← Back to Archives
VOLUME 15, ISSUE 7, JULY 2026
Publication in progress..
Challenges of Cloud Data Privacy in Surveillance: Legal, Technical, and Ethical Implications
Ahmed S. AlMahmeed
EduAssist: A Hierarchical Conversational Educational Recommendation (HCER) Framework for Personalized and Adaptive Learning
Shashank G, Gurudeep V, Vijay M
A Comprehensive Review of Cloud Security and Trust Management: Challenges, Threats, Security Techniques, and Future Directions
Shruti Mehan, Dinesh Parkash
A Comprehensive Review of Cloud Storage Technologies, Architecture, Security Challenges, and Future Directions
Arpit Sandhu, Dr. Dinesh Parkash
Agentic AI for Autonomous Cyber Incident Response: A Multi-Agent Framework for Intelligent Threat Mitigation
Syed Saifuddin Ahmed Muzaffar
Design of Digital Notice Board using ESP32
Dr. K. Senthil Babu, Dr. Dileep J, Dr. Kishore M
Smart Scan Shopping Trolley Using IOT
Ch.Swetha, M.Siri Vennela, B.Tejaswini, R.Poojitha, K.Sathwika
The Impact of Artificial Intelligence on Modern Society: Opportunities, Risks, and the Future of Human Development
Ahmed S. AlMahmeed
IoT-Based Biosensing Kit for Salivary Protein Estimation
Moushami D, Rachna V, B Srinidhi, Surekha Bhangari, Ganga Holi
Smart Traffic Light System using IoT
Mrs.Nasreen, Sunhera Fathima, T. Shiva Prasad, S. Shivani, R. Karthik
An Analysis of Thermal Throttling and Sustained Performance Degradation in Modern Mobile Processors
Supreeth Nandakumar Pawar, Tanishq Agarwal, Tanushree.R, Suhas K, Dr. Sonia Maria D'souza
IoT-Based Smart Helmet
Mr. M. Suresh Babu, M. Praneeth, R. Rishika, A. Jithendra, Shruthi Goud.P
A Scalable Extractive Text Summarisation Model for Hausa Language Documents Using K-Nearest Neighbours and Sparse Matrix Representation
Musa Tanimu Karatu, Abdulsamad Muazu, Ibrahim Saidu
Multi-Featured Smart Vehicle with Safety Monitoring using IoT
M. Ravi, Anup Mandal, G. Anirudh, H. Bhagya Shree, M. Shashank Yadav
DIY FIRE EXTINGUISHER DRONE USING IoT
Mrs. Laxmi Hugar, B. Kumaraswamy, D. Haasini, L. Divakar, M. Laxmi Bhavani
Smart Saline Monitoring and Alert System Using IoT
Rambabu Pemula, A. Athikah, B. Suraj, G. Koushik, P. Swaroop
THE INTELLIGENT CAR WITH ACCIDENT ALERT AND DRIVER ASSISTANCE SYSTEM
Mr. M . Ravi, Ch.Sohan, B.Aryan, M. Vaishnavi, B.Srinu
Artificial Intelligence for Antenna Design, Surrogate Modeling, And Optimization: A Review of Methods, Trends, And Open Challenges
Abinaya Sree R. J., Renisha G., Blessy S.
IoT-Based Smart Pothole Detection And Alert System
K.SanthiPriya, T.Vivekananda, V.Akhila, MD.Saniya, MohammedTalhaFarooqui
A Comparative Study of Conversational AI
Tools: ChatGPT, Claude, and Gemini in, Dr.P.Bharathisindhu
Quantum-Enhanced Intrusion Detection Systems for IoT Networks: Trends, Challenges, and Future Directions
Sivasubramanyam Medasani, M Neavruth Sai, Jhanavi C, Lakshmi B
Quantum Key Distribution for Secure IoT Communication: Recent Advances, Challenges, and Future Perspectives
Sivasubramanyam Medasani, Akhil Goutham K, Bhaskar S, H Vishnu
AI-Based Plagiarism Detection System Using Deep Learning and LLMs
Anitha J, Swathi, Vinanya V
Code Generation and Debugging Assistant using Deep Learning and Large Language Models
Nikhitha H S, Priyarani Suramanji, Dr Indumathi S K
Advanced time frequency approaches in SMOTFS and OTFS for wireless system
R. Prethesha and I. Muthumani
An IoT-Based Smart Umbrella for Weather Awareness, Renewable Energy Harvesting, and Emergency Location Tracking
Dr. Manu M N, Prof. Prarthana J V, Prof. Gayathri S
Smart IDS: Reducing False Alarms in Real-Time and Live Network Intrusion Detection Using Machine Learning
Kusumuru Mounika, Mandakuriti Sai Charan, Pyla Jyothi, Mukkera Akhil, Kindal Ashok Kumar
PERIPHERAL ARTERIAL DISEASE DETECTION USING MACHINE LEARNING
Ayesha Sayed, Ayishath Raheesha, Isha M Bhandary, Ishita P Acharya, Ms. Shwetha Kamath
Hyperloop: Revolutionizing Modern Transportation
Vishwa Tigari, Yashwanth V, Yogesh K N, Prof. Anitha J
Electronic Voting System Using Web Technology
Anusha S M, Kumar Siddamallappa U, Shreedevi Prakash Gotur
Abstract
Challenges of Cloud Data Privacy in Surveillance: Legal, Technical, and Ethical Implications
Ahmed S. AlMahmeed
DOI: 10.17148/IJARCCE.2026.15701
Abstract: The migration of surveillance systems to cloud infrastructure has improved scalability and analytics capabilities but introduces distinct privacy challenges: jurisdictional conflicts between GDPR and the CLOUD Act, expanded attack surfaces from third-party integrations, mandatory retention that conflicts with data minimization, and function creep enabled by centralized data lakes. Using case law from Schrems II, breach reports from ENISA, and technical evaluations of federated learning and differential privacy, this paper systematizes core risks of cloud surveillance. We contribute: 1) a taxonomy of seven cloud-surveillance privacy challenges, 2) an end-to-end architecture with privacy controls, 3) a STRIDE+LINDDUN threat model, and 4) a four-layer mitigation framework. Evaluation shows federated learning reduces raw video egress by 98% with 4% F1 loss, while geo-fenced encryption satisfies Schrems II supplementary measures. We argue that technical safeguards alone are insufficient without multilateral legal harmonization and independent oversight.
