International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control EngineeringA monthly Peer-reviewed & Refereed journal
IJIREEICE meets the suggestive parameters outlined in the latest University Grants Commission (UGC) for peer-reviewed journals, ensuring high standards of research integrity, publication ethics, and academic excellence.
Mr. Pranay R. Dive, Mr. Abhay B. Rathod, Ms. Pratiksha G. Gayane, Mr. Vishal V. Chavhan, Mr. Sahil J. Tiple, Mr. Om S. Gedam, Mr. Shikshesh A. Kulsange, Mr. Nishant M. Gujar
Sustainability through Inclusion and Innovation: The Role of Diversity, Equity,Team Cohesion, and Creativity
Srivardhani.T and Dr.Rajini.G*
DOI: 10.17148/IJIREEICE.2025.13501
Abstract: This study investigates the implementation and consequences of Diversity, Equity, and Inclusion (DEI) in HR processes in an Indian manufacturing company. In the context of evolving corporate culture, DEI becomes pivotal in making workplaces inclusive, innovative, and sustainable. This study intends to analyse the contribution of DEI programs towards prominent organizational factors such as team cohesion, innovation and creativity and sustainability in the long term. A standardized survey questionnaire was developed and inputs were obtained from employees of different departments. The findings strive to fill the gap between DEI theory and practice in an Indian manufacturing industry.
Mr. Pranay R. Dive, Mr. Abhay B. Rathod, Ms. Pratiksha G. Gayane, Mr. Vishal V. Chavhan, Mr. Sahil J. Tiple, Mr. Om S. Gedam, Mr. Shikshesh A. Kulsange, Mr. Nishant M. Gujar
DOI: 10.17148/IJIREEICE.2025.13502
Abstract: Public Announcement drones have gained significant attention in recent years due to their wide range of applications in various fields including security, agriculture, disaster management etc. The Public Announcement (PA) Project is an innovative initiative designed to use drone technology to broadcast public messages, alerts, and announcements in various urban and rural settings. This project explores the development of an Aerial Public Announcement Drone (APAD) designed to deliver live announcements in real-time using a walkie-talkie communication system. The project aims to create a reliable and cost-effective UAV-based solution for emergency communication, capable of broadcasting critical information to large crowds or remote areas during crises such as natural disasters, evacuations, or large public events. The Public Announcement (PA) Drone Project use of drones equipped with advanced audio systems to enhance public communication, including outdoor events, urban areas, and emergency situations. The Aerial Public Announcement Drone (APAD) integrates unmanned aerial vehicle (UAV) technology with real-time voice broadcasting capabilities, providing a mobile and efficient public address system. This drone system is designed to broadcast live messages across large areas, particularly where traditional infrastructure is lacking or ineffective. APAD finds application in emergency management, public safety, large-scale events, and rural outreach. The APAD system comprises a lightweight quadcopter drone equipped with a high-decibel loudspeaker, a real-time wireless communication module, an onboard flight controller, and a ground control for flight and audio management. The design emphasizes modularity, portability, and efficiency while maintaining a cost-effective architecture suitable for deployment in both urban and remote environments. The APAD system aims to enhance situational awareness, streamline information dissemination, and improve public engagement in critical and time-sensitive situations. The findings confirm that the APAD is an effective tool for real-time public announcements during emergencies. The use of a walkie-talkie-based communication system provides a cost-effective and flexible means of broadcasting critical information, enhancing the overall response during urgent situations. This project highlights the potential of UAVs to improve public safety and emergency communication efforts by integrating live communication capabilities in areas where traditional methods are limited.
