← Back to Archives
VOLUME 14, ISSUE 6, JUNE 2026
Publishing in progress.
GPS GUIDED TRASH COLLECTION ROBOT WITH AUTOMATIC SEGREGATION
Ms. Minchana B M, Ms. Divyashree R H, Ms. Supriya A P, Ms. Prabhavathi K, Mr. Vishwas P Gowda
AUTOMATIC TARIFF CALCULATION WITH WIRELESS ENERGY METER
Dr. Dilip Kumar Patel, Akhilesh Yadav, Ajay Sharma, Nitin Singh
Adaptive Terahertz Beam Steering for Enhanced Deep Space Communication Links
Mohammad Saara Banu and Maddala Vijayalakshmi
Dynamic IRS Selection for High-Speed Mobility in 6G Networks
Adla Deepthi, Dr.Rajkumar L.Biradar
A Survey on Recent Research Trends Towards Near field Body Coupled Communication
Changappa M K, Darshan A R, Hruthwik S, Ranganath B
Enhancing the Beam Alignment in 6G Networks using Deep Learning
Nakka Loktheja, Ambidi Naveena
SIMULATION AND COMPARATIVE ANALYSIS OF HYBRID RENEWABLE ENERGY SYSTEM FOR ENHANCED ENERGY EFFICIENCY
Ritesh Yadav, N.K.Rai, Shrey Srivastava, Ishika Chauhan, Aditya Vishwakarma
The Art of Asset-Less Compilation: Eliminating Design-to-Code Friction via AI Translation and Advanced React-CSS Interactions
T. Amalraj Victoire, D. Harish
“AIR POLLUTION DETECTION USING IOT ”
Prof. P. K . Digge, Shrushti Sanjay Ghante, Sanchita Rajesh Devkate, Pradnya Pradeep Kumri
Security Threats at the 5G Air Interface and Implications for Telemedicine Reliability: A Literature Survey
G.Sai Keerthi and Vikas Vippalapalli*
Federated Trust-Aware Spectrum Sensing For Cognitive Radio Enabled Internet Of Vehicles In 6G Networks
P. Sreesudha, Sameera Begum
DETECTION OF PHISHING WEBSITE USING MACHINE LEARNING AND FEATURES EXTRACTION
T. Amalraj Victoire, Anusha D
Study on Manufacturing Strategy, Capital Purchase & Production System in an Automobile Industry
Aditi Sharma, Amogh Dwivedi, Arun Kushwaha, Arjun Kushwaha, Deependra Singh Patel, Ashesh Tiwari
Adversarial Attacks on AI System, Vulnerabilities, Threat Models and Defensive Implications
Abdullateef Ajibola Adepoju, Saidu Sunbo Akanji, Rukayya Abdulganiyu Adepoju, Atuma Ochenu Lawrence
6G Wireless Networks: Beyond Terahertz Communications
Salamon S, Mr. P. Logaiyan
Secure File Sharing System using Hybrid Cryptogrphy
Mrs. M. Vasuki, Dr. T. Amalraj Victoire, A. J. Thamizharasu*
"Advanced Control Strategies for Grid-Connected Renewable Energy Systems using Power Electronics and Artificial Intelligence"
DR. R. K. Dhatrak, Prof. Suyog Sangharatna Dhoke, Subodh Sunil Bodhe, Mohammed Shaadurrahim Sheikh, Shivam Rampratap Das, Mayur Anand Pasle, Manish, Devidas Karmenge
Revolutionizing Farming with Machine Learning and IoT: A Smart Agriculture Approach
Sharad Ghule, Prashant Patil, Mtech Student, Depart.Artificial intelligent & Data Science Engineering
IoT-Based Smart Kitchen Inventory and Auto Shopping Assistant
Dr. P. N. Shinde, Prof. N. R. Janavekar, Vaishnavi Katare, Dnyaneshwari Kulkarni, Samruddhi Tilekar
ZooVision: AI-Powered Animal Captioning And Question Answering
Sarah Jose, Goutham Krishna L U
Bin2Win: Incentive-Based Intelligent Dustbin System
Dr. P. N. Shinde, Prof. N. R. Janavekar, Harshada P. Tompe, Bhakti A. Kalmegh, Vrunda B. Pawar
TRANSFORMER FAULT MONITORING AND AUTOMATION USING IoT
Dr. T.R. Sumithira, Dr. M. Mohammadha Hussaini, K. Sowmiya, S. Muralidharan, K. Vinithkannan, M. Nithish
BMS for Wind-Solar Hybrid System with Predictive Control Strategies
Yatiraj Ramesh Vhanmarathe, Vaibhav Hardas Dalvi, Siddharath Hanmant Garud, Gunjan Ajay Bhatgare, Prof. Mrs. P. S. Jadhav
Optimal Placement of SVC and OPF Solution Using Gravitational Search Algorithm Considering Ramp-Rate Constraints
Kaki Manisha Vani
PLC Based Tank Level and Temperature Control System
Dr. D.O. Patil, Dr. S.T. Sanamdikar, Budhibasava Jaka, Paras Jadhav
TEMPERATURE CONTROLLER SYSTEM BASED ON PLCs
Prof. Dr. Sanamdikar S. T., Prof. Dr. Patil D. O., Kokare Sakshee S., Netke Sanskruti M.
AI SaaS Platform Using PERN Stack
Prof. P. A. Patil, Dr P. N. Shinde, Atharva Kharat, Atharva Jagtap, Ajay Rathod
Sequential Growth Model and NeuroAMI Neural Network for Distribution Transformer Load Forecasting
Nemine, B. E., Ahiakwo, C. O., Braide, S. L., Amadi, H. N.
An AI-Powered Resume Evaluation and Applicant Tracking System Optimization Framework Using Machine Learning and Natural Language Processing
KANDULA MANOHAR RAMKRISHNA, Mr. B.N. SRINIVASA GUPTA*
A Web-Based Automated Examination Management System Using Flask Framework and Lightweight Relational Database Architecture
ATYAM SRAVANI, Dr. CHIRAPARAPU SRINIVASARAO*
A Serverless Job Portal Architecture Using Managed Cloud Functions and Automated Continuous-Integration Deployment
V.SAI SURYA PRABHAVATHI, K. LAKSHMI SAI SRI*
A Cloud-Deployed Intelligent Ride Allocation and Dynamic Fare Optimization System Using Python and RESTful Microservices
MULLAPUDI VINEELA SAI, Mr. KARRI LAKSHAMANA REDDY*
A Containerized Microservices Framework for Vendor and Supply Chain Management Using Docker and Kubernetes on AWS EKS
SONGA BHARATHI, PADALA SRINIVASA REDDY*
A Cloud-Native Hospital Appointment Scheduling and Electronic Health Record Management System Leveraging AWS Services and DevOps Automation
KADALI VASANTH, Smt A.N. RAMA MANI*
Abstract
GPS GUIDED TRASH COLLECTION ROBOT WITH AUTOMATIC SEGREGATION
Ms. Minchana B M, Ms. Divyashree R H, Ms. Supriya A P, Ms. Prabhavathi K, Mr. Vishwas P Gowda
DOI: 10.17148/IJIREEICE.2026.14601
Abstract: Rapid urbanization has greatly increased the need for efficient and hygienic municipal solid waste management systems. Traditional waste collection at the door still depends largely on manual work, fixed schedules, and there is no segregation of waste at the source which leads to operational inefficiencies and environmental problems. This paper discusses the design and development of a GPS, guided autonomous trash collection robot with automatic waste segregation. The proposed system makes use of an Arduino Uno microcontroller as the main control unit, coupled with a GPS module and a digital compass to enable accurate navigation outdoors. The robot receives user, defined pickup locations through a Bluetooth, enabled mobile application. Once the robot arrives at the location, it notifies the user and collects the waste which is automatically divided into wet and dry categories by a moisture, based sensing system. Waste segregation is further facilitated by a servo, actuated unit that directs the different wastes into the appropriate compartments. Testing the prototype confirms the excellent navigation of the robot, accurate waste separation, and no, fuss collecting of the garbage by the drone. The proposed system provides an economically viable and scalable alternative to conventional methods of waste management and is very likely to be adopted by both residential and institutional environments.
Keywords: Autonomous robot, Waste management, GPS navigation, Automatic waste segregation, Arduino Uno, Smart cities, Mobile robotics.
Keywords: Autonomous robot, Waste management, GPS navigation, Automatic waste segregation, Arduino Uno, Smart cities, Mobile robotics.