Keywords: Cloud surveillance, data privacy, GDPR, CLOUD Act, differential privacy, federated learning, STRIDE, cross-border data, immutability.
Keywords: Cloud surveillance, data privacy, GDPR, CLOUD Act, differential privacy, federated learning, STRIDE, cross-border data, immutability.
Abstract
EduAssist: A Hierarchical Conversational Educational Recommendation (HCER) Framework for Personalized and Adaptive Learning
Shashank G, Gurudeep V, Vijay M
DOI: 10.17148/IJARCCE.2026.15702
Abstract: The growth of digital learning platforms has changed the way students look for knowledge and academic support. As these environments continue to expand, there is a rising demand for tools that can respond instantly and adapt to the needs of individual learners. Educational chatbots have emerged as one answer to this demand, offering students immediate answers, access to study resources, and academic guidance outside the traditional classroom. This paper presents EduAssist, a conceptual educational chatbot built around Natural Language Processing (NLP), designed to support personalized learning and sustained student engagement. By analyzing user queries through NLP techniques, the system is intended to generate relevant answers and recommend educational resources tailored to each learner's needs. Through the combination of conversational interaction, structured knowledge management, and voice-based accessibility, EduAssist aims to make independent study more approachable and consistent. Because this work presents a system design rather than a deployed application, the paper focuses on architecture, proposed functionality, and anticipated behavior, and identifies the steps — including prototype development and empirical evaluation — required to validate the framework in practice.
Keywords: Educational Chatbot, Natural Language Processing (NLP), Personalized Learning, Adaptive Learning, Conversational AI, Student Support Systems, Educational Technology, Intelligent Tutoring Systems, Learning Analytics, Artificial Intelligence.
Keywords: Educational Chatbot, Natural Language Processing (NLP), Personalized Learning, Adaptive Learning, Conversational AI, Student Support Systems, Educational Technology, Intelligent Tutoring Systems, Learning Analytics, Artificial Intelligence.
Abstract
A Comprehensive Review of Cloud Security and Trust Management: Challenges, Threats, Security Techniques, and Future Directions
Shruti Mehan, Dinesh Parkash
DOI: 10.17148/IJARCCE.2026.15703
Abstract: Cloud computing has become one of the most widely used technologies for delivering computing resources and services over the internet. It provides several benefits such as flexibility, scalability, cost-effectiveness and easy access applications and data. However rapid growth of cloud services has also increased security concerns. Since sensitive and confidential information is stored over cloud platforms that are highly vulnerable to cyber-attacks, data breaches, malware attacks and insider threats. This paper presents an overview of cloud computing and its service models, along with major security threats and challenges, and also presents security solutions in the cloud environment. Various security techniques, such as encryption, authentication, access control, Artificial Intelligence-based security, and blockchain-based security, are discussed.
Keywords: Intrusion Detection Systems (IDS), Cuckoo Search Algorithms (CSA), Artificial Bee Colony Algorithm (ABC), Support Vector Machine (SVM), Naïve Bayes (NB)
Keywords: Intrusion Detection Systems (IDS), Cuckoo Search Algorithms (CSA), Artificial Bee Colony Algorithm (ABC), Support Vector Machine (SVM), Naïve Bayes (NB)
Abstract
A Comprehensive Review of Cloud Storage Technologies, Architecture, Security Challenges, and Future Directions
Arpit Sandhu, Dr. Dinesh Parkash
DOI: 10.17148/IJARCCE.2026.15704
Abstract: Cloud computing has transformed the way organizations store, manage, and access data by offering scalable, flexible, and cost-efficient storage services through the internet. However, challenges such as inefficient resource allocation, service downtime, vendor lock-in, and data security risks continue to limit its full potential. This paper presents an intelligent framework for optimizing cloud storage resources using machine learning. The framework leverages predictive models to analyse usage patterns, dynamically allocate resources, and enhance system performance while reducing operational costs. Machine learning techniques are further applied to strengthen security by detecting anomalies and mitigating threats, thereby improving reliability and resilience in cloud environments. The study reviews existing cloud storage models and deployment approaches, highlighting the advantages and limitations of public, private, and hybrid systems. It also examines distributed storage technologies and layered cloud storage architecture to establish the foundation for intelligent optimization. Experimental insights and comparative analysis demonstrate that machine learning-driven approaches significantly improve throughput, minimize latency, and ensure better scalability. The paper concludes by emphasizing future directions where artificial intelligence, blockchain, and decentralized storage can further advance secure, adaptive, and efficient cloud storage systems, making them central to next-generation computing.
