← Back to Archives
VOLUME 13, ISSUE 12, DECEMBER 2025
Renewable Energy: Integrated Smart Photobioreactor (PBR) For Mircoalgae Culture Application
Y.Y. Lau, T.S.Y. Moh
Design, Analysis, and Optimization of the Radiation Characteristics of a Circular Loop Antenna Using a Genetic Algorithm
Ofem Uket Omini, Etaba Aminu Agwu
Smart IOT Based Solar Robotic Grass Cutter and Water Sprinkler
Mrs. Bhavya K B, Disha Reddy K R, Dyuthi C, Hemanth P
CYBER-PHYSICAL SYSTEM FOR ENVIRONMENTAL MONITORING
Miss. Sabale Prachi Sanjay, Mr. Salve S.S.
“Design and Implementation of a Smart Irrigation System Using Soil Moisture Sensor and IoT”
G. Shri Lakshmi
Water Quality Prediction Using Machine Learning Technique
Ms. M. NANDHINI
BATTERY MANAGEMENT SYSTEM OF EV WITH HYBRID CHARGING USING IOT AND AI
Harsh Kumar Maddheshiya, Gaurav Singh, Pranjal Shukla, Rajiv, Shivam Mall, Sonali Gupta
LoRa BASED HYBRID POWER GENERATION SYSTEM
Swetha B, K A Lakshmi, Kavya I K, Ramya Inamati, Mallikarjun H
Fingerprint Based Exam Hall Authentication System
P. Thirupathi, V Rahul, D Ganesh Reddy, K Narender, G Uday Kiran
Skin Cancer (Melanoma) Detection Using Deep Learning
Pallavi R, Srinivasa H N, Mithun Gowda H, Surya S B
FTIR and UV-VIS Characterization of ZnO Produced using Neem (Azadirachta Indica) Leaves Extracts
Garba D. Sani, Aliyu Saidu, Aati Rilwanu, Suleiman Sahabi
UPI FRUAD DETECTION USING MACHINE LEARNING
Divyarani S Y, Sinchana K S, Minchu K S, Monisha B M
Design and Implementation of a Hybrid Micro- Power Energy Ecosystem for Automatic EV Charging Station
Sapna B. Verma*, Siddhartha Yadav, Divya Mishra, Manish Kumar, Nisha Kaithal
Brain Age Prediction Using MRI Data an Ensemble ANN Model
Pallavi R, Steve Fredrick P, Yashwanth Gowda KB, Rakshith Gowda NS
SMART TRAFFIC NAVIGATION SYSTEM WITH EMERGENCY VEHICLE PRIORITY USING AI-BASED SIGNAL CONTROL
Divyarani Y S, Gowtham C, Gagan Gowda G S, Vidhya A
Designing for High-Voltage Isolation, Creepage and Clearance Requirements in Medical Devices
Mahendra Ingale
Physical Design of NMOS Full Adder using Pass Transistor Logic (PTL)
Vishwas V, Moulya L, Poorvitha D, Ayush Ojha
Synergistic Manufacturing Architectures for Ultra-Precision Component Fabrication
Pallab Palta, Snehashish Hazari, Debnandan Goswami, Debojyoti Sarkar*
Design and Implementation of Binary Relevance Classifier for Leaf Classification using FPGA
Kondapally.Swathi, T. Satya Savithri
AI-Driven Zero-Trust Architecture for Enhanced Cybersecurity in Dynamic Network Environments
Meraj Farheen Ansari, Syed Sharik Ali
AI-Enhanced Safety for Heavy Load Construction Vehicles: An Integrated Embedded C++ Software Approach
Abdul Faisal Mohammed, Mohammed Akifuddin Ghori
AI-Assisted Data Quality Assessment for Big Data Pipelines: Framework, Techniques, and Empirical Evaluation
Mohammed Imran Ahmed, Syed Saifuddin Ahmed Muzaffar
GENDER DIFFERENCES IN COMMON STRESS AMONG POSTGRADUATE STUDENTS IN THE MARATHWADA REGION: A PILOT STUDY
Dr. Sunita Y. Patil
A Comparative Study of Psychological Problems with Respect to Depression Between Swimmers and Non-Swimmers in the Age Group of 24–30 Years
Dr. Pushpender Singh
Abstract
Data Engineering with AI for Smart Retail Inventory Optimization
Vikram Boga
Abstract: Smart retail—having in-store and online components—permits companies to provide support services that complement (but do not duplicate) customer value and convenience. It is thus feasible to address inventory optimization as an AI problem, taking into consideration customer needs for timely product availability without long delivery lead times. Data engineering principles reformulate inventory optimization as a recommendation engine, predicting future warehouse, store, and web inventory levels in the short and medium term for long-lead-time products to assist decisions on how much to order. A concept for a fully receptive data architecture is introduced, capable of supplying the large amount of quality-cleaned data required to train the AI models and to implement AI-based data pipelines that spatially distribute Web inventory recommendation across the supply chain. These pipelines, optimized for fast local machine learning (ML) workloads, reduce the volume of data sent to the core DB and the number of jobs initiated there, thus accelerating inventory-level refresh by making large amounts of inventory-ready data locally available. The data architecture, supporting the full data lifecycle in accordance with the smart retail concept, consists of data-ops pipelines designed for fully receptive external and internal data flows and data-engineering lines for preparatory and loading jobs dedicated to core BI information. An additional component dedicated to the implementation of AI-based data pipelines is sized to cope with the spatiotemporal distribution throughout the modelled area of slow-loading-tagged external data. Inventory-level refresh is accelerated by minimizing the volume of data sent to the core DB and the number of jobs initiated there, thus enabling core data availability that supports fast local ML workloads and local supply-demand analysis.
Keywords: Smart Retail Systems, Omnichannel Retail Architecture, AI-Based Inventory Optimization, Inventory Recommendation Engines, Predictive Inventory Forecasting, Retail Data Engineering, Smart Supply Chain Analytics, Web And Store Inventory Integration, Data-Ops Pipelines In Retail, AI-Driven Data Pipelines, Local Machine Learning Workloads, Spatiotemporal Inventory Distribution, Retail Data Lifecycle Management, Inventory-Level Refresh Optimization, Edge-Optimized Retail Analytics, Demand–Supply Alignment, Long Lead-Time Product Planning, Retail BI Data Architecture, Scalable Retail Data Platforms, AI-Enabled Inventory Decision Support.