Diagnosing chronic kidney disease using machine learning algorithms
R.Lavanya,V.Suvarna,S.Ajeez,A.Suprathika
DOI: 10.17148/IJIREEICE.2025.13503
Abstract: To its slower progression and less obvious onset, Chronic Kidney Disease can easily become a challenging health issue to recognize directly. issue from a global perspective with associated high disease morbidity and mortality rates and hence induces other diseases as well. However, investigations are conducted at different stages related to the stage of CKD, a majority of do not even recognize that they have the disease. Once CKD has been diagnosed at an early stage, timely treatment can be offered to manage the progression of this disease. In such situations, machine learning applications may help achieve the speed and accuracy needed for diagnosis; hence, the study, i.e., "A machine learning methodology for diagnosing chronic kidney disease," has been originated. CKD data covering instances with A very large collection of missing data was obtained From UC Irvine's Machine Learning Repository, also known as UCI. This is how the data came to be then subjected to KNN imputation to fill missing values. K-nearest neighbors imputation works by selecting for each incomplete sample some To perform the imputation, it would require samples that are most analogous to the observations done before the actual procedure. Missing data situations are commonplace Some measurements of the patients remain unrecorded under some conditions in the real-life medical settings. After the instances when the patients missed measurements, the physician prescribes the medication and returns the patient for another measurement. suitable imputation processes were completed on the incomplete data set, modeling was done with The six machine learning methods include: logistic regression, random forest, support vector machine, k-nearest neighbor, Naive Bayes classifier, and feedforward neural network. Overall, random forest was able to achieve the highest accuracy across a range of machine learning models. Learning from the errors in models developed thus requires an emphasis on designing an integrated model that can incorporate logistic regression and random forest through Perceptron, optimal in speed for this. Therefore, thereby we speculated that this could be a solution that can be generalized to other more complex clinical data with diseases.
Keywords: Logistic Regression, Random Forests, Support Vector Machines, k-nearest neighbors, and Naive Bayes in addition to feed forward neural networks.
Garlic Powder Manufacturing and Marketing in Bangalore: A Feasibility Study for the Bakery and Cafe Industry
Saatwik kumar G. V, Meghana K, Ruchitha D. N, Jadhav Subham Lala,Reema Sheerin S, Kavin Kumar P T, Yuktha T N, Nischal Godwin Sylvester
DOI: 10.17148/IJIREEICE.2025.13504
Abstract: This research paper examines the garlic powder manufacturing industry in India, focusing on market demand and consumer preferences in Bengaluru. Through quantitative surveys of 41 local businesses, including restaurants and bakeries, and secondary data analysis, the study reveals a robust demand for high-quality, organic garlic powder, driven by its convenience, shelf life, and culinary versatility. Key findings indicate a preference for organic products, competitive pricing within ₹200-₹500 per kg, and openness to locally sourced brands. The Indian garlic powder market is projected to grow at a CAGR of 5.8% over the next five years, supported by increasing processed food consumption. Recommendations include enhancing product quality, optimizing pricing, and improving packaging to strengthen market positioning. This study offers actionable insights for manufacturers aiming to capitalize on the expanding garlic powder market.
Parth N. Shahagadkar, Ankit V. Wagh, Swapnil A. Sanap
DOI: 10.17148/IJIREEICE.2025.13505
Abstract: Visually impaired individuals face significant challenges in navigating their surroundings safely and independently. Traditional mobility aids such as canes provide limited assistance and lack real-time hazard detection. This paper presents an indoor navigation system for visually impaired and designed to enhance mobility, safety, and emergency response. The system integrates two ultrasonic sensors—one for depth detection and another for obstacle avoidance. An LM393 Comparator IC sensor detects water on the road, warning users of wet surfaces. The device also includes a GPS module for real-time location tracking and a GSM module to send emergency SMS alerts. A panic button allows users to instantly send their location to predefined contacts in distress situations. The system is built around an Arduino Nano, ensuring efficient processing and communication. This assistive technology enhances the independence of visually impaired individuals by offering real-time alerts and automated emergency assistance. This innovation contributes to improving accessibility, safety, and overall quality of life for visually impaired users.