Abstract
AUTOMATIC TARIFF CALCULATION WITH WIRELESS ENERGY METER
Dr. Dilip Kumar Patel, Akhilesh Yadav, Ajay Sharma, Nitin Singh
DOI: 10.17148/IJIREEICE.2026.14602
Abstract: The current energy meter reading system relies on human labor, which has drawbacks such as computation errors, customer absences during billing, and additional costs associated with the billing procedure. The proposed system overcomes these limitations by implementing an automatic wireless energy monitoring and tariff calculation system. The system uses a digital energy meter, PIC16F72 microcontroller, ZigBee wireless communication modules, LCD display, optocoupler, relay circuit, and regulated power supply. The energy meter generates pulses proportional to electrical energy consumption. These pulses are detected using an IR sensor and processed by the microcontroller to calculate consumed energy units. The measured data is transmitted wirelessly to the Electricity Board (EB) section through ZigBee communication. At the EB section, automatic tariff calculation is performed based on predefined electricity rates. The billing information is transmitted back to the consumer side and displayed on the LCD screen. The system also includes an automatic load disconnection feature using a relay in case the electricity bill is not paid within the due date. The proposed system provides accurate billing, reduced manpower, real-time monitoring, improved efficiency, and secure wireless communication. The project can be effectively used in smart homes, industries, and modern automated energy management systems.
Keywords: ZigBee, Energy Meter, Wireless Communication, Automatic Billing, PIC16F72, Smart Metering, Tariff Calculation.
Keywords: ZigBee, Energy Meter, Wireless Communication, Automatic Billing, PIC16F72, Smart Metering, Tariff Calculation.
Abstract
Adaptive Terahertz Beam Steering for Enhanced Deep Space Communication Links
Mohammad Saara Banu and Maddala Vijayalakshmi
DOI: 10.17148/IJIREEICE.2026.14603
Abstract: Adaptive Terahertz (THz) beam steering is a promising and energy efficient technology which has the potential to enhance signal strength, link reliability and signal rate in deep space communication systems where conventional fixed-beam THz links experience severe path loss, atmospheric attenuation and degradation of the pointing error. Under deep space long-distance propagation conditions and a stable high-gain communication link, the problem of maintaining a stable high-gain communication link becomes one of the most critical issues. Conventional fixed-beam THz systems, based on fixed radiation patterns and mechanical steering, have limited pointing error rejection and high misalignment sensitivity, and are infeasible with spacecraft vibration and relative motion. This piece of work proposes a low-complexity adaptive beam steering scheme of the THz deep space communication links where closed-loop beamforming algorithm dynamically adapts the phased array radiation pattern [13], [15] in response to received signal strength feedback with no full channel state information required. The steering issue is formulated as an optimization of beamforming weights in real-time and is solved with the assistance of an adaptive algorithm which is scalable in nature and is less burdensome in terms of processing. To model more realistic deep space conditions, the system model is further developed to include distance-varying SNR degradation and dynamics of the pointing error. The characteristics of the channel capacity [1], [5] and the bit error rate of the adaptive THz beam steering is analyzed as the distance and pointing offset increase and displays the resilience of adaptive THz beam steering against non- adaptive fixed-beam systems. The simulation results, obtained by a full implementation in MATLAB, confirm the proposed strategy leads to the reduction of the sensitivity to pointing errors by a significant margin, high integrity of link maintenance, and spectral efficiency at the deep space propagation conditions. The presented framework offers a viable and scalable next generation deep space communication system solution to future lunar, Mars and interplanetary missions. The simulation results in MATLAB confirm that adaptive THz beam steering is always better than conventional fixed-beam steering in all the measures considered, such as cumulative distribution of channel capacity [1], [5], signal-to-noise ratio over long distance and the ability to tolerate normalized pointing errors. This work provides a solid base on which it is possible to implement intelligent and self-aligning THz communication terminals onboard deep space probes, eliminating the need to rely on bulky mechanical gimbals and allowing autonomous maintenance of links without necessarily ground-based intervention. The further development of this framework can include predictive beam steering with orbital dynamics and channel prediction made by machine learning to achieve even greater efficiency in deep space communication networks.
Keywords: Terahertz communication, deep space, beam steering, adaptive beamforming, phased array, MATLAB simulation, high-data-rate links.
Keywords: Terahertz communication, deep space, beam steering, adaptive beamforming, phased array, MATLAB simulation, high-data-rate links.
Abstract
Dynamic IRS Selection for High-Speed Mobility in 6G Networks
Adla Deepthi, Dr.Rajkumar L.Biradar
DOI: 10.17148/IJIREEICE.2026.14604
Abstract: The Intelligent Reflecting Surfaces (IRS) have become a promising technology in the enhancement of wireless communication by providing programmable control of the propagation environment. Most of currently available IRS-assisted systems are however designed under quasi-static conditions of the channel, which may not be suitable for high-mobility scenarios envisioned in future 6G networks. This paper proposes a Doppler-aware IRS performance evaluation framework for high-mobility scenarios.A channel model which includes Doppler frequency is developed to accurately represent the impact of user mobility on signal propagation. Under high mobility, the proposed scheme is able to effectively recover from the channel degradation caused by Doppler effect.The behavior of the proposed scheme is analyzed based on the large-scale Monte Carlo simulation in the parameters of Bit Error Rate (BER) and achievable rate under different signal-to-noise ratios and user velocities up to 250 km/h. The simulation results have shown that the dynamic IRS scheme performs significantly better than both the conventional static IRS and non-IRS system, with significantly lower BER and higher achievable rates in all the tested conditions. These results indicate the suitability of the proposed approach in ensuring stable and highly efficient communication in high-mobility settings, thus making it an excellent choice in next-generation 6G wireless systems.
Keywords: Intelligent Reflecting Surface (IRS), 6G, High Mobility, Doppler Effect, Dynamic IRS, Phase Adaptation, Bit Error Rate (BER), Achievable Rate.
Keywords: Intelligent Reflecting Surface (IRS), 6G, High Mobility, Doppler Effect, Dynamic IRS, Phase Adaptation, Bit Error Rate (BER), Achievable Rate.
Abstract
A Survey on Recent Research Trends Towards Near field Body Coupled Communication
Changappa M K, Darshan A R, Hruthwik S, Ranganath B
DOI: 10.17148/IJIREEICE.2026.14605
Abstract: Classic IoT-based smart agriculture is built on static sensor networks and a cloud-dominated architecture. While effective, such architectures tend to suffer from high latency, inefficient communication, and heavy power consumption due to continuous data transfer. To address this issue, we introduced Agro-Visconic – an IoT solution based on mobile computing that transfers intelligent data processing from the cloud to the edge of the network using Very Large-Scale Integration (VLSI). Instead of static architecture, our design features an autonomous robot as a mobile gateway. Thanks to AI-based visual processing performed on the FPGA platform through Verilog HDL programming, our solution is now completely cloudindependent and operates reliably even in places with no Internet access.
Abstract
Enhancing the Beam Alignment in 6G Networks using Deep Learning
Nakka Loktheja, Ambidi Naveena
DOI: 10.17148/IJIREEICE.2026.14606
Abstract: The emergence of sixth generation (6G) wireless communication networks requires a huge amount of data rate, low latency, massive connectivity, and high reliability in communication. The use of millimeter-wave (mmWave) communication is seen as one of the key technologies that will satisfy these requirements because of the availability of a wide bandwidth in the mmWave bands. In contrast, however, the path loss for mmWave systems is very high, signals can be blocked by objects and there is a high overhead of beam alignment that makes access to the systems difficult in dynamic wireless environments. Traditional exhaustive beam sweeping techniques are very time consuming and complex since all the beam directions have to be swept prior to establishing communication. To overcome these challenges, a Deep Learning-based Initial Access (DeepIA) framework for fast and reliable beam alignment in AI-powered 6G mmWave Networks is introduced in this paper. The proposed approach is based on a Deep Neural Network (DNN) designed to predict the best beam direction based on Received Signal Strength (RSS) measurements instead of doing a beam sweeping. A novel beam selection method called Sequential Feature Selection (SFS) is used to select the most informative beam combinations to achieve accuracy in prediction while minimizing beam sweeping delay. Moreover, to further improve the system performance under Non-Line-of-Sight (NLoS) channels, a technique called RSS averaging is introduced as an approach to reduce the fluctuation and shadow fading effects of the channel. The simulation results show that the proposed DeepIA framework can accurately predict the beams with a very small number of beam sweeps, which can significantly shorten the delay of initial access and enhance the efficiency of communication. The proposed approach is scalable and intelligent that can be used in the future 6G mmWave communication systems with the use of AI.