Keywords: Smart Retail Systems, Omnichannel Retail Architecture, AI-Based Inventory Optimization, Inventory Recommendation Engines, Predictive Inventory Forecasting, Retail Data Engineering, Smart Supply Chain Analytics, Web And Store Inventory Integration, Data-Ops Pipelines In Retail, AI-Driven Data Pipelines, Local Machine Learning Workloads, Spatiotemporal Inventory Distribution, Retail Data Lifecycle Management, Inventory-Level Refresh Optimization, Edge-Optimized Retail Analytics, Demand–Supply Alignment, Long Lead-Time Product Planning, Retail BI Data Architecture, Scalable Retail Data Platforms, AI-Enabled Inventory Decision Support.
Abstract
Renewable Energy: Integrated Smart Photobioreactor (PBR) For Mircoalgae Culture Application
Y.Y. Lau, T.S.Y. Moh
DOI: 10.17148/IJIREEICE.2025.131201
Abstract: In this study, the focus will be on the design and development of a smart photobioreactor (PBR) for microalgae culture with integrated harvesting components meant for renewable energy application. While there are lots of PBR designs have been reported, but the harvesting unit is not integrated in the PBR or built separately/stand-alone. Therefore, the extraction process is not straight-forward and will be a bit complicated during harvesting. Having a stand-alone harvesting unit means it involves more manpower and need to be manually done which is not error proof. In this paper, the idea is to have a PBR that is smartly monitor or control the growth or cultivation of the microalgae at its most optimum growth parameters together with a built-in harvesting system which will collect the output from microalgae automatically and in a closed-loop manner. For this purpose, a prototype of a PBR was built to mimic a relatively real-case growth condition.
Keywords: Photobioreactor; Microalgae culture; Smart; Integrated; Harvesting; Renewable energy.
Keywords: Photobioreactor; Microalgae culture; Smart; Integrated; Harvesting; Renewable energy.
Abstract
Design, Analysis, and Optimization of the Radiation Characteristics of a Circular Loop Antenna Using a Genetic Algorithm
Ofem Uket Omini, Etaba Aminu Agwu
DOI: 10.17148/IJIREEICE.2025.131202
Abstract: This study presents the design, analysis, and optimization of the radiation characteristics of a circular loop antenna employing a Genetic Algorithm (GA) to achieve enhanced performance across desired frequency bands. The circular loop antenna was modeled and simulated using the GA tool box in MATLAB, and key parameters such as loop radius, conductor radius, feed position, and substrate properties were optimized using GA to improve gain, bandwidth, and radiation efficiency. The optimization process utilized a fitness function that minimized return loss and maximized radiation resistance, leading to an optimal configuration that outperformed conventional designs. Simulation results demonstrate that the GA-optimized antenna exhibits improved impedance matching and stable radiation patterns over a wide frequency range. The proposed method confirms the effectiveness of evolutionary algorithms in antenna design, providing a robust framework for the automated optimization of microwave and wireless communication antennas.
Keywords: Circular loop antenna, Optimization, Genetic Algorithm, MATLAB, Radiation resistance, Radiation pattern, Gain.
Keywords: Circular loop antenna, Optimization, Genetic Algorithm, MATLAB, Radiation resistance, Radiation pattern, Gain.
Abstract
Smart IOT Based Solar Robotic Grass Cutter and Water Sprinkler
Mrs. Bhavya K B, Disha Reddy K R, Dyuthi C, Hemanth P
DOI: 10.17148/IJIREEICE.2025.131203
Abstract: Traditional grass-cutting machines depend on manual operation and the use of fossil fuels, which leads to environmental pollution, increased operational costs, and greater physical effort. To overcome these limitations, this project proposes the design and implementation of a solar powered grass cutter integrated with a water sprinkler system. The robot operates wirelessly through a Bluetooth-based mobile application that enables remote control of its movement and functionality. The core of the system is the Arduino UNO microcontroller, which coordinates motor control, blade operation, and sprinkler activation. A solar panel is used to charge the onboard rechargeable battery, ensuring continuous operation using renewable energy. The drive mechanism employs DC motors for mobility, and the cutting blade is powered through a high-torque motor for efficient grass trimming. The water sprinkler system is interfaced with a mini water pump that can be activated as required. This system minimizes human intervention, promotes energy efficiency, and eliminates dependency on fossil fuels. The portable design and eco-friendly operation make the robot suitable for home gardens, institutional lawns, and small-scale agricultural fields. The integration of solar energy and wireless control enhances both sustainability and ease of use, contributing to smart automation in agricultural and domestic maintenance applications.
Keywords: Solar-powered, Bluetooth based, portable design, high-torque.
Keywords: Solar-powered, Bluetooth based, portable design, high-torque.
Abstract
CYBER-PHYSICAL SYSTEM FOR ENVIRONMENTAL MONITORING
Miss. Sabale Prachi Sanjay, Mr. Salve S.S.
DOI: 10.17148/IJIREEICE.2025.131204
Abstract: Cyber-Physical System for Environmental Monitoring addresses the growing challenges posed by rapid environmental pollution, urbanisation, and industrialisation by providing an intelligent and automated monitoring solution. Traditional environmental data collection methods are slow, geographically limited, and lack real-time analytical capabilities. This project presents the design and implementation of an IoT-integrated Cyber-Physical System (CPS) that enables continuous, real-time environmental monitoring and analysis.
The system uses a Raspberry Pi 4 as the central processing unit, interfaced with low-cost sensors including the DHT11 for temperature and humidity, MQ135 for air quality, BMP180 for atmospheric pressure, and an LDR for light intensity measurement. These sensors collect real-time environmental data that are processed locally and transmitted wirelessly via the Raspberry Pi’s built-in Wi-Fi to the ThingSpeak cloud platform using HTTP/MQTT protocols. The cloud layer supports data storage, visualization, and remote analysis through interactive dashboards, enabling timely decision- making.
The integrated CPS architecture successfully combines sensing, computation, and communication, while automated alerts are triggered when environmental parameters exceed predefined thresholds, enabling proactive responses to hazardous conditions. The system ensures accuracy, scalability, low power consumption, and cost-effectiveness, making it suitable for deployment in smart cities, industrial zones, and agricultural environments.
Moreover, this project establishes a foundation for future advancements such as AI-driven predictive analytics and edge computing to support autonomous environmental control. Overall, the developed system contributes to sustainable environmental management and aligns with UN Sustainable Development Goal 13 (Climate Action) by promoting intelligent, data-driven monitoring for a safer and cleaner environment.
The system uses a Raspberry Pi 4 as the central processing unit, interfaced with low-cost sensors including the DHT11 for temperature and humidity, MQ135 for air quality, BMP180 for atmospheric pressure, and an LDR for light intensity measurement. These sensors collect real-time environmental data that are processed locally and transmitted wirelessly via the Raspberry Pi’s built-in Wi-Fi to the ThingSpeak cloud platform using HTTP/MQTT protocols. The cloud layer supports data storage, visualization, and remote analysis through interactive dashboards, enabling timely decision- making.