The Evolution of Blockchain: Transforming Industries Through Decentralization
Lekkala Vyshnavi
DOI: 10.17148/IJIREEICE.2025.13506
Abstract: Blockchain technology now stands as a revolutionary power that changes multiple businesses and breaks down established centralized operations. The following research studies blockchain development as it transforms different business sectors through decentralized systems mechanisms. The analysis evaluates the distinct properties of blockchain technology, including distributed ledger systems and immutable design, as well as peer-to-peer architecture that resolves recurring challenges within data protection, privacy, and security domains. Financial institutions are set up to adopt new ways of doing business through blockchain networks, which provide superior models for transaction processes, asset control systems, and regulatory compliance functions. The paper explores extended industry transformations created by blockchain technology, which goes beyond finance into alternate sectors, including energy systems, as well as internet decentralization through Web3. The paper uses extensive research from academic publications and industry documents to clarify blockchain development alongside its substantial transformations for business operations and societal delivery.
Synergizing Next-Generation Technologies: A Holistic Review of AI, IoT Systems, Industrial Innovation, and Blockchain Transformation for Future-Ready Ecosystems
Aditya Anand
DOI: 10.17148/IJIREEICE.2025.13507
Abstract: Current technology combines artificial intelligence with smart systems and industrial innovation and digital transformation elements to create the necessary environment for future enterprises. This combined convergence functions beyond simple technology overlap to create a thorough relationship which drives businesses toward new heights of industrial performance and adaptability and innovation capacities. The review examines multiple aspects of this technological union by illustrating fundamental concepts and main deployment areas and assessing how the technologies transform different industries. An analysis of contemporary technology practices and future prospective predictions will deliver an entire picture about how to correctly implement these systems to build forward-thinking resilient frameworks. AI combined with machine learning allows industrial operations to study extensive data collections which enhances production efficiency and controls both structural systems automatically. Through artificial intelligence and smart technology production systems improve manufacturing excellence along with sustainability of industrial activities. The industrial sector now experiences a complete transformation because of artificial intelligence systems combined with machine learning capabilities in traditional business operations. Systematic research along with ongoing investigation stands essential for integrating artificial intelligence into different computer application domains because of the complexities AI-powered blockchain systems encounter. The fourth industrial revolution stems mainly from how AI and ML incorporate with emerging innovations. The deployment of smart systems using AI and Internet of Things advancements has triggered extensive changes to environments which become linked and smart domains. Systems that use real-time gathered data alongside sophisticated algorithms help organizations make improved distribution choices and better decisions at the same time as allowing flexible and adaptive infrastructure installation.. The analytical strength of smart systems includes an ability to develop over time since these systems use data analytics and machine learning to improve their operational capabilities. This investigation traces smart systems' impact on transforming urban territories and industrial activities and healthcare delivery services as well as their capability to manage intricate issues and better human existence. Through the combination of machines and machine learning, robots have transfigured their capabilities from manual work to autonomous performance which reveals a new approach to machine data processing.
SMART GLOVE FOR SIGN LANGUAGE TRANSLATION USING IOT
Mrs. DIVYASHREE H S, ARUN KUMAR K M, DARSHAN D B, DARSHAN K B, GIRISH GOWDA Y A
DOI: 10.17148/IJIREEICE.2025.13508
Abstract: The design of a smart glove for deaf and dumb individuals using IoT technology aims to facilitate seamless communication by converting hand gestures into text and speech. This project integrates advanced sensors such as flex sensors to detect finger movements and accelerometers and gyroscopes to track hand orientation. The glove communicates wirelessly with paired devices using WI-FI modules, transmitting processed data to a mobile application. This app displays the translated text and provides text-to-speech functionality. Its ergonomic design ensures comfort and durability, with adjustable features to fit various hand sizes. Usability testing with real users ensures the glove meets user needs and incorporates feedback for continuous improvement. This innovative IoT-enabled smart glove enhances communication for deaf and dumb individuals.