Keywords: Deep Learning, 6G, mmWave Communication, Beam Alignment, Beamforming, Initial Access, Deep Neural Network (DNN), Artificial Intelligence (AI)
Keywords: Deep Learning, 6G, mmWave Communication, Beam Alignment, Beamforming, Initial Access, Deep Neural Network (DNN), Artificial Intelligence (AI)
Abstract
SIMULATION AND COMPARATIVE ANALYSIS OF HYBRID RENEWABLE ENERGY SYSTEM FOR ENHANCED ENERGY EFFICIENCY
Ritesh Yadav, N.K.Rai, Shrey Srivastava, Ishika Chauhan, Aditya Vishwakarma
DOI: 10.17148/IJIREEICE.2026.14607
Abstract: Solar energy is a fantastic clean power source, but its weather-dependent nature makes it highly unpredictable. To beat this volatility and keep the power flowing, we designed and tested a hybrid Photovoltaic-Fuel Cell (PV–FC) system in MATLAB/Simulink. A key part of the puzzle was finding the best way to lock onto maximum solar power, so we put three popular Maximum Power Point Tracking (MPPT) techniques to the test under identical conditions: Perturb and Observe (P&O), Incremental Conductance (INC), and Particle Swarm Optimization (PSO). Our simulations show that the intelligent PSO algorithm is the clear winner, reaching an impressive 97.65% tracking efficiency compared to 94.02% for INC and 90.96% for P&O. It responds much faster to environmental shifts, and when the sun dips, the integrated fuel cell seamlessly steps in to smooth out the supply. Ultimately, this hybrid setup proves to be a highly reliable blueprint for standalone grids, rural electrification, and a more resilient green energy infrastructure.
Keywords: Photovoltaic System, Fuel Cell, MPPT, Particle Swarm Optimization, Hybrid Energy System, MATLAB/Simulink.
Keywords: Photovoltaic System, Fuel Cell, MPPT, Particle Swarm Optimization, Hybrid Energy System, MATLAB/Simulink.
Abstract
The Art of Asset-Less Compilation: Eliminating Design-to-Code Friction via AI Translation and Advanced React-CSS Interactions
T. Amalraj Victoire, D. Harish
DOI: 10.17148/IJIREEICE.2026.14608
Abstract: This paper presents a modern framework for front-end web development that tightens the loop between UI/UX design psychology and production-ready React-CSS code. Traditional development workflows often suffer from structural friction and high financial overhead when translating high-fidelity prototypes from design tools to code. This project introduces an optimized pipeline leveraging specialized AI design intelligence to automatically compile advanced user interfaces directly into clean, modular React component architecture without the reliance on premium, cloud-hosted design platforms. In order to showcase the efficiency of this process, a premium web application was designed, specifically with emphasis on increasing usability by way of cognitive design techniques. The development includes a superior scrolling parallax animation system that is highly efficient in terms of fluid typography and mathematics-based semantic colors. Micro-interactions and stateful animations have been applied throughout the web application in order to keep user cognitive overload at a minimum. This research paper elaborates on the technical aspects of designing such a system, the benefits of the utility-first architecture, and an assessment comparing conventional design to code processes against the modern approach of AI and assetless compilation.
Keywords: Modern Front-End, User Interface/Experience Design, React Design Architecture, CSS-in-JS, AI Development Techniques, Parallax Animations, Component-Based Design, Fluid Typography, Micro- interactions.
Keywords: Modern Front-End, User Interface/Experience Design, React Design Architecture, CSS-in-JS, AI Development Techniques, Parallax Animations, Component-Based Design, Fluid Typography, Micro- interactions.
Abstract
“AIR POLLUTION DETECTION USING IOT ”
Prof. P. K . Digge, Shrushti Sanjay Ghante, Sanchita Rajesh Devkate, Pradnya Pradeep Kumri
DOI: 10.17148/IJIREEICE.2026.14609
Abstract: Air pollution has become a critical global challenge, demanding continuous and accurate monitoring to support timely mitigation efforts. This paper presents an Internet of Things (IoT)–based air pollution detection system designed to provide real-time assessment of key atmospheric pollutants. The proposed framework integrates low-cost environmental sensors with a microcontroller and wireless communication modules to measure parameters such as particulate matter, carbon monoxide, nitrogen dioxide, temperature, and humidity. Sensor data are transmitted to a cloud platform for storage, visualization, and analysis, enabling remote access through a web or mobile interface. Intelligent data processing techniques are employed to identify abnormal pollution patterns and trigger alerts. The system emphasizes energy efficiency, scalability, and ease of deployment, making it suitable for urban, industrial, and residential environments. Experimental results demonstrate reliable performance and show that IoT-based monitoring can deliver high- resolution environmental insights at a significantly lower cost compared to conventional monitoring stations. The study concludes that the proposed solution can support smart-city infrastructures and inform public health and policy decisions through continuous, real-time air quality surveillance.
Keywords: Internet of Things (IoT),Air Quality Monitoring,Pollution Detection, Smart Environment,GasSensor,MQ135 Sensor,MQ2 Sensor,Arduino Uno,NodeMCU,ESP8266,Environmental Monitoring,Real-Time Monitoring,Wireless Sensor Network,Smart City,Temperature and Humidity Sensor,Cloud Computing, Air Pollution Control,Embedded System,Data Analytics,IoT-Based Monitoring System.
Keywords: Internet of Things (IoT),Air Quality Monitoring,Pollution Detection, Smart Environment,GasSensor,MQ135 Sensor,MQ2 Sensor,Arduino Uno,NodeMCU,ESP8266,Environmental Monitoring,Real-Time Monitoring,Wireless Sensor Network,Smart City,Temperature and Humidity Sensor,Cloud Computing, Air Pollution Control,Embedded System,Data Analytics,IoT-Based Monitoring System.
Abstract
Security Threats at the 5G Air Interface and Implications for Telemedicine Reliability: A Literature Survey
G.Sai Keerthi and Vikas Vippalapalli*
DOI: 10.17148/IJIREEICE.2026.14610
Abstract: The rollout of fifth-generation (5G) networks has opened up new possibilities for telemedicine. It allows for real-time remote diagnostics, ongoing patient monitoring, and high-speed clinical communication. However, the open wireless nature of the 5G air interface brings significant security risks. These vulnerabilities can compromise network reliability and threaten the continuity of medical services. This paper reviews existing literature on security threats related to the 5G air interface, focusing on the reliability of telemedicine Quality of Service (QoS). This paper examine documented types of attacks, including physical-layer jamming, adaptive overshadowing, signaling flooding at the NAS and RRC layers, core network GTP exploitation, paging storms, and replay attacks. Thid paper draw on findings from recent peer-reviewed studies about their effects on important radio parameters like Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Signal-to-Interference-plus-Noise Ratio (SINR), latency, jitter, and throughput. This paper also look at machine learning methods for detecting anomalies linked to these attacks as mentioned in the literature. By relating documented attack patterns to established telemedicine QoS standards, this survey shows that the security of the 5G air interface is a matter of patient safety that needs careful consideration in healthcare network design. The paper points out ongoing research challenges and future paths that connect wireless network security with digital health.
Keywords: 5G security; telemedicine; air interface; jamming; signaling flooding; anomaly detection; RSRP; RSRQ; network reliability; healthcare IoT.
Keywords: 5G security; telemedicine; air interface; jamming; signaling flooding; anomaly detection; RSRP; RSRQ; network reliability; healthcare IoT.
Abstract
Federated Trust-Aware Spectrum Sensing For Cognitive Radio Enabled Internet Of Vehicles In 6G Networks
P. Sreesudha, Sameera Begum
DOI: 10.17148/IJIREEICE.2026.14611
Abstract: The rapid evolution of sixth-generation (6G) wireless networks has accelerated the development of intelligent communications systems capable of supporting ultra-reliable, low-latency applications.Cognitive Radio-Enabled Internet of Vehicles (CR-IoV) has emerged as a promising solution for efficient spectrum utilization in highly dynamic automotive environment. However, conventional centralized spectrum sensing techniques suffer from high communication overhead, privacy issues, and scalability limitations when deployed in large-scale vehicular networks. To address these challenges, this paper proposes a Federated Trust-Aware Spectrum Sensing framework for CR-IoV networks operating in 6G environments. The proposed approach integrates Federated Learning (FL) with a trust evaluation mechanism to enable decentralized model training while preserving user privacy and improving detection reliabilit. Convolutional Neural Networks (CNN) are used for local spectrum occupancy detection, while support vector machines (SVM) are used for intelligent road unit (RSU) selection and resource allocation. Trust-based aggregation is integrated to mitigate the impact of untrusted and malicious nodes during the global model updating process. MATLAB simulations are performed under different signal-to-noise ratio (SNR) conditions to evaluate the performance of the proposed framework. Simulation results demonstrate significant improvements in detection probability, detection accuracy, throughput, and spectrum utilization compared to centralized and conventional federated learning approaches. The proposed framework provides a scalable, secure and efficient solution for future 6G-enabled intelligent vehicle communication systems.
Keywords: Cognitive Radio, Internet of Vehicles, Federated Learning, Trust Management, Spectrum Sensing, Convolutional Neural Network, Support Vector Machine, 6G Networks.
Keywords: Cognitive Radio, Internet of Vehicles, Federated Learning, Trust Management, Spectrum Sensing, Convolutional Neural Network, Support Vector Machine, 6G Networks.
