology.
The system utilizes the MediaPipe Hands framework to detect and track 21 three-dimensional hand landmarks in each frame. These landmarks are converted into a 63-dimensional feature vector that represents the hand’s spatial structure. A supervised machine learning pipeline was developed using five different algorithms: Random Forest, Support Vector Machine, Multilayer Perceptron, K-Nearest Neighbours, and Gradient Boosting. The models were trained on a custom dataset consisting of 2,700 labelled samples across nine distinct gesture classes.
Among the evaluated models, the Random Forest classifier delivered the best performance, achieving a test accuracy of 97.4% and a macro F1-score of 0.971. The system maintains real-time responsiveness, operating at approximately 28.6 frames per second on a standard laptop without requiring GPU support. Recognized gestures are translated into system- level media commands such as play/pause, volume control, track switching, mute, and full screen mode through a cross- platform interface.
The system was also tested under different lighting conditions, showing only a minor drop in accuracy of about 3.3% in low-light environments. Overall, the proposed approach is efficient, accessible, and platform-independent, making it a promising solution for touchless interaction in applications such as smart environments, healthcare systems, and assistive technologies.
Keywords: Hand Gesture Recognition, Computer Vision, Human-Computer Interaction, Touchless Interface, MediaPipe, Real-Time Gesture Detection, Random Forest, OpenCV, Machine Learning, Accessibility Technology.
Abstract
Anemia Detection Through Nail Imaging: From Clinical Signs to AI Solutions
Mohamed Athfan D, Noorul Hasan Z, Deepa Sre A P
DOI: 10.17148/IJIREEICE.2026.14392
Abstract: Anemia, defined by a reduction in red blood cell count or hemoglobin (Hb) concentration below normal levels, remains a significant global health issue, affecting approximately 30–40% of women and children worldwide. Early detection is critical to prevent complications such as fatigue, cognitive impairment in children, and increased maternal- fetal morbidity. Traditional diagnostic methods rely on invasive and resource-intensive blood tests, limiting accessibility in low-resource settings. This project proposes a novel, non-invasive approach for anemia detection using computer vision and deep learning techniques applied to smartphone-captured fingernail images. Visual signs such as nail-bed pallor and koilonychia (spoon-shaped nails), which correlate with hemoglobin deficiency, form the basis of this image- based screening system. The proposed framework includes assembling a labeled dataset of fingernail images paired with ground-truth Hb values from clinical and public sources. Preprocessing steps involve region of interest (ROI) extraction using YOLOv8 for fingernail detection, color normalization to account for skin tone variations and lighting inconsistencies, and data augmentation for robustness. A convolutional neural network (CNN) architecture, such as DenseNet169 or MobileNetV3, is fine-tuned for classification of anemic versus non-anemic cases. Explainable AI methods like Grad-CAM are employed to ensure model transparency and highlight relevant image regions influencing predictions. Deployment considerations include optimizing models for on-device inference using TensorFlow Lite, integrating real-time user guidance for image capture, and ensuring compliance with privacy and regulatory standards. This solution aims to democratize anemia screening, enabling scalable, accessible, and non-invasive early diagnosis in community and telehealth settings.
Keywords: Anemia detection, non-invasive, nail imaging, deep learning, computer vision, YOLOv8, DenseNet169, MobileNetV3, Explainable AI, Grad-CAM, telehealth.
Keywords: Anemia detection, non-invasive, nail imaging, deep learning, computer vision, YOLOv8, DenseNet169, MobileNetV3, Explainable AI, Grad-CAM, telehealth.
Abstract
Smart Skill Gap Analyzer for Career Readiness
Mala Bharumathi M, Madhumitha MD, Kamil Arsath Ahammed A
DOI: 10.17148/IJIREEICE.2026.14393
Abstract: In the rapidly evolving global job market, students frequently encounter challenges in discerning the requisite skills for their desired career trajectories and accurately assessing their preparedness levels. This research introduces a Smart Skill Gap Analyzer for Career Readiness, an advanced artificial intelligence (AI)-based system designed to meticulously analyse a user’s existing skill set against the dynamic demands of a target job role. The system not only precisely identifies skill discrepancies but also forecasts the potential trajectory of skill improvement over time. Leveraging a real-time dataset meticulously curated from prominent online job portals, the system captures contemporary industry skill requirements. Machine learning models, specifically Linear Regression, Random Forest, and Logistic Regression, implemented using the Scikit-learn library, are employed to estimate skill progression and predict the temporal investment required to achieve optimal job readiness. Furthermore, the system incorporates a sophisticated resume analyser for automated skill extraction and a personalized learning recommendation module that suggests pertinent courses for targeted skill enhancement. An intuitive and interactive dashboard, enriched with Matplotlib and Plotly visualizations, empowers users to monitor their progress effectively and strategically plan their learning pathways. Future enhancements envision the integration of an AI chatbot career advisor to provide more dynamic and conversational guidance.
Keywords: Skill Gap Analysis, Career Readiness, Machine Learning, Artificial Intelligence, Linear Regression, Random Forest, Logistic Regression, Scikit-learn, Resume Analysis, Personalized Learning, Career Guidance.
Keywords: Skill Gap Analysis, Career Readiness, Machine Learning, Artificial Intelligence, Linear Regression, Random Forest, Logistic Regression, Scikit-learn, Resume Analysis, Personalized Learning, Career Guidance.
Abstract
Android-Based Inventory Management System
SUNIL NAIK
DOI: 10.17148/IJIREEICE.2026.14394
Abstract: Inventory management is an essential process in businesses and organizations for tracking products, materials, and stock levels. Traditional inventory systems often involve manual record keeping, which may lead to errors and delays. Android-based inventory management systems provide a simple and efficient solution using smartphones and mobile applications. These systems help users manage stock information, update records in real time, and improve operational efficiency. This paper discusses the working, features, advantages, applications, and future scope of Android-based inventory management systems[1][2].