Mrs. Noor Ayesha, Preetham K N, Mohammad Sufiyan Khan
DOI: 10.17148/IJIREEICE.2025.13509
Abstract: In modern precision agriculture, early detection of fruit diseases is crucial to preventing postharvest losses and maintaining quality yields. Traditional detection methods relying on manual inspection are inefficient and prone to error. We present a real-time fruit disease identification approach that leverages the YOLO (You Only Look Once) object detection architecture as its foundational framework., enhanced with preprocessing techniques like Finite Impulse Response (FIR) filtering for image quality improvement. YOLO’s convolutional neural network (CNN) architecture enables multi-scale feature extraction, allowing effective identification of diseased regions without compromising image resolution. We present the complete workflow from data acquisition, preprocessing, and training to evaluation and deployment. Experimental results demonstrate the model’s effectiveness with high accuracy, precision, and recall, suggesting strong potential for real-time application in agricultural environments.
Dr. Madhan Kumar G S, Dr. Mahadev Prasad Y N, Ms. Kusuma S, Ms. Prakruthi K P, Ms. Ranjitha N, Ms. Sindhu K
DOI: 10.17148/IJIREEICE.2025.13510
Abstract: This paper presents an intelligent and user-friendly android-based application for the automatic detection of Alzheimer's disease and brain tumors. Neurological disorders like these pose significant diagnostic challenges due to their complexity and the critical need for early detection. Our project employs a hybrid approach, combining image processing and machine learning techniques, to provide rapid, preliminary diagnostic insights to both patients and medical professionals. The application features two primary modules: Brain Tumor Detection and Alzheimer's Prediction. The Brain Tumor module processes uploaded brain X-ray images, applying pre-processing steps like grayscale conversion, thresholding, and binarization. Feature extraction is then performed, followed by the use of a U-Net deep learning model to segment and classify the tumor, determining if the image indicates a normal state or a specific tumor type. The Alzheimer’s module operates on tabular health and lifestyle data, where users input structured features such as age, gender, ethnicity, education level, BMI, smoking and alcohol consumption habits, physical activity, and diet quality. These inputs undergo pre-processing through normalization and categorical encoding. The processed data is then analyzed using machine learning algorithms like Random Forest and Support Vector Machine to predict the likelihood of Alzheimer’s disease. By integrating both image-based and feature-based diagnostic methods into a single platform, this system significantly enhances the scope and accuracy of early detection. The dual-model architecture not only supports medical assessments but also empowers users with accessible health screening tools. Future enhancements are envisioned to include MRI integration, cloud deployment, and direct communication with healthcare providers. This intelligent application stands as a potential decision-support system in the domain of preventive neurological healthcare.
C K HARSHIL GOWDA, BHARATH S, UJWAL A N, BHARATH KUMAR M, Dr. N.M. MAHESH GOWDA
DOI: 10.17148/IJIREEICE.2025.13511
Abstract: The stock market is a dynamic and complex system influenced by various factors such as financial indicators, market sentiment, political events, and economic conditions. Predicting stock prices is a challenging task due to the non- linear and volatile nature of the market. This project aims to analyze historical stock market data and predict future prices using deep learning techniques, particularly Long Short-Term Memory (LSTM) networks. By integrating historical price trends and sentiment analysis of financial news, we enhance the accuracy of predictions. The dataset includes 20 years of stock prices and recent sentiment scores from news headlines. The LSTM model is trained on this combined dataset to learn temporal patterns and market behavior. A user-friendly web interface developed using Flask allows users to input a stock ticker and receive the next day’s predicted price. This project demonstrates the potential of AI in financial forecasting and provides a tool for investors to make data-driven decisions.
An Android Based E-Commerce Platform For Empowering Farmers In Agricultural Marketing
Akshath M J, Meghana N R, Shreemurty Kashinath Bellagi, Sagar J S, Usha Rani R
DOI: 10.17148/IJIREEICE.2025.13512
Abstract: This study presents the design and development of a mobile e-commerce platform for the agricultural sector, aimed at empowering farmers by providing direct access to markets. The application supports secure user registration and authentication, enabling both farmers and buyers to create accounts using various methods, including OTP verification. Farmers can list products by uploading images, descriptions, and prices through a user-friendly interface, while buyers can conveniently browse and order items. Additionally, a dedicated module for purchasing pesticides and fertilizers is integrated, offering product information and pricing. The platform encourages digital participation in agriculture, reducing dependency on intermediaries and promoting fair trade practices.