The integrated CPS architecture successfully combines sensing, computation, and communication, while automated alerts are triggered when environmental parameters exceed predefined thresholds, enabling proactive responses to hazardous conditions. The system ensures accuracy, scalability, low power consumption, and cost-effectiveness, making it suitable for deployment in smart cities, industrial zones, and agricultural environments.
Moreover, this project establishes a foundation for future advancements such as AI-driven predictive analytics and edge computing to support autonomous environmental control. Overall, the developed system contributes to sustainable environmental management and aligns with UN Sustainable Development Goal 13 (Climate Action) by promoting intelligent, data-driven monitoring for a safer and cleaner environment.
Abstract
“Design and Implementation of a Smart Irrigation System Using Soil Moisture Sensor and IoT”
G. Shri Lakshmi
DOI: 10.17148/IJIREEICE.2025.131205
Abstract: This paper presents an soil moisture sensor to detect the moisture content in the soil and an NodeMCU (ESP32) Microcontroller Board to control a water pump. The system uses a IoT-based smart irrigation system designed to automatically control water flow according to soil moisture levels. When the soil is dry, the motor is switched ON to provide water, and it automatically switches OFF when the required moisture level is reached. The project is further enhanced using IoT, allowing users to monitor and control the irrigation process remotely via the internet. This approach ensures efficient water usage, reduces manual effort, and is especially beneficial for agricultural and home gardening applications.
Keywords: IoT, NodeMCU (ESP32) Microcontroller, Soil Moisture Sensor, Smart Irrigation, Automated Watering System
Keywords: IoT, NodeMCU (ESP32) Microcontroller, Soil Moisture Sensor, Smart Irrigation, Automated Watering System
Abstract
Water Quality Prediction Using Machine Learning Technique
Ms. M. NANDHINI
DOI: 10.17148/IJIREEICE.2025.131206
Abstract: Water quality assessment is essential for ensuring public health, environmental safety, and sustainable water resource management. Traditional methods of water monitoring rely on manual sampling and laboratory analysis, which are often time-consuming, expensive, and incapable of providing real-time insights. This study proposes a machine learning (ML)-based framework for accurate and timely prediction of water quality parameters such as pH, turbidity, dissolved oxygen, nitrates, and phosphates. Historical and sensor-based datasets are utilized to train and evaluate supervised ML models, including Random Forest (RF), Support Vector Machine (SVM), and XGBoost. Data preprocessing, feature selection, and model evaluation are incorporated to enhance prediction accuracy. Experimental results demonstrate that the proposed ML models can reliably forecast water quality metrics, providing early warnings of potential contamination events. This approach not only reduces dependence on manual testing but also supports real-time water management and pollution mitigation strategies, making it suitable for smart city and industrial applications.
Keywords: Water Quality Prediction, Machine Learning, Random Forest, XGBoost, Support Vector Machine, Environmental Monitoring, Predictive Analytics
Keywords: Water Quality Prediction, Machine Learning, Random Forest, XGBoost, Support Vector Machine, Environmental Monitoring, Predictive Analytics
Abstract
BATTERY MANAGEMENT SYSTEM OF EV WITH HYBRID CHARGING USING IOT AND AI
Harsh Kumar Maddheshiya, Gaurav Singh, Pranjal Shukla, Rajiv, Shivam Mall, Sonali Gupta
DOI: 10.17148/IJIREEICE.2025.131207
Abstract: Future Electrical vehicles (EV) are widely praised for their environmental benefits, superior efficiency, and enhanced driving experience compare to conventional internal combustion engine (IC) vehicles. They represent a significant stepping sustainable transportation, though they still phase challenges related to initial cost and infrastructure. BMS systems will not only extend the battery life and promote safe operation, but also incorporate two new functionalities: the capability to optimize scheduling and utilization lifetime, and the ability to detect and diagnose anomalies early to enable predictive maintenance and minimize downtime. Furthermore, BMS development and deployment for hybrid energy storage and end-of-life equipment repurposing are key enablers for achieving the broad adoption of electric vehicles and the accelerated integration of renewable energy into the electrical grid.
Keywords: Battery Management System, Electric Vehicles, Hybrid Charging, Artificial Intelligence, Internet of Things, Machine Learning, Datasets.
Keywords: Battery Management System, Electric Vehicles, Hybrid Charging, Artificial Intelligence, Internet of Things, Machine Learning, Datasets.
Abstract
LoRa BASED HYBRID POWER GENERATION SYSTEM
Swetha B, K A Lakshmi, Kavya I K, Ramya Inamati, Mallikarjun H
DOI: 10.17148/IJIREEICE.2025.131208
Abstract: The project develops a solar–wind hybrid power generation system with battery storage to ensure a reliable and sustainable energy supply. It uses an energy management system, MPPT charge controllers, inverter, and real-time monitoring to optimize power generation, storage, and usage while protecting system components. Designed for residential and small commercial applications, the system provides continuous power, improves efficiency, and supports energy independence with reduced environmental impact.
Keyword: Wind Turbines, system, power, MPPT
Keyword: Wind Turbines, system, power, MPPT
Abstract
Fingerprint Based Exam Hall Authentication System
P. Thirupathi, V Rahul, D Ganesh Reddy, K Narender, G Uday Kiran
DOI: 10.17148/IJIREEICE.2025.131210
Abstract: In educational institutions, ensuring the integrity of exams and preventing malpractice is a growing concern. Traditional methods of student authentication during exams, such as student ID cards or roll call, are prone to human errors and fraud. This paper proposes a fingerprint-based exam hall authentication system to improve security and ensure accurate identity verification. By leveraging biometric fingerprint recognition, the system provides a more secure, efficient, and automated solution for confirming student identity before and during exams.
The proposed system captures the student's fingerprint using a fingerprint scanner, which is then matched with a pre- enrolled fingerprint database to authenticate the student. This approach eliminates the possibility of impersonation and helps to prevent cheating. Additionally, the system records each authentication event, creating a reliable log that can be used for audit purposes.
The implementation of the fingerprint-based system not only enhances security but also streamlines the exam process by reducing the need for manual checks and enhancing the overall exam experience. Furthermore, the system can be integrated with existing exam management software to facilitate seamless operations.
The proposed system captures the student's fingerprint using a fingerprint scanner, which is then matched with a pre- enrolled fingerprint database to authenticate the student. This approach eliminates the possibility of impersonation and helps to prevent cheating. Additionally, the system records each authentication event, creating a reliable log that can be used for audit purposes.