Keywords: Intrusion Detection system (IDS), Cuckoo Search Algorithm (CSA), Artificial Bee Colony Algorithm (ABC), Support Vector Machine (SVM), Na𝑖̈ ve Bayes (NB)
Keywords: Intrusion Detection system (IDS), Cuckoo Search Algorithm (CSA), Artificial Bee Colony Algorithm (ABC), Support Vector Machine (SVM), Na𝑖̈ ve Bayes (NB)
Abstract
Agentic AI for Autonomous Cyber Incident Response: A Multi-Agent Framework for Intelligent Threat Mitigation
Syed Saifuddin Ahmed Muzaffar
DOI: 10.17148/IJARCCE.2026.15705
Abstract: As a result of hidden-run Agentic approach, AI becomes a huge form of protecting computers against any hacker attacks. It enables systems to work autonomously based on goal-oriented reasoning, planning, and implementation. In this paper, we will try to analyses how it is possible to implement agentic AI technology (in a broader sense) to achieve autonomous cyber-attack response. We would like to know how it could help make wise affirmative action an automated one and thus transform its people-dependent nature into a defensible real-time reaction to any attack. According to the architecture proposed, there are many cooperative agents playing separate roles (detect, analyses, decide, respond, and learn). Such a system learns continually by combining reinforcement learning and threat intelligence, coupled with feedback mechanisms, which results in making a computer immune to any advanced cyber- attack and zero-day attack. Many benchmark datasets have been applied, and as a result, this system was proved to significantly outperform other systems in terms of detection accuracy, response time, and automation efficiency, despite being compared with classic/semi-automatic one.
Keywords: Agentic AI, Autonomous Cyber Incident Response, Multi-Agent Systems, Cybersecurity Automation, Reinforcement Learning, Threat Intelligence, SOC Automation, Adaptive Security Systems
Keywords: Agentic AI, Autonomous Cyber Incident Response, Multi-Agent Systems, Cybersecurity Automation, Reinforcement Learning, Threat Intelligence, SOC Automation, Adaptive Security Systems
Abstract
Design of Digital Notice Board using ESP32
Dr. K. Senthil Babu, Dr. Dileep J, Dr. Kishore M
DOI: 10.17148/IJARCCE.2026.15706
Abstract: Communication plays a major role in educational institutions, offices, and public places. Traditionally, notice boards have been used to display important announcements, schedules, circulars, and emergency alerts. These notice boards require manual posting, which involves printing the notice, physically placing it on the board, and frequently updating or removing it. This traditional process is slow, time-consuming, labour-dependent, and often leads to communication delays. With the increasing use of smartphones, cloud computing, and IoT (Internet of Things), there is a growing need for a modern, efficient, and instant notice delivery system. IoT technology allows devices to communicate and share information over the internet in real time. By applying IoT to notice boards, messages can be updated wirelessly from anywhere, eliminating the need for manual updates.
The ESP32 microcontroller, with built-in Wi-Fi, makes it possible to connect a display system to the internet. Combining ESP32 with Firebase Realtime Database enables fast and reliable cloud-based communication. A notice posted from a mobile app can reach the display board instantly through the cloud. This forms the foundation of an IoT-powered digital notice board system. In this project, a mobile application is used to create and send messages. These messages are uploaded to Firebase, and the ESP32 retrieves them and displays them on a VGA monitor. This provides a smart, eco- friendly, and automated replacement for traditional notice boards. The system is especially useful for institutions that require quick updates, such as schools, colleges, offices, malls, and transport stations Over the past several decades, notice boards have remained a common means of communication in public and private institutions.
Keywords: Cloud, ESP32, Mobile Application, Display, Web Page, Wi-Fi.
The ESP32 microcontroller, with built-in Wi-Fi, makes it possible to connect a display system to the internet. Combining ESP32 with Firebase Realtime Database enables fast and reliable cloud-based communication. A notice posted from a mobile app can reach the display board instantly through the cloud. This forms the foundation of an IoT-powered digital notice board system. In this project, a mobile application is used to create and send messages. These messages are uploaded to Firebase, and the ESP32 retrieves them and displays them on a VGA monitor. This provides a smart, eco- friendly, and automated replacement for traditional notice boards. The system is especially useful for institutions that require quick updates, such as schools, colleges, offices, malls, and transport stations Over the past several decades, notice boards have remained a common means of communication in public and private institutions.