AI DRIVEN SOLUTION FOR ETHICAL TEXT AND IMAGE MODERATION
Dr. Akshath M J, Deekshitha C, Deekshitha M, Deepika T R, Deepthi K
DOI: 10.17148/IJIREEICE.2025.13513
Abstract: This project proposes an AI-powered solution for moderating unethical and harmful text and image content on digital platforms. With the surge in user-generated content, challenges like hate speech, explicit visuals, and cyberbullying require real-time, accurate, and ethical moderation. The system utilizes Google Cloud’s Natural Language API and image recognition tools to automatically detect, classify, and flag inappropriate content. It combines advanced NLP and computer vision techniques to support multilingual input and context-aware analysis. The integrated administrator dashboard enhances review efficiency, while Explainable AI ensures transparency. This framework aims to create safer online spaces through scalable and ethical content governance.
Review On: A Comprehensive Fashion Recommendation System
Afjal Siddique, Aman K. Kannaujia, Gufran Khan, Rohit Kumar
DOI: 10.17148/IJIREEICE.2025.13514
Abstract: The rapidly evolving fashion industry demands intelligent and personalized recommendation systems to enhance user experiences and promote e-commerce growth. This paper proposes an AI-Based Fashion Recommendation System that utilizes Machine Learning (ML) and Deep Learning (DL) techniques to deliver customized clothing and accessory suggestions. The system is composed of three modules: Admin, User, and Retailer. Through Convolutional Neural Networks (CNNs), clustering algorithms, and behavioral analytics, the platform enhances fashion product discovery, addresses cold start problems, and improves customer engagement.
Abstract: This paper presents a gesture-controlled music player system that interprets real-time hand gestures to control media functions such as play, pause, next/previous track, and volume adjustment. The project aims to deliver a touchless user experience, offering intuitive control of digital media via simple hand movements detected through a webcam. The system utilises computer vision technologies, including Opencv, MediaPipe, and Python’s gesture recognition algorithms. Designed with accessibility and hygiene in mind, this music player is particularly relevant in environments where hands-free interaction is preferred or necessary. Testing showed gesture accuracy of over 90% under good lighting conditions, confirming the system's practical usability. Future enhancements will focus on integrating machine learning for personalised gesture mapping and expanding crossplatform support.
Abstract: This paper presents a comprehensive overview of the development and design of an AIpowered calculator, inspired by interactive platforms such as iPad Math Notes. The project utilizes AI, particularly the Flash Gemini Generative API, to interpret, solve, and explain mathematical expressions. The frontend, built with TypeScript, TailwindCSS, and React, integrates seamlessly with a Python backend, facilitating real-time computational assistance. The solution is rendered via MathJax, ensuring high-quality mathematical notation, making the tool ideal for educational and professional applications.