The implementation of the fingerprint-based system not only enhances security but also streamlines the exam process by reducing the need for manual checks and enhancing the overall exam experience. Furthermore, the system can be integrated with existing exam management software to facilitate seamless operations.
Abstract
Skin Cancer (Melanoma) Detection Using Deep Learning
Pallavi R, Srinivasa H N, Mithun Gowda H, Surya S B
DOI: 10.17148/IJIREEICE.2025.131211
Abstract: Melanoma is one of the deadliest forms of skin cancer, and early diagnosis is critical for improving patient survival rates. This paper presents a deep learning-based melanoma detection system that classifies dermoscopic skin images into benign and malignant categories. The proposed system employs a Convolutional Neural Network (CNN) with EfficientNet architecture for accurate feature extraction and classification. A Flask-based web application is developed to enable users to upload images and receive real-time predictions. The experimental results demonstrate that the proposed approach achieves reliable accuracy and can assist dermatologists in clinical decision-making The proposed system employs a Convolutional Neural Network (CNN) using EfficientNet architecture to classify dermoscopic skin lesion images into benign and malignant categories. Image preprocessing techniques including resizing, normalization, and data augmentation are applied to enhance model robustness and reduce overfitting. The trained model is integrated into a web-based application using the Flask framework, enabling users to upload skin lesion images and receive real-time prediction results.
Keywords: Melanoma Detection, Deep Learning, CNN, EfficientNet, Medical Image Analysis
Keywords: Melanoma Detection, Deep Learning, CNN, EfficientNet, Medical Image Analysis
Abstract
FTIR and UV-VIS Characterization of ZnO Produced using Neem (Azadirachta Indica) Leaves Extracts
Garba D. Sani, Aliyu Saidu, Aati Rilwanu, Suleiman Sahabi
DOI: 10.17148/IJIREEICE.2025.131212
Abstract: The growing demand for sustainable nanomaterials has intensified interest in green synthesis methods that utilize plant extracts as reducing and stabilizing agents. This research focuses on the green synthesis and characterization of zinc oxide (ZnO) nanoparticles using Neem (Azadirachta indica) leaves extract by employing simulation technique. Ultraviolet–Visible (UV–VIS) spectroscopy, Fourier Transform Infrared (FTIR) Spectroscopy and Hall-effect electrical transport properties in the other way were used to determine optical properties, functional groups with structural features and electrical transport properties respectively of the produced ZnO using simulation technique. UV–VIS spectra revealed a strong absorption peak around 360–380 nm, confirming the presence of ZnO nanoparticles and indicating a blue-shift associated with nanoscale dimensions. FTIR spectra displayed characteristic Zn–O vibrational bands between 430–500 cm⁻¹, along with phytochemical signatures responsible for reduction and capping. Hall measurements indicate n-type conductivity with carrier concentrations in the 1017–1019 cm⁻³ range and mobilities of 8–32 cm²V⁻¹s⁻¹. The findings confirm that Neem extract is an efficient biogenic agent for synthesizing ZnO nanoparticles with desirable optical and functional characteristics. The study also demonstrates that Neem-extract- mediated ZnO shows optical and electrical properties compatible with photovoltaic window layers and UV-sensing applications, while offering an eco-friendly synthesis route. The ecological and material advantages of plant-based nanoparticle synthesis were highlighted and baseline data for applications in environmental remediation, photocatalysis, and biomedical fields were provided.
Keywords: ZnO nanoparticles, Neem extract, green synthesis, FTIR, UV–VIS, Hall Effect.
Keywords: ZnO nanoparticles, Neem extract, green synthesis, FTIR, UV–VIS, Hall Effect.
Abstract
UPI FRUAD DETECTION USING MACHINE LEARNING
Divyarani S Y, Sinchana K S, Minchu K S, Monisha B M
DOI: 10.17148/IJIREEICE.2025.131213
Abstract: With the rapid growth of digital payment systems in India, the Unified Payments Interface (UPI) has become one of the most widely used platforms for real-time financial transactions. While UPI offers convenience, speed, and accessibility, it has also become a target for fraudulent activities such as unauthorized transactions, phishing attacks, identity theft, and account takeovers. These increasing fraud incidents highlight the need for an intelligent and automated fraud detection system to ensure secure digital transactions. This project presents a UPI Fraud Detection System using Machine Learning techniques to identify and prevent fraudulent transactions in real time. The proposed system analyzes historical transaction data and user behavior patterns to distinguish between legitimate and fraudulent activities. Key features such as transaction amount, transaction frequency, time of transaction, location variance, device usage, and transaction velocity are extracted and processed for model training. Machine learning algorithms such as Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) are applied to classify transactions as either genuine or fraudulent.
Keywords: UPI FRUAD , Machine learning , historical transaction,random forest, fraudulent
Keywords: UPI FRUAD , Machine learning , historical transaction,random forest, fraudulent
Abstract
Design and Implementation of a Hybrid Micro- Power Energy Ecosystem for Automatic EV Charging Station
Sapna B. Verma*, Siddhartha Yadav, Divya Mishra, Manish Kumar, Nisha Kaithal
DOI: 10.17148/IJIREEICE.2025.131214
Abstract: With the rapid growth of electric vehicles (EVs), the demand for safe, efficient, and user- friendly charging infrastructure has become a major challenge. Conventional plug-in charging systems often face issues such as cable wear, electrical hazards, and lack of automation. To address these limitations, this study proposes a fully automated wireless EV charging system that enhances both safety and convenience. The system uses an Arduino Nano as the central controller, integrating an RFID module for user authentication, a relay for controlled power switching, and a buck converter for voltage regulation. Once an authorized user is detected through RFID, the system automatically initiates wireless charging and continuously monitors parameters such as voltage, current, and time through a serial interface for cost estimation. The proposed design eliminates manual intervention, minimizes connection-related risks, and provides a reliable and low-cost solution for modern EV charging applications. This automated system demonstrates a smart approach to developing safer and more accessible EV infrastructure.
Keywords: Electric vehicles, wireless power transfer, RFID authentication, Arduino Nano, automated charging system, relay control, buck converter, IoT monitoring, smart EV infrastructure, contactless charging.
Keywords: Electric vehicles, wireless power transfer, RFID authentication, Arduino Nano, automated charging system, relay control, buck converter, IoT monitoring, smart EV infrastructure, contactless charging.