Abstract
DETECTION OF PHISHING WEBSITE USING MACHINE LEARNING AND FEATURES EXTRACTION
T. Amalraj Victoire, Anusha D
DOI: 10.17148/IJIREEICE.2026.14612
Abstract: Phishing attacks represent a rapidly expanding threat in cyberspace that causes significant financial losses to web users and companies on an annual basis. Any sensitive data acquired from the customers by using different social engineering tactics is considered unauthorized, and any kind of website, pop-ups, instant message, emails, and other communication tools can be employed for recognizing phishing. In this paper, we propose a mechanism that could help recognize phishing or real URLs. The dataset consists of clean, spam, malicious, phishing, and defacement websites. Also, phishing URLs obtained from an open-source website known as "Phish Tank," which provides phishing URLs in different formats such as JSON, CSV, and others, have been included. Six models for recognizing phishing URLs based on the machine learning and deep neural network algorithms have been tested. With a set of about 10,000 random URLs, including up to 23,328 phishing URLs and 4894 valid URLs, divided into training and testing datasets the main aim of our study consists in creating software applications for detecting phishing URLs online. The dataset of Uniform Resource Locator has been tested and trained through feature selections like HTTPS and JavaScript-based features, domain-based features, address bar-based features to distinguish between genuine and phishing URLs. This study has offered an approach towards the classification of URLs into legitimate and phishing URLs.
Keywords: Phishing, Detection, Machine Learning, Neural Network, Authentication, Identification.
Keywords: Phishing, Detection, Machine Learning, Neural Network, Authentication, Identification.
Abstract
Study on Manufacturing Strategy, Capital Purchase & Production System in an Automobile Industry
Aditi Sharma, Amogh Dwivedi, Arun Kushwaha, Arjun Kushwaha, Deependra Singh Patel, Ashesh Tiwari
DOI: 10.17148/IJIREEICE.2026.14613
Abstract: The automotive industry is continuously evolving with increasing demand for advanced technologies, improved fuel efficiency, enhanced vehicle performance, and better driving comfort. Commercial vehicle manufacturers are increasingly adopting advanced transmission systems and automated manufacturing technologies to meet global standards and customer expectations. Transmission systems are among the most critical components in any automobile because they directly influence vehicle performance, torque transmission, fuel efficiency, and operational reliability. Modern commercial vehicles require advanced transmission systems capable of delivering efficient power transmission while maintaining durability and performance under varying operating conditions.
In the automobile industry, the Capital Purchase (CapEx) and Production System are highly integrated frameworks. CapEx builds the foundation—procuring multi-million-dollar physical assets like robotics, stamping presses, and plant construction—while the Production System manages the day-to-day manufacturing and assembly operations using these assets. This Paper aims to identify the key features involved in Manufacturing Strategy, Capital Purchase & Production system in an Automobile Industry.
Keywords: Automobile, Manufacturing, Capital purchase, Production System
In the automobile industry, the Capital Purchase (CapEx) and Production System are highly integrated frameworks. CapEx builds the foundation—procuring multi-million-dollar physical assets like robotics, stamping presses, and plant construction—while the Production System manages the day-to-day manufacturing and assembly operations using these assets. This Paper aims to identify the key features involved in Manufacturing Strategy, Capital Purchase & Production system in an Automobile Industry.
Keywords: Automobile, Manufacturing, Capital purchase, Production System
Abstract
Adversarial Attacks on AI System, Vulnerabilities, Threat Models and Defensive Implications
Abdullateef Ajibola Adepoju, Saidu Sunbo Akanji, Rukayya Abdulganiyu Adepoju, Atuma Ochenu Lawrence
DOI: 10.17148/IJIREEICE.2026.14614
Abstract: Concerns about the security of artificial intelligence systems have grown sharply as these technologies take on increasingly consequential roles in healthcare, infrastructure, finance and national security. One of the most pressing threats in this space is the adversarial attack, an intentional, engineered input designed to cause an AI model to behave in ways its designers never intended. This paper brings together a decade of published evidence through a structured meta-analysis of secondary adversarial attack case studies spanning the period 2015 to 2025. The domains covered include computer vision, natural language processing, cybersecurity tools, autonomous systems and decision-support platforms. What emerges from this synthesis is not a collection of isolated incidents but a consistent picture, adversarial weaknesses are baked into how modern machine learning systems are built, stemming from their sensitivity to high- dimensional inputs, poorly defined threat assumptions, and exposure at multiple points along the data supply chain. Among the attack types reviewed, evasion attacks appeared most frequently, accounting for 78 percent of documented cases, while backdoor and data poisoning attacks, though rarer, often left the most lasting damage. One of the more striking findings is how readily attack strategies move across domains and model types and how closely AI security threats are beginning to resemble traditional cybersecurity problems. Defences, meanwhile, have struggled to keep pace, most of the mitigation strategies reviewed broke down once attackers adapted. The paper concludes with a call for threat modelling that spans the full AI development lifecycle, evaluation methods that measure genuine resilience rather than clean-data accuracy and governance structures that treat adversarial robustness as a first-class requirement.
Keywords: Adversarial Attacks, Machine Learning Security, Evasion Attacks, Data Poisoning, AI Robustness, Threat Modelling, Defensive AI.
Keywords: Adversarial Attacks, Machine Learning Security, Evasion Attacks, Data Poisoning, AI Robustness, Threat Modelling, Defensive AI.
Abstract
6G Wireless Networks: Beyond Terahertz Communications
Salamon S, Mr. P. Logaiyan
DOI: 10.17148/IJIREEICE.2026.14615
Abstract: The world is on the verge of entering the 6G era, where communication will no longer be limited to fast downloads or low latency but will become the backbone of immersive experiences such as holographic meetings, digital twins, and autonomous robotics. Terahertz (THz) frequencies are considered the crown jewel of 6G for enabling terabit-per-second data rates, but they also bring unique hurdles such as short range and high energy loss. This paper reviews recent advances in THz communication and highlights how technologies like Reconfigurable Intelligent Surfaces (RIS), artificial intelligence, and quantum-safe security are being integrated to overcome these limitations. We propose a system where THz links are supported by RIS networks, AI-driven orchestration, and hybrid security models, creating a more reliable, intelligent, and secure foundation for future wireless networks.
Keywords: 6G, Terahertz Communication, Reconfigurable Intelligent Surfaces, Artificial Intelligence, Quantum-Safe Security, Joint Sensing and Communication
Keywords: 6G, Terahertz Communication, Reconfigurable Intelligent Surfaces, Artificial Intelligence, Quantum-Safe Security, Joint Sensing and Communication
Abstract
Secure File Sharing System using Hybrid Cryptogrphy
Mrs. M. Vasuki, Dr. T. Amalraj Victoire, A. J. Thamizharasu*
DOI: 10.17148/IJIREEICE.2026.14616
Abstract: The increasing use of digital platforms for storing and sharing files has raised concerns about data security and privacy. Sensitive information shared over networks is often exposed to risks such as unauthorized access, data theft, and cyber-attacks. Therefore, it is important to develop secure methods for protecting files during storage and transmission.
This project presents a Secure File Sharing Using Hybrid Cryptography system that aims to enhance data security through the use of multiple encryption techniques. The system divides an uploaded file into different segments and encrypts each segment using AES, DES, and Blowfish algorithms. To ensure secure key exchange between users, the RSA algorithm is employed. This combination of symmetric and asymmetric encryption techniques provides an additional layer of security while maintaining efficient file processing.
The system allows users to securely upload, share, and access files through a protected environment. By encrypting file data and securing encryption keys, the proposed solution helps prevent unauthorized access and improves the confidentiality of shared information.
The developed system offers a practical and reliable approach for secure file sharing and can be applied in environments where data protection is a critical requirement. The use of hybrid cryptography strengthens overall security and makes the system suitable for modern file-sharing applications security.
Keywords: Hybrid Cryptography, Secure File Sharing, AES, DES, Blowfish, RSA, Data Security, Encryption, Java Application
This project presents a Secure File Sharing Using Hybrid Cryptography system that aims to enhance data security through the use of multiple encryption techniques. The system divides an uploaded file into different segments and encrypts each segment using AES, DES, and Blowfish algorithms. To ensure secure key exchange between users, the RSA algorithm is employed. This combination of symmetric and asymmetric encryption techniques provides an additional layer of security while maintaining efficient file processing.
The system allows users to securely upload, share, and access files through a protected environment. By encrypting file data and securing encryption keys, the proposed solution helps prevent unauthorized access and improves the confidentiality of shared information.
The developed system offers a practical and reliable approach for secure file sharing and can be applied in environments where data protection is a critical requirement. The use of hybrid cryptography strengthens overall security and makes the system suitable for modern file-sharing applications security.