Keywords: Cloud, ESP32, Mobile Application, Display, Web Page, Wi-Fi.
Abstract
Smart Scan Shopping Trolley Using IOT
Ch.Swetha, M.Siri Vennela, B.Tejaswini, R.Poojitha, K.Sathwika
DOI: 10.17148/IJARCCE.2026.15707
Abstract: The Smartscan Shopping Trolley is an innovative system designed to simplify and automate the billing process in supermarkets. This project integrates a microcontroller-based system with a barcode or QR code scanner mounted on a trolley, allowing customers to scan items before placing them into the cart. Once scanned, the system retrieves the product information and automatically updates the total cost, which is displayed in real time on an LCD screen, If an item is removed, the user can rescan it to deduct the price from the total. To ensure accuracy and prevent unauthorized additions, the system includes an error detection mechanism that triggers a buzzer or voice alert when an invalid or unregistered product is scanned. Additionally, loT functionality can be incorporated to transmit billing data to a mobile application or cloud platform, enhancing user convenience and enabling real-time monitoring. This project reduces waiting time at billing counters, improves shopping efficiency, and demonstrates the practical application of embedded systems and loT in smart retail environments.
Keywords: IoT (Internet of Things), Smart Shopping Trolley, Barcode Scanner, QR Code System, Automated Billing System, Embedded Systems, Real-Time Processing, RFID, Smart Retail, Arduino, ESP8266
Keywords: IoT (Internet of Things), Smart Shopping Trolley, Barcode Scanner, QR Code System, Automated Billing System, Embedded Systems, Real-Time Processing, RFID, Smart Retail, Arduino, ESP8266
Abstract
The Impact of Artificial Intelligence on Modern Society: Opportunities, Risks, and the Future of Human Development
Ahmed S. AlMahmeed
DOI: 10.17148/IJARCCE.2026.15708
Abstract: Artificial Intelligence (AI) has emerged as one of the most transformative technologies of the 21st century, reshaping modern society, economic structures, and knowledge systems. Recent research from Harvard Business School, the UN, Brookings, and Goldman Sachs paints a consistent picture: AI is reshaping creativity, productivity, and how people make decisions (Harvard Business School, 2025; United Nations, 2026). This research provides a comprehensive analysis of AI from both conceptual and applied perspectives, examining its foundations, current development, and wide- ranging societal impact. The study explores AI’s influence across key domains: economic systems, work and employment, education, healthcare, governance, and social interaction. Particular emphasis is placed on AI’s role in increasing productivity, enabling automation, and transforming traditional industries. A significant focus is the transition from assistive to agentic AI — autonomous systems that can plan, reason and execute workflows — now functioning as digital teammates (Harvard Business School, 2025). In parallel, the research critically analyzes risks: job displacement, mental health harms, deceptive AI behavior, governance gaps, and concentrated development in the U.S. and China (UN Scientific Panel, 2026). Findings highlight the necessity for proactive governance and ethical frameworks to mitigate risks while maximizing benefits.
Keywords: artificial intelligence, agentic AI, modern society, economic impact, future of work, AI governance, digital divide, human-AI collaboration
Keywords: artificial intelligence, agentic AI, modern society, economic impact, future of work, AI governance, digital divide, human-AI collaboration
Abstract
IoT-Based Biosensing Kit for Salivary Protein Estimation
Moushami D, Rachna V, B Srinidhi, Surekha Bhangari, Ganga Holi
DOI: 10.17148/IJARCCE.2026.15709
Abstract: The rapid advancement of Internet of Things (IoT) technology has enabled the development of intelligent healthcare systems capable of real-time monitoring and analysis. This paper presents the design and implementation of an IoT-based biosensing kit for estimating protein concentration in human saliva using a colorimetric detection technique. The proposed system integrates an ESP32 microcontroller, TCS3200 colour sensor, Biuret reagent, I2C LCD display, and the ThingSpeak cloud platform to provide a portable, cost-effective, and non-invasive protein detection solution. The colorimetric reaction converts biochemical changes into measurable optical signals, which are processed using a calibration model to estimate protein concentration and transmitted to the cloud for real-time visualization and analysis. The developed prototype was evaluated through a preliminary experimental study by comparing salivary protein concentration before and after chanting, demonstrating the feasibility of the proposed approach for behavioural and physiological monitoring. Experimental results demonstrated successful protein estimation, reliable cloud-based data monitoring, and ease of operation, indicating the potential of the proposed system for point-of-care diagnostics and future smart healthcare applications.
Keywords: Internet of Things (IoT), ESP32, Salivary Protein Detection, Biosensor, TCS3200 Colour Sensor, Biuret Assay, ThingSpeak, Non-invasive Diagnostics.
Keywords: Internet of Things (IoT), ESP32, Salivary Protein Detection, Biosensor, TCS3200 Colour Sensor, Biuret Assay, ThingSpeak, Non-invasive Diagnostics.