Abstract
Brain Age Prediction Using MRI Data an Ensemble ANN Model
Pallavi R, Steve Fredrick P, Yashwanth Gowda KB, Rakshith Gowda NS
DOI: 10.17148/IJIREEICE.2025.131215
Abstract: Brain Age Prediction was developed to address the need for early identification and monitoring of neurodegenerative changes before clinical symptoms appear. Traditional methods rely on cognitive testing and expert MRI interpretation, often leading to late diagnoses. This project introduces a web portal that converts routine MRI scans into predictions of healthy-brain lifespan using machine learning and large neuroimaging datasets. Using the OpenBHB dataset (3,985 individuals aged 5.9–88), four volumetric biomarkers—total intracranial volume, cerebrospinal fluid volume, gray matter volume, and white matter volume—were extracted via K-means clustering and standardized. Chronological age served as the regression target. Three neural architectures were developed: Ultra_ResDNN (residual connections), Ultra_WideDeep (wide-linear + deep-MLP), and Ultra_Attention (multi-head self-attention). Outputs were ensembled to yield robust predictions. On a held-out test set, the ensemble achieved a mean absolute error of 0.58 years and explained 96.38% of variance (R² = 0.9638), demonstrating clinical-grade accuracy.
Abstract
SMART TRAFFIC NAVIGATION SYSTEM WITH EMERGENCY VEHICLE PRIORITY USING AI-BASED SIGNAL CONTROL
Divyarani Y S, Gowtham C, Gagan Gowda G S, Vidhya A
DOI: 10.17148/IJIREEICE.2025.131216
Abstract: Rapid urbanization and the continuous increase in vehicle population have resulted in severe traffic congestion in metropolitan cities. Conventional traffic signal systems operate on fixed time intervals and fail to adapt dynamically to real-time traffic density, often leading to unnecessary delays. One of the most critical consequences of such inefficiency is the delayed movement of emergency vehicles such as ambulances, fire engines, and police vehicles. This project presents a Smart Traffic Navigation System that dynamically controls traffic signals based on lane-wise vehicle density and provides absolute priority to emergency vehicles. The system is implemented using Python and Pygame, simulating a real-world four-way intersection with intelligent traffic management. When an emergency vehicle is detected, the system overrides normal traffic flow and creates a clear emergency corridor.
Abstract
Designing for High-Voltage Isolation, Creepage and Clearance Requirements in Medical Devices
Mahendra Ingale
DOI: 10.17148/IJIREEICE.2025.131217
Abstract: As electrification accelerates across the automotive, industrial, and medical domains, ensuring electrical safety and system reliability in high-voltage environments has become a critical design challenge. The integration of high- voltage circuits within the compact, complex housings of medical electromechanical devices presents critical safety challenges. This paper explores the design considerations for ensuring proper high-voltage isolation, with an emphasis on creepage and clearance distances, insulation coordination, and material selection within electromechanical housings. Special focus is given to patient and operator protection as defined by MOPP (Means of Patient Protection) and MOOP (Means of Operator Protection) under IEC 60601-1, alongside practical guidance on structural design, risk mitigation, and validation testing.
The integration of high-voltage electrical systems into compact electromechanical housing has introduced new complexities in insulation coordination and safety design. Medical devices such as infusion pumps, imaging systems, surgical robots, and dialysis machines increasingly integrate electromechanical systems that operate at potentially hazardous voltages. Their housings must safely contain and isolate these electrical components while often remaining compact and lightweight.
Distances are governed by strict international safety standards such as IEC 60664-1, which provides insulation coordination rules, and domain-specific regulations like IEC 60601-1 for medical devices. The required distances vary based on several factors: working voltage, pollution degree, material tracking resistance (CTI), altitude, and insulation type (functional, basic, and reinforced).
Keywords: Creepage clearance, Medical domain, Electromechanical devices, CTI, Housing
The integration of high-voltage electrical systems into compact electromechanical housing has introduced new complexities in insulation coordination and safety design. Medical devices such as infusion pumps, imaging systems, surgical robots, and dialysis machines increasingly integrate electromechanical systems that operate at potentially hazardous voltages. Their housings must safely contain and isolate these electrical components while often remaining compact and lightweight.
Distances are governed by strict international safety standards such as IEC 60664-1, which provides insulation coordination rules, and domain-specific regulations like IEC 60601-1 for medical devices. The required distances vary based on several factors: working voltage, pollution degree, material tracking resistance (CTI), altitude, and insulation type (functional, basic, and reinforced).
Keywords: Creepage clearance, Medical domain, Electromechanical devices, CTI, Housing
Abstract
Physical Design of NMOS Full Adder using Pass Transistor Logic (PTL)
Vishwas V, Moulya L, Poorvitha D, Ayush Ojha
DOI: 10.17148/IJIREEICE.2025.131218
Abstract: This project presents an NMOS-based Full Adder designed using Pass Transistor Logic to achieve low power, high speed, and compact layout. The design was implemented in Cadence Virtuoso at the 180 nm technology node to minimize the number of transistors and area compared to standard CMOS adders. A restoration circuit ensures full logic levels for reliable performance. Simulation results confirm the improvement in efficiency and make the design suitable for low-power VLSI and embedded applications.
Keywords: NMOS, Pass Transistor Logic, Full Adder, Low Power VLSI, Cadence Virtuoso, CMOS, Integrated Circuit Design.
Keywords: NMOS, Pass Transistor Logic, Full Adder, Low Power VLSI, Cadence Virtuoso, CMOS, Integrated Circuit Design.
Abstract
Synergistic Manufacturing Architectures for Ultra-Precision Component Fabrication
Pallab Palta, Snehashish Hazari, Debnandan Goswami, Debojyoti Sarkar*
DOI: 10.17148/IJIREEICE.2025.131219
Abstract: This paper explores the design and analysis of hybrid manufacturing processes for producing high-precision parts. Hybrid manufacturing combines traditional subtractive methods with additive manufacturing techniques to leverage the strengths of both approaches. The study focuses on the integration of these processes to achieve superior precision, reduced material waste, and enhanced production efficiency. Through a detailed analysis of various hybrid manufacturing techniques, this paper aims to provide insights into the optimal strategies for producing high-precision components. The findings highlight the potential of hybrid manufacturing in meeting the demands of industries requiring precise and complex parts.
Keywords: Hybrid manufacturing processes, Multi-process integration, Laser-assisted machining, Ultrasonic-assisted manufacturing, Micro-machining, CAD/CAM integration, Finite Element Analysis (FEA), Dimensional accuracy, Process modeling and simulation, Surface integrity analysis.
Keywords: Hybrid manufacturing processes, Multi-process integration, Laser-assisted machining, Ultrasonic-assisted manufacturing, Micro-machining, CAD/CAM integration, Finite Element Analysis (FEA), Dimensional accuracy, Process modeling and simulation, Surface integrity analysis.