Keywords: Hybrid Cryptography, Secure File Sharing, AES, DES, Blowfish, RSA, Data Security, Encryption, Java Application
Abstract
AI BASED SPAM TEXT DETECTOR
MANJUPRIYA.A, Mr. P. LOGAIYAN
DOI: 10.17148/IJIREEICE.2026.14617
Abstract: The idea of Artificial Intelligence belongs to Computer Science. The idea here is to develop machines which can perform tasks done by humans. I intend to discuss Artificial Intelligence. The technology has been adopted by many industries including health care and education. Artificial Intelligence is really useful, in these areas. Artificial Intelligence is also used in finance and cyber security. Artificial Intelligence is really useful, in places. Spamming has increased tremendously through the usage of such means. The content of spam consists of malicious ads, fake links, phishing, and misleading information. It could lead to many problems for an individual as well as for the organization. Most of the conventional techniques used in detecting spam content have proven themselves inefficient in identifying complex patterns of spam. Therefore, it is proposed to use AI-Based Spam Text Detection System for the identification and classification of spam as well as non-spam texts by using machine learning and Natural Language Processing. Machine learning techniques are trained using big datasets consisting of both types of messages to ensure greater accuracy in prediction. Due to the usage of technology in NLP, it gets extremely easy for the computer to interpret the meaning that is concealed within the messages.
Keywords: Artificial Intelligence, Spam Filter Technique, Machine Learning, Natural Language Processing, Text Categorization, Computer Security.
Keywords: Artificial Intelligence, Spam Filter Technique, Machine Learning, Natural Language Processing, Text Categorization, Computer Security.
Abstract
"Advanced Control Strategies for Grid-Connected Renewable Energy Systems using Power Electronics and Artificial Intelligence"
DR. R. K. Dhatrak, Prof. Suyog Sangharatna Dhoke, Subodh Sunil Bodhe, Mohammed Shaadurrahim Sheikh, Shivam Rampratap Das, Mayur Anand Pasle, Manish, Devidas Karmenge
DOI: 10.17148/IJIREEICE.2026.14618
Abstract: This paper presents the detailed modelling and simulation of a hybrid renewable energy-based microgrid integrating solar photovoltaic (PV), wind energy generation, battery energy storage, and conventional grid supply. The system is developed using the MATLAB/Simulink environment, enabling accurate representation of dynamic system behavior and real-time performance analysis. Advanced control strategies are implemented using PID controllers combined with logic-based switching mechanisms to ensure efficient coordination among multiple energy sources. A priority-based energy management system (EMS) is designed to maximize the utilization of renewable energy while maintaining system stability and reliability under varying operating conditions.
The proposed system is evaluated under six distinct operational scenarios, including variations in solar irradiance, wind speed, load demand, and battery state of charge. These scenarios help analyze the system’s adaptability and robustness in real-world conditions. Simulation results demonstrate that the hybrid microgrid effectively reduces dependency on grid power, enhances energy efficiency, and ensures continuous power supply even during fluctuations in renewable sources. Furthermore, the integration of intelligent control improves overall system reliability, optimizes power flow, and contributes to sustainable energy management.
Keywords: Renwable Energy; Energy Efficiency; Solar Power Generation;MATLAB/Simulink; Energy Management System
The proposed system is evaluated under six distinct operational scenarios, including variations in solar irradiance, wind speed, load demand, and battery state of charge. These scenarios help analyze the system’s adaptability and robustness in real-world conditions. Simulation results demonstrate that the hybrid microgrid effectively reduces dependency on grid power, enhances energy efficiency, and ensures continuous power supply even during fluctuations in renewable sources. Furthermore, the integration of intelligent control improves overall system reliability, optimizes power flow, and contributes to sustainable energy management.
Keywords: Renwable Energy; Energy Efficiency; Solar Power Generation;MATLAB/Simulink; Energy Management System
Abstract
Revolutionizing Farming with Machine Learning and IoT: A Smart Agriculture Approach
Sharad Ghule, Prashant Patil, Mtech Student, Depart.Artificial intelligent & Data Science Engineering
DOI: 10.17148/IJIREEICE.2026.14619
Abstract: The rapid growth of digital technologies has opened new possibilities for transforming agriculture into a more precise, productive, and sustainable sector. This project, titled "Revolutionizing Farming with Machine Learning and IoT: A Smart Agriculture Approach" introduces an integrated system that leverages sensor-based monitoring and intelligent machine learning models to support farmers in making informed decisions. The proposed system uses ESP32-driven IoT modules connected with soil moisture sensors, water-level units, temperature–humidity sensors, LDR, gas detectors, and an OLED display to continuously capture real-time field conditions. These sensor readings are processed to monitor crop health, optimize irrigation, and reduce unnecessary resource consumption. Alongside IoT monitoring, the project incorporates machine learning models for crop prediction, yield estimation, fertilizer recommendation, disease detection through image analysis, and weather forecasting. Unlike conventional platforms that rely only on manual soil reports or isolated data inputs, the system offers a unified approach combining automation, analytics, and actionable insights. An additional marketplace module promotes direct farmer-to-consumer interactions, improving transparency and strengthening farmer income. Overall, the project demonstrates how integrating IoT sensing with predictive ML algorithms can significantly improve agricultural productivity, sustainability, and decision-making efficiency while reducing environmental impacts.
Keywords: IoT, Machine Learning, Smart Agriculture, Crop Prediction, Yield Estimation, Fertilizer Recommendation, ESP32, Soil Moisture Sensor, Weather Forecasting, Image Analysis, Precision Farming, Sustainability, Real-Time Monitoring, LDR Sensor, Gas Sensor, Agriculture Marketplace, Automation, Data-Driven Decision Making, Smart Farming.
Keywords: IoT, Machine Learning, Smart Agriculture, Crop Prediction, Yield Estimation, Fertilizer Recommendation, ESP32, Soil Moisture Sensor, Weather Forecasting, Image Analysis, Precision Farming, Sustainability, Real-Time Monitoring, LDR Sensor, Gas Sensor, Agriculture Marketplace, Automation, Data-Driven Decision Making, Smart Farming.
Abstract
IoT-Based Smart Kitchen Inventory and Auto Shopping Assistant
Dr. P. N. Shinde, Prof. N. R. Janavekar, Vaishnavi Katare, Dnyaneshwari Kulkarni, Samruddhi Tilekar
DOI: 10.17148/IJIREEICE.2026.14620
Abstract: With the rapid growth in technology around, life is getting easier and easier. The world is shifting towards smartness and automation with the help of sensor technology, which is playing a huge role. Kitchen is an important space where the ingredients and the grocery items are still managed manually, which may lead to wastage of food, unnecessary purchases of items, making poor expense management. This paper proposes an IoT-Based Smart Kitchen Inventory and Auto Shopping Assistant which helps with the monitoring and management of the kitchen inventory with help of real- time data processing. This system helps from tracking the inventory to restocking the inventory to keeping a track on the expenses. The system uses Esp32 microcontroller, load cell sensors with HX711 module which helps in tracking the inventory system. The data is transmitted over Wi-fi to server backend. The system detects the items on low stock and generates a shopping list along with sending notification. Addition to this, an OCR (Optical Character Recognition)- based receipt scanning feature is added to extract the product and price information from the bill for automatic expense tracking and updating the inventory status. A web application is built to provide real-time status, shopping list and track of expense to the user.
Keywords: Esp32, HX711, Load cell Sensor, OCR, Inventory Monitoring, Internet of Things (IoT), Smart Kitchen, Real- time Monitoring, Optical Character Recognition, Expense tracking.
Keywords: Esp32, HX711, Load cell Sensor, OCR, Inventory Monitoring, Internet of Things (IoT), Smart Kitchen, Real- time Monitoring, Optical Character Recognition, Expense tracking.
Abstract
ZooVision: AI-Powered Animal Captioning And Question Answering
Sarah Jose, Goutham Krishna L U
DOI: 10.17148/IJIREEICE.2026.14621
Abstract: This paper presents ZooVision, a domain-specific Visual Question Answering (VQA) system developed to support zoo animal identification and interactive educational applications. The proposed framework combines vision and language understanding by fine-tuning a Vision-and-Language Transformer (ViLT) on a custom dataset consisting of 212 animal images representing 20 different species. Through this specialized training process, the model acquires knowledge related to animal classification, dietary habits, habitats, and behavioral characteristics, enabling it to provide more accurate and context-aware responses to user queries. To further enhance visual understanding, a BLIP-based image captioning model is employed to generate descriptive captions from input images. These captions are incorporated as additional contextual information through a prompt augmentation strategy inspired by the Caption- Conditioned Visual Question Answering (CC-VQA) framework. The integration of caption-generated semantic context helps the system better align visual features with natural language questions, resulting in improved reasoning and answer accuracy. Furthermore, the fine-tuning process expands the model's domain knowledge by introducing 292 specialized biological terms that are not commonly represented in general-purpose VQA datasets. This enriched vocabulary enables the system to deliver more detailed and informative responses within the zoological domain. Experimental observations indicate that the caption-conditioned approach contributes to stronger contextual understanding, particularly for species recognition and attribute-based questioning. The modular architecture of ZooVision also allows future integration of larger datasets and advanced vision-language models. To facilitate practical use, the complete framework is deployed as a responsive web application where users can upload animal images, view automatically generated captions, and interactively ask questions. By combining image captioning and visual question answering within a unified platform, ZooVision demonstrates the potential of multimodal artificial intelligence to enhance zoological learning, public engagement, and wildlife-related educational experiences.