Abstract
Smart Traffic Light System using IoT
Mrs.Nasreen, Sunhera Fathima, T. Shiva Prasad, S. Shivani, R. Karthik
DOI: 10.17148/IJARCCE.2026.15710
Abstract: The Smart Traffic Light System Using IoT is an intelligent traffic management solution designed to reduce traffic congestion and improve the efficiency of road intersections. This project integrates a microcontroller-based system with vehicle detection sensors to monitor real-time traffic density on different roads. Based on the collected data, the system automatically adjusts traffic signal timings to provide smoother vehicle movement and minimize unnecessary waiting time. The system also incorporates IoT technology to transmit traffic information to a cloud platform or mobile application, enabling real-time monitoring and remote management by traffic authorities. Additionally, emergency vehicle priority can be implemented to ensure faster clearance for ambulances and fire services. The proposed system helps reduce fuel consumption, travel time, and environmental pollution while improving road safety. This project demonstrates the practical application of embedded systems and IoT in developing efficient, reliable, and smart traffic management solutions for modern cities.
Keywords: IoT (Internet of Things), Smart Traffic Light System, Traffic Management, Vehicle Detection Sensors, Automated Traffic Control, Embedded Systems, Real-Time Monitoring, Arduino, ESP8266, Smart Cities.
Keywords: IoT (Internet of Things), Smart Traffic Light System, Traffic Management, Vehicle Detection Sensors, Automated Traffic Control, Embedded Systems, Real-Time Monitoring, Arduino, ESP8266, Smart Cities.
Abstract
An Analysis of Thermal Throttling and Sustained Performance Degradation in Modern Mobile Processors
Supreeth Nandakumar Pawar, Tanishq Agarwal, Tanushree.R, Suhas K, Dr. Sonia Maria D'souza
DOI: 10.17148/IJARCCE.2026.15711
Abstract: Mobile processors are advancing at a blistering pace, but managing the heat they generate remains a massive challenge. This paper investigates how different tiers of smartphone processors handle heat buildup and performance drops during a variety of sustained workloads, including 3D rendering and high-resolution media consumption. By using diagnostic tools (ADB) to bypass standard benchmark software, raw hardware metrics were extracted directly from the devices. The data reveals that highly clocked processing units generate extreme heat during heavy compute tasks, suffering massive performance drops (up to 35%) to stop themselves from overheating. In contrast, processors designed for balanced power draw naturally operate cooler by prioritizing efficiency cores. Furthermore, the data demonstrates that offloading sustained media tasks to dedicated Video Processing Units (VPUs) significantly reduces thermal saturation across all architectures, providing a more stable, long-term user experience.
Keywords: System on a Chip, SoC Microarchitecture, ARM Cortex-X, Thermal Throttling Management, DVFS Optimization, big.LITTLE Task Scheduling, Performance Degradation, Android OS Telemetry.
Keywords: System on a Chip, SoC Microarchitecture, ARM Cortex-X, Thermal Throttling Management, DVFS Optimization, big.LITTLE Task Scheduling, Performance Degradation, Android OS Telemetry.
Abstract
IoT-Based Smart Helmet
Mr. M. Suresh Babu, M. Praneeth, R. Rishika, A. Jithendra, Shruthi Goud.P
DOI: 10.17148/IJARCCE.2026.15712
Abstract: This project focuses on the design and implementation of an IoT-based Smart Helmet System to enhance the safety of two-wheeler riders. Statistics indicate that a significant number of road accidents are caused by alcohol consumption, negligence, and fatigue. The proposed system integrates multiple sensors, including an alcohol sensor to detect the presence of alcohol in the rider’s breath and a detection mechanism to ensure helmet usage before vehicle ignition. The system also incorporates environmental monitoring to identify accident-prone zones. A communication module is used to send real-time alerts and emergency notifications in case of accidents. The integration of embedded systems and IoT technology enables real-time monitoring and preventive measures. This solution aims to reduce human errors, enforce safety compliance, and provide a cost-effective approach to minimizing road accidents and fatalities among two-wheeler users. This paper presents the design and implementation of an IoT-based smart helmet system aimed at enhancing the safety of two-wheeler riders. The proposed system integrates multiple sensors, including an alcohol sensor to detect the presence of alcohol in the rider’s breath and a helmet detection mechanism to ensure proper usage before vehicle ignition. An accident detection module is incorporated using motion and impact sensors to identify potential crashes in real time. In the event of an accident, a communication module sends immediate alerts and location details to emergency contacts. Additionally, environmental monitoring is utilized to identify accident-prone conditions. The integration of embedded systems and IoT technology enables real-time monitoring and preventive safety measures. This system aims to reduce road accidents caused by human error, enforce safety compliance, and provide a cost-effective solution for improving rider safety.
Keywords: Smart Helmet, IoT, Alcohol Detection, Accident Detection, Rider Safety, Sensors, Emergency Alert System, Two-Wheeler Safety.
Keywords: Smart Helmet, IoT, Alcohol Detection, Accident Detection, Rider Safety, Sensors, Emergency Alert System, Two-Wheeler Safety.