Abstract
Design and Implementation of Binary Relevance Classifier for Leaf Classification using FPGA
Kondapally.Swathi, T. Satya Savithri
DOI: 10.17148/IJIREEICE.2025.131220
Abstract: This paper presents an enhanced real-time multilabel leaf classification system based on the Binary Relevance (BR) approach, efficiently implemented on the Xilinx PYNQ-Z2 FPGA platform. The multilabel classification task is decomposed into independent binary Support Vector Machine (SVM) models, each dedicated to identifying a specific leaf type, enabling modular scalability and parallel inference potential. Image preprocessing and feature extraction are performed using Python and OpenCV on the Processing System (PS), ensuring robust handling of diverse imaging conditions. Classification control logic is designed in Verilog and rigorously validated through simulation, guaranteeing precise sequencing and reliable hardware-software coordination. A user-friendly button-triggered prediction mechanism initiates on-demand classification, with results visually conveyed via onboard LEDs. Evaluated on both standard and custom datasets, the system demonstrates superior robustness against challenges such as low-light conditions, image rotation, and scale variations. Achieving high classification accuracy (>93%), ultra-low latency, and minimal power consumption, the proposed FPGA-based solution establishes a highly effective, deployable framework for embedded plant monitoring and precision agriculture applications.
Keywords: Binary Relevance, FPGA, Leaf Classification, PYNQ-Z2, Support Vector Machine, Embedded System, Real-time Prediction
Keywords: Binary Relevance, FPGA, Leaf Classification, PYNQ-Z2, Support Vector Machine, Embedded System, Real-time Prediction
Abstract
AI-Driven Zero-Trust Architecture for Enhanced Cybersecurity in Dynamic Network Environments
Meraj Farheen Ansari, Syed Sharik Ali
DOI: 10.17148/IJIREEICE.2025.131221
Abstract: Cloud computing, remote work, the Internet of Things (IoT), and internationally distributed network environments are all fast changing, making traditional perimeter-based security solutions useless against emerging cyberthreats. Zero-Trust Architecture (ZTA) is based on the principle that "never trust, always verify." Access, authorization, and authentication are continuously needed even though the least amount of electricity is used. Due to their reliance on manual installation, strict limitations, and laws that forbid modifications, many of today's Zero-Trust systems find it difficult to adjust to changing attack patterns and sophisticated user behavior.
The Zero-Trust Architecture proposed in this work makes use of artificial intelligence to facilitate dynamic trust evaluation and real-time access limitation. They do this by using machine learning and advanced analytics. Real-time risk and trust scores for apps, devices, and users are computed using contextual awareness, behavioral analytics, and continuous monitoring. The system employs deep learning-based behavioral modelling, AI-driven anomaly detection, and reinforcement learning for policy optimization to identify who has access to what and what threats are likely to materialize.
A thorough architectural framework is presented in the article, which includes important elements like the trust evaluation module, the AI-powered policy engine, the telemetry gathering layer, and the policy implementation locations. In tests using real-world cybersecurity datasets, our approach fared better than current rule-based Zero-Trust systems in terms of response time, false positives, and threat detection. According to the results, AI can change Zero- Trust from a static security framework into an active defence system that adjusts itself. This study contributes to the expanding literature on intelligent cybersecurity by offering a Zero-Trust framework that is future-proof, scalable, and dependable. Because of this, it may be applied to both enterprise and contemporary cloud-native systems.
Keywords: Machine learning, AI, cloud security, network security, continuous authentication, anomaly detection, trust assessment, adaptive access control, and zero-trust architecture are a few examples. Machine learning, AI, cloud security, network security, continuous authentication, anomaly detection, trust assessment, adaptive access control, and zero-trust architecture are a few examples.
The Zero-Trust Architecture proposed in this work makes use of artificial intelligence to facilitate dynamic trust evaluation and real-time access limitation. They do this by using machine learning and advanced analytics. Real-time risk and trust scores for apps, devices, and users are computed using contextual awareness, behavioral analytics, and continuous monitoring. The system employs deep learning-based behavioral modelling, AI-driven anomaly detection, and reinforcement learning for policy optimization to identify who has access to what and what threats are likely to materialize.
A thorough architectural framework is presented in the article, which includes important elements like the trust evaluation module, the AI-powered policy engine, the telemetry gathering layer, and the policy implementation locations. In tests using real-world cybersecurity datasets, our approach fared better than current rule-based Zero-Trust systems in terms of response time, false positives, and threat detection. According to the results, AI can change Zero- Trust from a static security framework into an active defence system that adjusts itself. This study contributes to the expanding literature on intelligent cybersecurity by offering a Zero-Trust framework that is future-proof, scalable, and dependable. Because of this, it may be applied to both enterprise and contemporary cloud-native systems.
Keywords: Machine learning, AI, cloud security, network security, continuous authentication, anomaly detection, trust assessment, adaptive access control, and zero-trust architecture are a few examples. Machine learning, AI, cloud security, network security, continuous authentication, anomaly detection, trust assessment, adaptive access control, and zero-trust architecture are a few examples.
Abstract
AI-Enhanced Safety for Heavy Load Construction Vehicles: An Integrated Embedded C++ Software Approach
Abdul Faisal Mohammed, Mohammed Akifuddin Ghori
DOI: 10.17148/IJIREEICE.2025.131222
Abstract: Dump trucks, cranes, excavators, and loaders are among the heavy load vehicles used on construction sites that have significantly increased in number as a result of the quick growth of infrastructure. These devices greatly increase production, but they also pose serious safety issues because they are hard to spot, site circumstances change, people grow tired, equipment malfunctions, and they are near employees. In order to enhance the safety, dependability, and accident avoidance of high-load construction trucks, this article proposes a comprehensive safety framework that integrates Artificial Intelligence (AI) and Embedded C++. Using cameras, radar, lidar, inertial sensors, and load cells, the suggested system aggregates data from several sensors. Additionally, it uses real-time edge AI models to identify dangers, monitor blind spots, avoid overloads, and detect hazards. A real-time operating system (RTOS) and a safety- critical embedded software architecture designed in modern C++ (C++17/20) guarantee that the system can handle faults, respond consistently, and connect safely to car actuators. For extended use, the framework incorporates fail-safe modes, extra watchdogs, and safe over-the-air updates. Controlled field testing and simulations are used to generate an exact experimental design. Time-to-intervention, false alarm rate, detection accuracy, system delay, and system availability are examples of performance measures. The suggested approach shows how AI-assisted active safety systems can be implemented on resource-constrained embedded platforms while meeting dependability and real-time requirements. The next generation of smart construction vehicles will have a workable, scalable, and industry-ready solution thanks to this effort.