Keywords: Visual Question Answering, Image Captioning, BLIP, ViLT, Deep Learning, Prompt Augmentation, Wildlife Education.
Keywords: Visual Question Answering, Image Captioning, BLIP, ViLT, Deep Learning, Prompt Augmentation, Wildlife Education.
Abstract
Bin2Win: Incentive-Based Intelligent Dustbin System
Dr. P. N. Shinde, Prof. N. R. Janavekar, Harshada P. Tompe, Bhakti A. Kalmegh, Vrunda B. Pawar
DOI: 10.17148/IJIREEICE.2026.14622
Abstract: Improper waste disposal and lack of public motivation remain major challenges in maintaining urban cleanliness. This paper presents an IoT-based Smart Dustbin with a Reward System that encourages people to dispose of waste properly by giving digital reward points. The system uses sensors and an ESP32 to detect waste, monitor bin level, and send real-time data to the cloud. It also prevents misuse and helps authorities track waste collection efficiently. The system demonstrates scalability, low cost, and suitability for smart city applications. This system combines IoT and automation to improve waste management and encourage people to keep surroundings clean. The system helps improve cleanliness and supports smart waste management in public areas.
Keywords: RFID, IoT, Reward System, Smart City, Arduino, ESP32, Sensors, Cloud Monitoring, Sustainable Waste Management.
Keywords: RFID, IoT, Reward System, Smart City, Arduino, ESP32, Sensors, Cloud Monitoring, Sustainable Waste Management.
Abstract
TRANSFORMER FAULT MONITORING AND AUTOMATION USING IoT
Dr. T.R. Sumithira, Dr. M. Mohammadha Hussaini, K. Sowmiya, S. Muralidharan, K. Vinithkannan, M. Nithish
DOI: 10.17148/IJIREEICE.2026.14623
Abstract: The main aim of this project is to detect transformer line faults and monitor the system in real time. The system uses ESP32, voltage sensor, relay, buzzer, LCD display, and IoT platforms like Blynk.The voltage values are continuously monitored and displayed on the LCD. The data is also sent to the loT platform for remote monitoring. When a fault occurs, the system gives an alert using a buzzer and automatically disconnects the supply using a relay. This helps to protect the transformer and reduce damage.This project provides a simple, low-cost, and effective solution for transformer monitoring and automation.
Keywords: Digital Relay, Transformer, Microcontroller, Fault Detection, Protection System
Keywords: Digital Relay, Transformer, Microcontroller, Fault Detection, Protection System
Abstract
BMS for Wind-Solar Hybrid System with Predictive Control Strategies
Yatiraj Ramesh Vhanmarathe, Vaibhav Hardas Dalvi, Siddharath Hanmant Garud, Gunjan Ajay Bhatgare, Prof. Mrs. P. S. Jadhav
DOI: 10.17148/IJIREEICE.2026.14624
Abstract: The increasing penetration of renewable energy sources into power systems introduces challenges related to intermittency, load uncertainty, and grid stability. This project proposes an Artificial Neural Network (ANN)-based Energy Management System (EMS) for a wind–solar hybrid microgrid (though the presented work focuses on PV, the framework is extensible) with predictive control strategies to address these issues. The system comprises two interconnected microgrids, each featuring photovoltaic (PV) generation, a battery energy storage system (BESS), local loads, and power electronic converters. A key innovation is the integration of an ANN controller that predicts load demand and energy requirements with high accuracy (~99%) by learning from historical data. Based on these predictions, the EMS dynamically balances generation, storage, and demand, deciding in real time whether to charge the battery from surplus PV or discharge during deficits. A Multi-Microgrid Controller (MMGC) further enables efficient power sharing between the two microgrids, enhancing overall reliability and energy utilization. The proposed approach improves grid stability, reduces energy wastage and power imbalance, and ensures uninterrupted power supply despite renewable fluctuations. Validated through literature-supported methodologies, this ANN-based predictive EMS offers a scalable, intelligent solution for modern renewable-integrated microgrids, contributing to enhanced energy efficiency, reduced operational costs, and resilient multi-microgrid operation.
Keywords: BMS, ANN, PV. EMS, Multi-Microgrid Controller, a battery energy storage system (BESS)
Keywords: BMS, ANN, PV. EMS, Multi-Microgrid Controller, a battery energy storage system (BESS)
Abstract
Optimal Placement of SVC and OPF Solution Using Gravitational Search Algorithm Considering Ramp-Rate Constraints
Kaki Manisha Vani
DOI: 10.17148/IJIREEICE.2026.14625
Abstract: In this paper we present a Gravitational Search Algorithm (GSA)-based OPF (Optimal Power Flow) problem based on Static Var Compensator (SVC) and generator ramp rate constraints. The OPF problem is designed to minimize generation fuel cost and voltage deviation while satisfying power balance equations and operating limits of generators, transformers, transmission lines and reactive power sources. An SVC is placed on the weakest bus under consideration to mitigate voltage deviation and is a controllable reactive power injection device. The proposed GSA can cope with the nonlinear and constrained nature of the OPF problem by adaptively interacting among possible solutions. We evaluate the effectiveness of the method on the IEEE 14-bus test system and compare it with Particle Swarm Optimization (PSO). The simulation results demonstrate that the proposed approach achieves lower generation cost, transmission losses, better voltage profile, and faster convergence than PSO. These results support the idea that integrated GSA, SVC compensation and ramp rate constraints are an effective and computationally efficient solution for practical application of OPF in power systems.
Keywords: Optimal Power Flow, Gravitational Search Algorithm, Static Var Compensator, Ramp-Rate Constraint, Voltage Deviation, Economic Load Dispatch, FACTS Devices
Keywords: Optimal Power Flow, Gravitational Search Algorithm, Static Var Compensator, Ramp-Rate Constraint, Voltage Deviation, Economic Load Dispatch, FACTS Devices
Abstract
PLC Based Tank Level and Temperature Control System
Dr. D.O. Patil, Dr. S.T. Sanamdikar, Budhibasava Jaka, Paras Jadhav
DOI: 10.17148/IJIREEICE.2026.14626
Abstract: The increasing adoption of automation in industrial processes has created a need for practical training systems that demonstrate real-time process control concepts. This paper presents the development of a Mini Process Control Plant based on an Allen-Bradley Micro820 Programmable Logic Controller (PLC) and Human Machine Interface (HMI). The developed setup integrates three important process variables, namely temperature, level, and flow, into a single educational platform. Temperature regulation is achieved using a heating element controlled through a Solid State Relay (SSR), while level control is performed using a water tank, pump, and level sensing arrangement. Flow measurement is carried out using a flow sensor interfaced with the PLC. The system supports both manual and automatic operating modes and provides real-time monitoring, alarm handling, and operator interaction through the HMI dashboard. Experimental observations demonstrate satisfactory control performance and reliable system operation. The proposed setup offers a cost-effective alternative to commercial training systems and serves as a useful platform for learning industrial automation and process control principles.
Keywords: PLC, HMI, Process Control, Micro820 PLC, Temperature Control, Level Control, Flow Control, Industrial Automation, Educational Trainer.
Keywords: PLC, HMI, Process Control, Micro820 PLC, Temperature Control, Level Control, Flow Control, Industrial Automation, Educational Trainer.
Abstract
TEMPERATURE CONTROLLER SYSTEM BASED ON PLCs
Prof. Dr. Sanamdikar S. T., Prof. Dr. Patil D. O., Kokare Sakshee S., Netke Sanskruti M.
DOI: 10.17148/IJIREEICE.2026.14627
Abstract: Temperature control is a critical parameter across a vast spectrum of industrial applications, including chemical reactors, food processing, metallurgical furnaces, and HVAC systems, where maintaining thermal stability directly influences product quality, safety, and operational efficiency. Traditional temperature control methodologies, often reliant on manual oversight or rigid analog instrumentation, frequently suffer from significant thermal lag, steady- state errors, and poor adaptability to dynamic load changes. This paper presents the design, development, and implementation of an automated, closed-loop industrial temperature control system utilizing a Programmable Logic Controller (PLC).
The core architecture of the proposed system leverages a three-tiered automation framework. At the input stage, a high- precision industrial sensor—specifically a PT100 Resistance Temperature Detector (RTD)—continuously monitors the environmental temperature,
Converting thermal variations into standardized Analog signals. These signals are processed by the PLC's Analog input module. The PLC serves as the central processing unit, executing a robust Proportional-Integral-Derivative (PID) control algorithm programmed via Ladder Diagram (LD) logic. Based on the real-time error computation between the process variable and the user-defined setpoint, the PLC modulates its output signals to drive a Solid*-tate Relay (SSR), which precisely regulates the power delivered to the heating elements and auxiliary cooling fans.