Abstract
A Scalable Extractive Text Summarisation Model for Hausa Language Documents Using K-Nearest Neighbours and Sparse Matrix Representation
Musa Tanimu Karatu, Abdulsamad Muazu, Ibrahim Saidu
DOI: 10.17148/IJARCCE.2026.15713
Abstract: Extractive text summarisation has become an essential Natural Language Processing (NLP) task for managing the rapid growth of digital textual information. However, conventional graph-based summarisation methods often suffer from high computational complexity and memory consumption due to exhaustive pairwise sentence similarity computations, limiting their applicability to large-scale datasets and low-resource languages such as Hausa. This study proposes a scalable extractive text summarisation model for Hausa language documents using K-Nearest Neighbours (KNN) and Sparse Matrix Representation to improve computational efficiency while preserving summary quality. The proposed approach preprocesses Hausa news articles through tokenisation, stop-word removal, and TF-IDF vectorisation, after which KNN identifies the nearest neighbouring sentences to construct a sparse similarity matrix. This reduces computational complexity from O(N²) to O(N log N) by eliminating unnecessary similarity computations while preserving the most informative sentence relationships for graph-based ranking. The proposed model was evaluated on a corpus of Hausa news articles and compared with a Graph Convolutional Network–Recurrent Neural Network (GCN– RNN) model using ROUGE-1, ROUGE-2, ROUGE-L, execution time, memory consumption, compression ratio, and computational complexity. Experimental results demonstrate that the proposed model completed summarisation in 32 s while consuming only 4.79 MB of memory, compared with 104 s and 112.96 MB for the GCN–RNN model, representing reductions of 69.23% in execution time and 95.76% in memory usage. It also achieved ROUGE-1, ROUGE-2, and ROUGE-L F1-scores of 85.36%, 75.64%, and 76.77%, respectively, outperforming the baseline while maintaining superior computational efficiency. These findings demonstrate that the proposed KNN with Sparse Matrix Representation provides an efficient, scalable, and practical framework for extractive text summarisation of Hausa language documents and offers a promising solution for other low-resource languages.
Keywords: Extractive Text Summarisation, Hausa Language, Natural Language Processing, K-Nearest Neighbours, Sparse Matrix Representation, TF-IDF, ROUGE Evaluation, Scalable Text Summarisation, Computational Efficiency.
Keywords: Extractive Text Summarisation, Hausa Language, Natural Language Processing, K-Nearest Neighbours, Sparse Matrix Representation, TF-IDF, ROUGE Evaluation, Scalable Text Summarisation, Computational Efficiency.
Abstract
Multi-Featured Smart Vehicle with Safety Monitoring using IoT
M. Ravi, Anup Mandal, G. Anirudh, H. Bhagya Shree, M. Shashank Yadav
DOI: 10.17148/IJARCCE.2026.15714
Abstract: Road traffic accidents remain one of the leading causes of preventable fatalities worldwide, primarily due to delayed hazard perception and delayed emergency response. This paper presents a Multi-Featured Smart Vehicle with Safety Monitoring using IoT, a low-cost, retrofit-capable embedded system that combines real-time obstacle avoidance, blind-spot monitoring, automatic accident detection and GPS-based emergency alerting on a single dual-core ESP32 platform. The system fuses data from an HC-SR04 ultrasonic sensor, two infrared proximity sensors, an MPU6050 accelerometer-gyroscope and a Neo-6M GPS module, and uses an RTOS-based dual-core scheduling strategy to guarantee that collision-avoidance logic is never delayed by network activity. On detecting a severe impact, the system autonomously halts the drive motors and broadcasts an SOS message containing a live Google-Maps location link over Bluetooth to a connected terminal, eliminating dependence on human intervention during the critical “golden hour” after a crash. Experimental evaluation of the prototype across repeated test trials shows a crash-detection accuracy of 96%, a forward-obstacle avoidance efficiency of 95%, a blind-spot alert reliability of 98%, and an average end-to-end SOS response time of 1.45 seconds. These results demonstrate that high-end vehicular safety features, traditionally restricted to expensive luxury vehicles, can be replicated at a fraction of the cost using accessible embedded hardware, making the proposed architecture suitable for retrofitting into economy and public-transport vehicles.
Keywords: Internet of Things (IoT), ESP32 Microcontroller, Accident Detection, Obstacle Avoidance, Blind-Spot Monitoring, GPS Tracking, Smart Vehicle Safety, RTOS.
Keywords: Internet of Things (IoT), ESP32 Microcontroller, Accident Detection, Obstacle Avoidance, Blind-Spot Monitoring, GPS Tracking, Smart Vehicle Safety, RTOS.