Abstract: This document presents Sentiment Analysis, an AI-powered sentiment analysis system that leverages advanced large language models (LLMs) via the LangChain framework. The primary objective of this project is to analyse and classify textual input into sentiment categories such as Positive, Neutral, and Negative, with potential applications in content moderation, user feedback analysis, and social media monitoring. The system is built using a modular Python backend, integrated with LangChain to streamline prompt engineering and model interaction. By utilizing APIs from state-of-the-art language models (e.g., Gemini or GPT), SENTIMENT ANALYSIS delivers high-accuracy, context- aware sentiment classification. This paper describes the architectural components, implementation methodology, and output results of the SENTIMENT ANALYSIS framework. The proposed approach demonstrates the effectiveness of combining LLMs with LangChain’s orchestration layer for building adaptable, intelligent sentiment analysis tools. Sentiment Analysis is built around the idea of creating a communication platform that values thoughtful expression, emotional context, and user control. One of the core features we’re working on is an intelligent flow for handling user posts, called Echoes. When a user writes an Echo, it goes through a validation process using Zod both on the frontend and at the Cloudflare middleware layer to ensure the data is clean and safe. Instead of immediately storing the Echo in the database, it’s first passed through backend functions that handle specific logic as needed. The Echo is then temporarily saved with a private flag and sent to an Azure-based API powered by FastAPI, where the data is validated again using Pydantic. From there, the Echo enters a custom sentiment analysis pipeline built using LangChain. This model, trained specifically for the kind of conversations expected on Sentiment Analysis, classifies the Echo as positive, neutral, or negative. If it’s found to be positive, the system updates the Echo in the database, changes its visibility from private to public, and reflects the change on the user interface in real time. For Echoes that come back as neutral or negative, the system holds them in private, generates alternative phrasings using the LangChain suggestion engine, and saves those suggestions in the database for the user to review. The user can choose to rephrase and publish, or keep it as is. Throughout this process, LangMemo keeps track of context to ensure a smooth and consistent experience. This entire flow helps users communicate more thoughtfully, while giving them tools to refine their messages and maintain control over what they share. It’s a step toward building a platform where expression feels safe, supported, and emotionally aware.
Keywords: Sentiment Analysis, LangChain, Large Language Models (LLMs), Text Classification, PromptEngineering, Artificial Intelligence
Energy-Aware Policy Optimization with PPO for Edge AI Applications
Darshit Sandeep Raut, Sanika Rajan Shete, Anant Manish Singh*
DOI: 10.17148/IJIREEICE.2025.13519
Abstract: The increasing deployment of AI applications at the edge has created an urgent need for intelligent energy management systems that can dynamically optimize power consumption while maintaining acceptable performance levels. Traditional approaches often treat energy consumption as a secondary concern, leading to suboptimal resource utilization and reduced operational sustainability. This research introduces a comprehensive energy-aware policy optimization framework utilizing Proximal Policy Optimization (PPO) for edge artificial intelligence applications, addressing the critical challenge of balancing computational performance with energy efficiency in resource-constrained environments. Our proposed framework integrates real-time energy monitoring, adaptive policy learning and intelligent resource allocation to create a holistic solution for edge AI deployment. The methodology employs a multi-objective optimization approach that considers both immediate energy costs and long-term performance implications, utilizing advanced reinforcement learning techniques to learn optimal policies from environmental feedback. Through extensive experimentation on real-world datasets including environmental sensor networks and mobile edge computing scenarios, we demonstrate significant improvements in energy efficiency while maintaining or enhancing computational performance. The results show up to 34.6% reduction in energy consumption compared to baseline methods with improved stability and adaptability across diverse operational conditions. This research contributes to the growing field of sustainable AI by providing practical solutions for energy-conscious edge computing deployment, particularly relevant for IoT applications, autonomous systems and smart city infrastructure where energy efficiency directly impacts operational viability and environmental sustainability.
Keywords: Edge Computing, Energy Optimization, Proximal Policy Optimization, Reinforcement Learning, Sustainable AI, Resource Management, IoT Applications, Power Efficiency
DESIGN AND CONSTRUCTION OF A SMART DC-DC CHARGE CONTROLLER FOR SOLAR CHARGE STATIONS
Onyeyili T.I., Okafor C.S., Azubogu A.C.O., Anyanwu Nnamdi S.
DOI: 10.17148/IJIREEICE.2025.13520
Abstract: Efficient solar energy conversion necessitates advanced charge controllers. This paper presents the design and construction of a smart DC-DC charge controller for solar charge stations. The controller, employing Maximum Power Point Tracking (MPPT), efficiently charges 12V-48V batteries up to 20A, maximizing power extraction from solar panels. This paper details the design and experimental performance validation of a smart solar charge controller based on the Perturb and Observe (P&O) MPPT algorithm for charging 12V to 48V batteries with a maximum charging current of 20A.
Keywords: Solar Charge Controller, DC-DC Converter, MPPT (Maximum Power Point Tracking), Battery Charging.