To enhance operational visibility and human-centric control, a Human-Machine Interface (HMI) is integrated into the architecture. The HMI provides real-time data visualization, graphical trend logging, alarm management for thermal overshoots, and an intuitive platform for dynamic setpoint adjustments. Experimental results demonstrate that the PLC- based PID configuration significantly minimizes temperature overshoot, dampens thermal oscillations, and reduces settling time compared to conventional ON/OFF control strategies. Ultimately, the developed system offers a highly modular, scalable, and noise-immune solution capable of achieving precise, continuous thermal regulation in demanding manufacturing environments.
The core architecture of the proposed system leverages a three-tiered automation framework. At the input stage, a high- precision industrial sensor—specifically a PT100 Resistance Temperature Detector (RTD)—continuously monitors the environmental temperature,
Converting thermal variations into standardized Analog signals. These signals are processed by the PLC's Analog input module. The PLC serves as the central processing unit, executing a robust Proportional-Integral-Derivative (PID) control algorithm programmed via Ladder Diagram (LD) logic. Based on the real-time error computation between the process variable and the user-defined setpoint, the PLC modulates its output signals to drive a Solid*-tate Relay (SSR), which precisely regulates the power delivered to the heating elements and auxiliary cooling fans.
To enhance operational visibility and human-centric control, a Human-Machine Interface (HMI) is integrated into the architecture. The HMI provides real-time data visualization, graphical trend logging, alarm management for thermal overshoots, and an intuitive platform for dynamic setpoint adjustments. Experimental results demonstrate that the PLC- based PID configuration significantly minimizes temperature overshoot, dampens thermal oscillations, and reduces settling time compared to conventional ON/OFF control strategies. Ultimately, the developed system offers a highly modular, scalable, and noise-immune solution capable of achieving precise, continuous thermal regulation in demanding manufacturing environments.
Abstract
AI SaaS Platform Using PERN Stack
Prof. P. A. Patil, Dr P. N. Shinde, Atharva Kharat, Atharva Jagtap, Ajay Rathod
DOI: 10.17148/IJIREEICE.2026.14628
Abstract: In recent years, Artificial Intelligence has made a revolution in web applications through automatic generation of content, image processing, productivity services, and so on. This paper will describe the design and implementation of AI-integrated Software as a Service (SaaS) built with the PERN stack that consists of PostgreSQL, Express.js, React.js, and Node.js. In this regard, the platform will incorporate various AI tools into one web app, which would give users access to AI services through a friendly and centralised environment. Specifically, the software will include Article Generator, Blog Title Generator, AI Image Generator, Background Removal, Object Removal, and Resume Review services. To achieve that goal, this project uses cutting-edge AI APIs that include the OpenAI API, Gemini API, Clipdrop API, and Cloudinary services for content generation and image manipulation. Besides, Clerk authentication is used for managing users' accounts, while Neon PostgreSQL serves as the database to securely store information. As for the frontend, Vercel is utilized to deploy the application.
To conclude, the suggested system aims at saving users' time and effort spent when using artificial intelligence technology for the creation of content and editing images. Additionally, the application implements a concept of partial free access according to which a user is allowed to use certain AI programs, such as Article Generator and Blog Title Generator, within a specific limit. The usage of advanced programs will be possible after purchasing access through subscriptions.
Keywords: Artificial Intelligence, SaaS Platform, PERN Stack, React.js, Node.js, PostgreSQL, OpenAI API, Gemini API, Image Processing, Cloud Computing
To conclude, the suggested system aims at saving users' time and effort spent when using artificial intelligence technology for the creation of content and editing images. Additionally, the application implements a concept of partial free access according to which a user is allowed to use certain AI programs, such as Article Generator and Blog Title Generator, within a specific limit. The usage of advanced programs will be possible after purchasing access through subscriptions.
Keywords: Artificial Intelligence, SaaS Platform, PERN Stack, React.js, Node.js, PostgreSQL, OpenAI API, Gemini API, Image Processing, Cloud Computing
Abstract
Sequential Growth Model and NeuroAMI Neural Network for Distribution Transformer Load Forecasting
Nemine, B. E., Ahiakwo, C. O., Braide, S. L., Amadi, H. N.
DOI: 10.17148/IJIREEICE.2026.14629
Abstract: Accurate distribution transformer load forecasting is essential for ensuring reliable power system operation, preventing transformer overloading, supporting asset management, and facilitating effective capacity expansion planning. However, increasing load demand, stochastic consumer behaviour, seasonal variations, and measurement uncertainties pose significant challenges to conventional forecasting techniques. This study presents a Sequential Growth Model integrated with a Neuronal Auditory Machine Intelligence (NeuroAMI) Neural Network for real-time distribution transformer load forecasting using historical electrical load time-series data. The proposed methodology incorporates a real-time discrete sampling model, finite-window normalization, data augmentation through noise injection, and trend- seasonal decomposition to improve data quality and model robustness. The NeuroAMI neural network employs auditory- inspired spectrogram feature extraction, heteroscedastic Gaussian negative log-likelihood optimization, regularized learning objectives, and online mini-batch gradient adaptation to accurately predict future transformer loading conditions. Historical transformer load data spanning 2008–2017 were utilized to forecast loading conditions from 2018–2027. The results demonstrated significant forecasting capability, with transformer load demand increasing from approximately 8,000 kW in 2017 to over 10,000 kW by 2027. The training process exhibited stable convergence, as the Negative Log- Likelihood loss decreased from approximately 80 to 20, while regularization loss reduced from about 15 to 5 over 100 training epochs. Furthermore, feeder-level forecasting revealed projected load growth from 1,500 kW to 1,850 kW for Elekahia feeder, 4,700 kW to 6,000 kW for Stadium Road feeder, and 3,600 kW to 4,300 kW for Rumukalagbor feeder. The study concludes that the proposed Sequential Growth–NeuroAMI framework provides an intelligent, adaptive, and reliable forecasting tool capable of supporting utility operational policies, preventive maintenance strategies, transformer capacity planning, and sustainable distribution network expansion.
Keywords: NeuroAMI, Transformer, Loads Forecast, Machine Learning
Keywords: NeuroAMI, Transformer, Loads Forecast, Machine Learning
Abstract
An AI-Powered Resume Evaluation and Applicant Tracking System Optimization Framework Using Machine Learning and Natural Language Processing
KANDULA MANOHAR RAMKRISHNA, Mr. B.N. SRINIVASA GUPTA*
DOI: 10.17148/IJIREEICE.2026.14630
Abstract: The recruitment landscape has been reshaped by the widespread deployment of Applicant Tracking Systems (ATS), which automatically filter the overwhelming volume of applications received for every advertised vacancy. A large share of qualified candidates are nonetheless rejected before any human review because their resumes are poorly aligned with machine-readable parsing conventions and role-specific terminology. This study presents an intelligent resume evaluation and ATS optimization framework that couples natural language processing with supervised machine learning to quantify the suitability of a curriculum vitae against a target job description and to deliver actionable, personalized improvement guidance. The proposed pipeline ingests heterogeneous document formats, performs robust text extraction and normalization, derives semantic and lexical features, and produces a calibrated compatibility score through a soft-voting ensemble of classifiers. A skill-gap analyzer cross-references extracted competencies against a curated knowledge base to surface missing keywords and formatting deficiencies. The system was implemented as a modular web application with a Node.js and React front end and a Python analytical back end. Experimental evaluation on a corpus of annotated resume–vacancy pairs demonstrated an accuracy of 92.7% and an F1-score of 0.921, surpassing four competitive baseline classifiers. Beyond predictive performance, the framework reduced the average number of unaddressed keyword gaps per resume by a substantial margin in a controlled user study. The principal contributions are a reproducible feature-engineering scheme, an interpretable scoring mechanism, and an end-to-end deployable architecture suitable for real-world career-support settings.
Keywords: Resume evaluation, Applicant Tracking System, Natural Language Processing, Machine Learning, Ensemble Learning, Skill-Gap Analysis, Recruitment Automation, Text Mining
Keywords: Resume evaluation, Applicant Tracking System, Natural Language Processing, Machine Learning, Ensemble Learning, Skill-Gap Analysis, Recruitment Automation, Text Mining
Abstract
A Web-Based Automated Examination Management System Using Flask Framework and Lightweight Relational Database Architecture
ATYAM SRAVANI, Dr. CHIRAPARAPU SRINIVASARAO*
DOI: 10.17148/IJIREEICE.2026.14631
Abstract: The rapid proliferation of digital infrastructure in educational institutions has necessitated a paradigm shift from conventional paper-based assessments toward automated, technology-driven examination platforms. This paper presents the design, implementation, and evaluation of a lightweight yet fully functional web-based examination management system developed using the Flask micro-framework in Python 3.11, a SQLite relational database, and a responsive front-end interface rendered through the Jinja2 templating engine. The proposed system encompasses a dual- role architecture supporting both student and administrative workflows. Students can register, authenticate, attempt a dynamically served multiple-choice examination, and immediately retrieve their evaluated results. Administrators are provided with a secured dashboard enabling complete lifecycle management of examination questions including creation, modification, and deletion as well as oversight of candidate performance records and the ability to reset individual examination attempts. The system enforces a single-attempt constraint per candidate through session-aware database integrity checks, mitigating examination malpractice. Deployment readiness is demonstrated through Gunicorn WSGI server integration and AWS CodeBuild compatibility via a structured buildspec.yml configuration. Empirical evaluation indicates a mean page response latency of 4.2 seconds under simulated load, with an average system usability score of 90 out of 100. The proposed architecture establishes a cost-effective, scalable, and pedagogically sound foundation for digital assessment, with prospective extensions including adaptive questioning, AI-driven proctoring, and multi-subject examination modules.