Abstract
DIY FIRE EXTINGUISHER DRONE USING IoT
Mrs. Laxmi Hugar, B. Kumaraswamy, D. Haasini, L. Divakar, M. Laxmi Bhavani
DOI: 10.17148/IJARCCE.2026.15715
Abstract: Fire accidents pose a serious threat to human life, property, and the environment, especially in industrial areas, forests, warehouses, and residential buildings. Traditional firefighting methods often expose firefighters to hazardous conditions and may result in delayed emergency response. This paper presents the design and development of a DIY Fire Extinguisher Drone, a low-cost unmanned aerial vehicle (UAV) designed to detect and suppress small-scale fires efficiently. The proposed system integrates an ESP32 microcontroller, flame sensor, smoke sensor, GPS module, camera module, relay-controlled water pump, and brushless DC motors to create an intelligent firefighting platform. Upon detecting fire, the drone identifies the affected area, activates the onboard extinguishing mechanism, and simultaneously transmits real-time video and GPS coordinates to the operator for effective monitoring and emergency response. The lightweight design, affordable hardware, and modular architecture make the system suitable for educational institutions, industries, and disaster management applications. Experimental evaluation demonstrates reliable fire detection, rapid response time, and effective suppression of controlled fire scenarios while reducing human involvement in dangerous environments.
The proposed DIY Fire Extinguisher Drone provides an economical, efficient, and scalable solution for enhancing firefighting operations and improving public safety through modern UAV technology.
Keywords: DIY Fire Extinguisher Drone, Unmanned Aerial Vehicle (UAV), ESP32, Fire Detection, Flame Sensor, Smoke Sensor, GPS, IoT, Emergency Response, Embedded Systems.
The proposed DIY Fire Extinguisher Drone provides an economical, efficient, and scalable solution for enhancing firefighting operations and improving public safety through modern UAV technology.
Keywords: DIY Fire Extinguisher Drone, Unmanned Aerial Vehicle (UAV), ESP32, Fire Detection, Flame Sensor, Smoke Sensor, GPS, IoT, Emergency Response, Embedded Systems.
Abstract
Smart Saline Monitoring and Alert System Using IoT
Rambabu Pemula, A. Athikah, B. Suraj, G. Koushik, P. Swaroop
DOI: 10.17148/IJARCCE.2026.15716
Abstract: Giving a patient IV saline is about as routine as hospital care gets, yet how that drip is tracked has barely changed in decades — a nurse still walks over and eyeballs the bottle. Drip rates are set by hand, and hand-set rates drift, so pinning down exactly when a bag will run dry is more guesswork than science. If nobody catches an empty bottle in time, the consequences are not trivial: blood can back up into the line, the line can become contaminated, or, worse, air can enter the vein and trigger an embolism.The moment fluid drops into the Low band, the system does more than flash a light. A buzzer sounds close to the patient, and a SIM900 GSM/GPRS module sends an SMS directly to the caretaker's phone over the cellular network — a channel that keeps working even when hospital Wi-Fi is congested or down entirely, so the message gets through regardless. To stop staff being bombarded with repeat alerts for a single event, the firmware relies on state flags that cap each threshold breach at exactly one notification.Cost was a deliberate design constraint: every part is a common, off-the-shelf component, and the total build comes in well under the price of a commercial infusion-monitoring pump, which makes the system a realistic option for hospitals and clinics working with tight budgets.
Keywords: Smart Saline Monitoring, Internet of Things, ESP32, Load Cell, HX711 Amplifier, GSM Alert System, IV Fluid Monitoring, Patient Safety, Embedded Healthcare System, Alarm Fatigue Reduction.
Keywords: Smart Saline Monitoring, Internet of Things, ESP32, Load Cell, HX711 Amplifier, GSM Alert System, IV Fluid Monitoring, Patient Safety, Embedded Healthcare System, Alarm Fatigue Reduction.
Abstract
THE INTELLIGENT CAR WITH ACCIDENT ALERT AND DRIVER ASSISTANCE SYSTEM
Mr. M . Ravi, Ch.Sohan, B.Aryan, M. Vaishnavi, B.Srinu
DOI: 10.17148/IJARCCE.2026.15717
Abstract: Road accidents Road accidents continue to be a major cause of injuries and fatalities worldwide due to driver negligence, poor visibility, and delayed obstacle detection. Traditional vehicle safety systems mainly focus on minimizing accident impact rather than preventing collisions. This paper presents an IoT Based Intelligent Car with Driver Assistance System, an intelligent and cost-effective solution developed using the ESP32 microcontroller, HC-SR04 ultrasonic sensor, SG90 servo motor, L298N motor driver, and the built-in Bluetooth of the ESP32. The ultrasonic sensor continuously scans the surroundings by rotating through the servo motor to detect nearby obstacles. Based on the measured distance, the ESP32 controls the vehicle to avoid collisions automatically. Users can also operate the vehicle manually through Bluetooth using a smartphone application. Experimental testing demonstrated reliable obstacle detection, smooth Bluetooth communication, and efficient autonomous navigation. The proposed system is affordable, portable, and suitable for educational, research, and intelligent transportation applications. By integrating embedded systems with IoT technology, the system enhances driver safety and contributes to the development of smart transportation.
Keywords: Internet of Things (IoT), ESP32, Intelligent Car, Driver Assistance System, Obstacle Avoidance, Ultrasonic Sensor, Bluetooth Control, Servo Motor, L298N Motor Driver, Embedded Systems.