Keywords: fault-tolerant systems, sensor fusion, embedded C++ systems, high load trucks, construction safety, predictive risk assessment, autonomous safety intervention, edge artificial intelligence, real-time operating systems (RTOS), and IoT-enabled construction equipment.
Keywords: fault-tolerant systems, sensor fusion, embedded C++ systems, high load trucks, construction safety, predictive risk assessment, autonomous safety intervention, edge artificial intelligence, real-time operating systems (RTOS), and IoT-enabled construction equipment.
Abstract
AI-Assisted Data Quality Assessment for Big Data Pipelines: Framework, Techniques, and Empirical Evaluation
Mohammed Imran Ahmed, Syed Saifuddin Ahmed Muzaffar
DOI: 10.17148/IJIREEICE.2025.131223
Abstract: Data is continuously coming in from many sources at a fast rate in today's big data ecosystems. Because of this, making ensuring the data is of a suitable quality is both crucial and challenging. Inaccurate analytics outputs and worse performance, fairness, and credibility of later AI models can result from poor data quality, which can show up as missing values, inconsistencies, anomalies, duplication, and delayed updates. The conventional methods of evaluating data quality—static rules, manual profiling, and preset limitations—do not work well with big data pipelines that are constantly changing.
An approach for AI-assisted data quality evaluation that can be used to both massive batch and streaming pipelines is covered in this paper. In order to automatically profile data, detect quality problems, and produce adaptive quality ratings for a range of attributes like completeness, consistency, correctness, timeliness, and validity, the suggested method makes use of machine learning and deep learning. Unsupervised models for anomaly detection include autoencoders and isolation forests. In contrast, supervised learning techniques estimate quality labels and scores based on expert feedback and historical data. The architecture provides a way for the system to keep learning, allowing it to adjust when pipeline configurations and data distributions change.
The AI-assisted approach beats conventional rule-based approaches at identifying intricate and previously unidentified data quality problems, according to an experimental evaluation using real-world big data workloads. The findings also demonstrate that downstream analytics and machine learning models perform better when trained on data validated by the suggested approach. All things considered, our study shows that AI-driven data quality assessment may be a scalable, flexible, and astute way to guarantee that future large data pipelines contain accurate data.
Keywords: AI-driven data quality and big data pipelines assessing data quality, applying machine learning, identifying anomalies, profiling, streaming, and data governance. clever engineering of data.
An approach for AI-assisted data quality evaluation that can be used to both massive batch and streaming pipelines is covered in this paper. In order to automatically profile data, detect quality problems, and produce adaptive quality ratings for a range of attributes like completeness, consistency, correctness, timeliness, and validity, the suggested method makes use of machine learning and deep learning. Unsupervised models for anomaly detection include autoencoders and isolation forests. In contrast, supervised learning techniques estimate quality labels and scores based on expert feedback and historical data. The architecture provides a way for the system to keep learning, allowing it to adjust when pipeline configurations and data distributions change.
The AI-assisted approach beats conventional rule-based approaches at identifying intricate and previously unidentified data quality problems, according to an experimental evaluation using real-world big data workloads. The findings also demonstrate that downstream analytics and machine learning models perform better when trained on data validated by the suggested approach. All things considered, our study shows that AI-driven data quality assessment may be a scalable, flexible, and astute way to guarantee that future large data pipelines contain accurate data.
Keywords: AI-driven data quality and big data pipelines assessing data quality, applying machine learning, identifying anomalies, profiling, streaming, and data governance. clever engineering of data.
Abstract
GENDER DIFFERENCES IN COMMON STRESS AMONG POSTGRADUATE STUDENTS IN THE MARATHWADA REGION: A PILOT STUDY
Dr. Sunita Y. Patil
DOI: 10.17148/IJIREEICE.2025.131224
Abstract: Stress is a prevalent psychological concern among students in higher education and has a significant impact on academic performance, mental health, and overall well-being. The present study aimed to examine gender differences in common stress among Postgraduate students. A descriptive cross-sectional research design was adopted for the study. The sample consisted of 150 Postgraduate students, including 75 male and 75 female students, selected randomly from higher education institutions. Data were collected using a self-designed stress questionnaire that assessed common stress levels among students. Descriptive statistics, including mean and standard deviation, along with an independent t-test, were used to analyze the data.
The results revealed that female students experienced higher levels of common stress compared to male students. The mean score for common stress among male students was 24.67 (SD = 6.04), whereas female students recorded a higher mean score of 28.78 (SD = 5.22). The calculated t-value of 2.89 was found to be statistically significant at the 0.05 level, indicating a significant gender difference in common stress levels. These findings suggest that female students are more vulnerable to stress, possibly due to greater academic pressure, emotional sensitivity, and socio-cultural expectations. The study highlights the need for gender-sensitive stress management strategies and counseling interventions in higher education institutions to promote students’ mental health and academic success.
Keywords: Gender, Perceived Stress, Postgraduate Students, Marathwada, Mental Health
The results revealed that female students experienced higher levels of common stress compared to male students. The mean score for common stress among male students was 24.67 (SD = 6.04), whereas female students recorded a higher mean score of 28.78 (SD = 5.22). The calculated t-value of 2.89 was found to be statistically significant at the 0.05 level, indicating a significant gender difference in common stress levels. These findings suggest that female students are more vulnerable to stress, possibly due to greater academic pressure, emotional sensitivity, and socio-cultural expectations. The study highlights the need for gender-sensitive stress management strategies and counseling interventions in higher education institutions to promote students’ mental health and academic success.
Keywords: Gender, Perceived Stress, Postgraduate Students, Marathwada, Mental Health
Abstract
A Comparative Study of Psychological Problems with Respect to Depression Between Swimmers and Non-Swimmers in the Age Group of 24–30 Years
Dr. Pushpender Singh
DOI: 10.17148/IJIREEICE.2025.131225
Abstract: The present study aimed to compare psychological problems with respect to depression between swimmers and non-swimmers aged 24–30 years. A total of 185 participants were selected for the study, comprising 69 swimmers and 116 non-swimmers. Depression levels were assessed using a standardized psychological depression scale. Descriptive statistics, including mean scores and standard deviations, were computed, and an independent samples t-test was applied to determine group differences. The results revealed that non-swimmers (M = 18.67, SD = 3.54) exhibited significantly higher depression levels than swimmers (M = 16.32, SD = 3.12). The obtained t-value (t = 3.25) was statistically significant at the 0.05 level, indicating a meaningful difference between the two groups. The findings suggest that regular participation in swimming may play a protective role in reducing depressive symptoms. The study highlights the importance of physical activity, particularly swimming, as a potential intervention for improving mental health among young adults.