Keywords: web-based examination system, Flask framework, SQLite database, e-assessment, automated grading, educational technology, session management, WSGI deployment
Keywords: web-based examination system, Flask framework, SQLite database, e-assessment, automated grading, educational technology, session management, WSGI deployment
Abstract
A Serverless Job Portal Architecture Using Managed Cloud Functions and Automated Continuous-Integration Deployment
V.SAI SURYA PRABHAVATHI, K. LAKSHMI SAI SRI*
DOI: 10.17148/IJIREEICE.2026.14632
Abstract: Online recruitment platforms must contend with highly irregular traffic, frequent feature updates, and the need to remain cost-effective during idle periods, yet many are built on continuously provisioned servers that incur expense even when unused and demand substantial operational effort to scale and maintain. This paper presents a job portal engineered on a serverless paradigm, in which application logic executes as managed, event-driven cloud functions that scale automatically with demand and incur charges only during actual execution. The platform pairs Java-based backend functions with a Node.js web client hosted and continuously deployed through a managed hosting service integrated with an automated continuous-integration build pipeline, so that every code change is compiled, tested, and released without manual intervention. Requests are routed through an API gateway to function handlers that perform authentication, job search, application submission, posting, and intelligent candidate matching, supported by managed database, object- storage, and identity services. Experimental evaluation under simulated load demonstrated an average warm response time of 82 milliseconds at one hundred requests per second and graceful degradation under higher load, while eliminating idle infrastructure cost entirely. Compared with a continuously provisioned monolithic baseline, the serverless platform achieved superior scalability, markedly higher deployment frequency, and substantial idle-cost savings. The principal contributions of this work are a fully serverless recruitment-platform architecture, an integrated continuous-deployment pipeline that accelerates and de-risks releases, and an empirical demonstration of favourable latency, scalability, and cost characteristics relative to conventional server-based designs.
Keywords: Serverless computing, job portal, cloud functions, continuous integration, continuous deployment, auto- scaling, function-as-a-service, recruitment platform.
Keywords: Serverless computing, job portal, cloud functions, continuous integration, continuous deployment, auto- scaling, function-as-a-service, recruitment platform.
Abstract
A Cloud-Deployed Intelligent Ride Allocation and Dynamic Fare Optimization System Using Python and RESTful Microservices
MULLAPUDI VINEELA SAI, Mr. KARRI LAKSHAMANA REDDY*
DOI: 10.17148/IJIREEICE.2026.14633
Abstract: The rapid proliferation of on-demand urban mobility services has underscored the critical need for efficient, scalable, and cost-transparent platforms that can seamlessly connect passengers with nearby drivers in real time. This paper presents the design, implementation, and evaluation of an intelligent cloud-deployable ride allocation and dynamic fare optimization platform developed entirely in Python. The proposed system leverages the FastAPI asynchronous web framework for high-throughput request handling, SQLAlchemy Object-Relational Mapping (ORM) for persistent data management, and OpenStreetMap Nomination for cost-free geocoding augmented by database-level caching. The core algorithmic contributions encompass a Haversine-based greedy nearest-driver matching algorithm and a five-tier rule- based surge pricing model that continuously evaluates real-time demand-to-supply ratios to determine an appropriate fare multiplier. The system supports three role-segregated user classes-passenger, driver, and administrator-governed by session-based authentication reinforced through Cross-Site Request Forgery (CSRF) token validation. An automated test suite comprising 40 scenarios across seven functional modules achieves a 100% pass rate, validating fare computation accuracy, driver assignment correctness, and end-to-end ride lifecycle integrity. Deployment configurations targeting Amazon Web Services Elastic Beanstalk confirm cloud portability. Experimental results demonstrate sub-millisecond fare computation, sub-5-millisecond driver matching, and an 85% geocoding cache hit rate, collectively affirming the platform's suitability for production-grade urban ride-sharing deployment.
Keywords: ride-sharing systems; dynamic fare optimization; Haversine algorithm; nearest-driver matching; surge pricing; FastAPI; cloud deployment; OpenStreetMap Nomination.
Keywords: ride-sharing systems; dynamic fare optimization; Haversine algorithm; nearest-driver matching; surge pricing; FastAPI; cloud deployment; OpenStreetMap Nomination.
Abstract
A Containerized Microservices Framework for Vendor and Supply Chain Management Using Docker and Kubernetes on AWS EKS
SONGA BHARATHI, PADALA SRINIVASA REDDY*
DOI: 10.17148/IJIREEICE.2026.14634
Abstract: Modern supply chains span many vendors, fluctuating order volumes, and geographically dispersed stakeholders, yet a large share of enterprise procurement systems remain monolithic and statically provisioned, which limits their ability to scale during demand peaks and complicates iterative feature delivery. This paper presents the design, implementation, and evaluation of a containerized vendor and supply chain management platform built as a set of independently deployable microservices. The business logic is implemented in Java and exposed through RESTful interfaces, while a Node.js layer renders the client experience. Each service is packaged as a Docker image and orchestrated on Amazon Elastic Kubernetes Service (EKS), where a Horizontal Pod Autoscaler adjusts replica counts according to live CPU and request metrics, and a managed ingress controller balances inbound traffic. Persistent state is externalized to Amazon RDS, with Redis caching and Amazon S3 document storage. Delivery is automated through a container pipeline that builds and tests artifacts, publishes images to Amazon ECR, and performs rolling updates with health-gated rollback. Experimental evaluation under synthetic procurement load shows that the proposed system sustains average response times below 300 ms at eight thousand concurrent requests, scaling elastically from three to eighteen pods, whereas a virtual-machine monolith degrades beyond three seconds. The platform also reduces deployment lead time and isolates faults to individual services. The contributions are a modular containerized reference architecture, an autoscaling orchestration strategy, and a reproducible continuous-delivery workflow for supply chain operations.
Keywords: Microservices; Docker; Kubernetes; AWS EKS; supply chain management; horizontal pod autoscaling; containerization; DevOps
Keywords: Microservices; Docker; Kubernetes; AWS EKS; supply chain management; horizontal pod autoscaling; containerization; DevOps
Abstract
A Cloud-Native Hospital Appointment Scheduling and Electronic Health Record Management System Leveraging AWS Services and DevOps Automation
KADALI VASANTH, Smt A.N. RAMA MANI*
DOI: 10.17148/IJIREEICE.2026.14635
Abstract: The growing demand for accessible and reliable digital healthcare has exposed the limitations of conventional, on-premise hospital management software, which frequently suffers from poor scalability, fragmented patient data, and unreliable service availability during peak load. This study presents the design and evaluation of a cloud-native platform that unifies outpatient appointment scheduling with electronic health record (EHR) management while embedding continuous integration and continuous delivery (CI/CD) practices throughout its lifecycle. The proposed system adopts a containerized microservice architecture deployed on Amazon Web Services (AWS), in which application logic is implemented in Python and the presentation layer is built using Node.js. A priority-aware scheduling routine allocates consultation slots, while patient records are persisted across managed relational and object storage services to balance consistency and elasticity. Infrastructure provisioning, automated testing, and deployment are orchestrated through an Infrastructure-as-Code and pipeline-driven DevOps workflow. Experimental evaluation under synthetic concurrent load demonstrates that the platform sustains an average response latency of roughly 312 ms at 1000 simultaneous users— markedly lower than a monolithic baseline—while horizontal auto-scaling preserves a measured service availability of 99.8%. Adoption of automated pipelines reduced deployment lead time from approximately 95 minutes to under 10 minutes and shortened mean recovery time after failure. The principal contributions are an integrated appointment-plus- EHR reference architecture, a reproducible DevOps automation strategy for healthcare workloads, and an empirical performance characterization that quantifies the benefits of cloud elasticity for clinical service delivery.
Keywords: Cloud computing; Electronic Health Records; Appointment scheduling; Amazon Web Services; DevOps; Microservices; Continuous integration; Healthcare informatics
Keywords: Cloud computing; Electronic Health Records; Appointment scheduling; Amazon Web Services; DevOps; Microservices; Continuous integration; Healthcare informatics