Keywords: Depression, Psychological Problems, Swimmers, Non-Swimmers, Physical Activity
Keywords: Depression, Psychological Problems, Swimmers, Non-Swimmers, Physical Activity
Abstract
AI and Data Engineering Frameworks for Smart Government Decision Making
Bhasker Katta
DOI: 10.17148/IJIREEICE.2025.131226
Abstract: The demand for real-time evidence-based policy decision-making and management is driving governments to enhance their analytical capabilities through AI. However, actual AI uptake in the public sector remains limited. Current government ML models and innovations rely primarily on internal IT infrastructure and cloud-based platforms. This research outlines the AI and data engineering frameworks required to execute a future-ready government analytical agenda for smart decision-making. The analysis identifies three types of data pipeline architectures and the foundations of an integrated data ecosystem tailored to the specific characteristics of public sector data. These are combined with the essential requirements for data quality and governance, and different AI deployment models for PLG predictive and prescriptive analytics applications. Finally, seven use areas for healthcare, social services, urban planning, transport, crime and disaster response are examined. The resulting design delivers a comprehensive, objective, and evidence-based perspective on AI frameworks for real-time smart government. Despite practical implementation challenges, the recommendations align both with state-of- the-art AI developments and with the ML and AI strategies of important public and commercial institutions. The rapid development of analytics and AI technologies, combined with the capacity to harness the massive amount of data generated by public sector operations, unquestionably represents a significant opportunity for governments to transform their traditional ways of working. More than ever, there is a strong demand for real-time, objective, and evidence-based analysis to support the challenging decision-making environments created by the COVID-19 pandemic and other current global crises. However, in practice, only a limited number of governments have adopted a formal AI framework. Most AI innovations in the public sector remain isolated. Advanced ML models, especially deep-learning techniques, are mainly developed for specific applications, while broader ML initiatives are becoming more common, primarily driven by cloud-based platforms. At the same time, private organizations are increasingly offering prescriptive or predictive services to governments, filling in the gaps in their analytics capabilities.
Keywords: AI for Smart Government, Public Sector Analytics, Evidence-Based Policy Making, Real-Time Government Decision Support, Government Data Engineering Frameworks, Public Sector Data Pipelines, Integrated Government Data Ecosystems, Data Quality and Governance, Machine Learning in Government, Predictive and Prescriptive Analytics, Cloud- Based Government AI, Public Sector AI Adoption, Digital Government Transformation, AI Deployment Models, Health and Social Services Analytics, Urban Planning Intelligence, Smart Transport Analytics, Crime and Disaster Response Systems, Government AI Strategy, Future-Ready Public Sector Analytics.
Keywords: AI for Smart Government, Public Sector Analytics, Evidence-Based Policy Making, Real-Time Government Decision Support, Government Data Engineering Frameworks, Public Sector Data Pipelines, Integrated Government Data Ecosystems, Data Quality and Governance, Machine Learning in Government, Predictive and Prescriptive Analytics, Cloud- Based Government AI, Public Sector AI Adoption, Digital Government Transformation, AI Deployment Models, Health and Social Services Analytics, Urban Planning Intelligence, Smart Transport Analytics, Crime and Disaster Response Systems, Government AI Strategy, Future-Ready Public Sector Analytics.
Abstract
Cloud Computing and AI for Intelligent Transportation Safety Systems
Dasari Vinay
DOI: 10.17148/IJIREEICE.2025.131227
Abstract: Cloud Computing and Artificial Intelligence will enable Intelligent Transportation Safety Systems (ITSS) that ensure a reliable low accident rate in road traffic. ITSS are considered an extension of Intelligent Transportation Systems connected to Cloud Computing with integrated Artificial Intelligence and focus on traffic safety. ITSS detect critical situations, predict dangerous conditions, and inform vehicle and driver assistance systems in real time to avoid accidents, control signal flows, and manage incidents. Today’s configuration of CT and AI can only solve special tasks, for instance, the level of cloud service and the bandwidth of data exchange. However, both technologies can work on a multidisciplinary basis, increase the robustness of work, manage data from various sources, analyze them dynamically and, thus, bring traffic safety to a new level.
The paper applies the original methodology developed for expanding the possible use of Cloud Computing and AI in solving applied problems. Cloud Computing allows integration of data from multiple sources in real time. AI based on interconnection and dynamic development between models of risk, collision, smart camera detection of critical mode conditions, IP-traffic incident detection and routing for traffic management on internal cloud and on-device level of connected vehicles makes it possible to predict modes of accidents with high probability and with a certain reaction time. Although the current architecture of Cloud Computing for ITSS has its limitations, it has enough potential to integrate a sufficiently rich set of modern safety-related solutions.
Keywords: Intelligent Transportation Safety Systems, Cloud Computing For Traffic Safety, AI-Enabled Traffic Management, Real- Time Accident Prediction, Connected Vehicle Safety Systems, Cloud-Based Traffic Data Integration, AI Risk And Collision Models, Smart Camera Traffic Detection, Incident Detection And Management, Low-Latency Safety Analytics, Vehicle-To-Cloud Communication, Predictive Road Safety Analytics, Multisource Traffic Data Fusion, Dynamic Traffic Risk Assessment, AI-Assisted Driver Support, Signal Flow Optimization, IP-Traffic Monitoring, Robust Transportation Safety Architectures, Cloud–Edge ITS Integration, Next-Generation Road Safety Systems.
The paper applies the original methodology developed for expanding the possible use of Cloud Computing and AI in solving applied problems. Cloud Computing allows integration of data from multiple sources in real time. AI based on interconnection and dynamic development between models of risk, collision, smart camera detection of critical mode conditions, IP-traffic incident detection and routing for traffic management on internal cloud and on-device level of connected vehicles makes it possible to predict modes of accidents with high probability and with a certain reaction time. Although the current architecture of Cloud Computing for ITSS has its limitations, it has enough potential to integrate a sufficiently rich set of modern safety-related solutions.
Keywords: Intelligent Transportation Safety Systems, Cloud Computing For Traffic Safety, AI-Enabled Traffic Management, Real- Time Accident Prediction, Connected Vehicle Safety Systems, Cloud-Based Traffic Data Integration, AI Risk And Collision Models, Smart Camera Traffic Detection, Incident Detection And Management, Low-Latency Safety Analytics, Vehicle-To-Cloud Communication, Predictive Road Safety Analytics, Multisource Traffic Data Fusion, Dynamic Traffic Risk Assessment, AI-Assisted Driver Support, Signal Flow Optimization, IP-Traffic Monitoring, Robust Transportation Safety Architectures, Cloud–Edge ITS Integration, Next-Generation Road Safety Systems.