Keywords: Internet of Things (IoT), ESP32, Intelligent Car, Driver Assistance System, Obstacle Avoidance, Ultrasonic Sensor, Bluetooth Control, Servo Motor, L298N Motor Driver, Embedded Systems.
Abstract
Artificial Intelligence for Antenna Design, Surrogate Modeling, And Optimization: A Review of Methods, Trends, And Open Challenges
Abinaya Sree R. J., Renisha G., Blessy S.
DOI: 10.17148/IJARCCE.2026.15718
Abstract: The increasing complexity of modern wireless communication systems has significantly transformed the antenna design process. Conventional antenna development primarily relies on full-wave electromagnetic (EM) simulations combined with iterative optimization techniques. Although these methods provide accurate results, they often require extensive computational time, particularly when dealing with multi-parameter, multi-objective, or broadband antenna structures. In recent years, artificial intelligence (AI) has emerged as a promising alternative for accelerating antenna analysis and design. Machine learning (ML), deep learning (DL), surrogate modeling, inverse design, and generative approaches have demonstrated the ability to predict antenna performance with considerably fewer electromagnetic simulations while maintaining satisfactory accuracy. This review presents a comprehensive analysis of recent research on AI-assisted antenna design, covering studies involving microstrip patch antennas, ultra-wideband (UWB) antennas, antenna arrays, metasurfaces, horn antennas, and reconfigurable antenna structures. The reviewed literature is organized according to major AI methodologies, including classical machine learning algorithms, deep learning architectures, surrogate modeling techniques, inverse design frameworks, and hybrid optimization approaches. Their advantages, limitations, and practical applications are critically discussed and compared. Furthermore, this review identifies several challenges that continue to limit the widespread adoption of AI-driven antenna design, including the absence of standardized benchmark datasets, inconsistent reporting of computational efficiency, limited experimental validation, and the difficulty of developing generalized models that can perform well across multiple antenna topologies. Finally, potential research directions such as physics-informed learning, transfer learning, generative artificial intelligence, digital twins, and automated antenna design frameworks are highlighted. The objective of this review is to provide researchers and engineers with a structured overview of current developments while identifying opportunities for future advancements in intelligent antenna design.
Keywords: Artificial Intelligence; Machine Learning; Deep Learning; Antenna Design; Surrogate Modeling; Inverse Design; Antenna Optimization; Electromagnetic Simulation; Metasurfaces; Wireless Communication
Keywords: Artificial Intelligence; Machine Learning; Deep Learning; Antenna Design; Surrogate Modeling; Inverse Design; Antenna Optimization; Electromagnetic Simulation; Metasurfaces; Wireless Communication
Abstract
IoT-Based Smart Pothole Detection And Alert System
K.SanthiPriya, T.Vivekananda, V.Akhila, MD.Saniya, MohammedTalhaFarooqui
DOI: 10.17148/IJARCCE.2026.15719
Abstract: Poor road conditions, especially potholes and damaged road surfaces, are a major cause of traffic accidents, vehicle damage, increased travel time, and higher maintenance costs. In many regions, road inspections are still carried out manually, making the process time-consuming, expensive, and often incapable of identifying road damage in real time. This paper presents an IoT-Based Smart Pothole Detection and Alert System designed to automate pothole detection and provide instant location-based reporting using low-cost embedded hardware. The proposed system is built around an ESP32 microcontroller, which continuously monitors road surface conditions using a VL53L3CX Time-of-Flight (ToF) sensor. Whenever a significant increase in the measured distance indicates the presence of a pothole, the ESP32 processes the sensor data, activates a buzzer to indicate successful detection, and acquires the geographical coordinates of the damaged road using a Neo-6M GPS module. The collected information, including the pothole status, latitude, longitude, and detection time, is transmitted through the ESP32's built-in Wi-Fi module to the ThingSpeak cloud platform, where it can be monitored remotely through an online dashboard. This enables road maintenance authorities to identify damaged road locations quickly, monitor road conditions in real time, and prioritize repair work more efficiently. A working prototype of the proposed system was developed and experimentally tested under different road conditions. The results demonstrated reliable pothole detection, accurate GPS location tracking, and near real-time cloud data transmission with low processing latency. Overall, the proposed system demonstrates that a simple, portable, and cost-effective combination of embedded sensors, GPS technology, wireless communication, and cloud computing can significantly improve road monitoring, enhance transportation safety, reduce vehicle damage, and contribute to the development of intelligent transportation systems and smart city infrastructure.
Keywords: Internet of Things (IoT), ESP32, Smart Pothole Detection, Vibration Sensor, GPS Tracking, Thing Speak, Road Condition Monitoring, Smart Transportation, Cloud Computing, Intelligent Road Infrastructure.
Keywords: Internet of Things (IoT), ESP32, Smart Pothole Detection, Vibration Sensor, GPS Tracking, Thing Speak, Road Condition Monitoring, Smart Transportation, Cloud Computing, Intelligent Road Infrastructure.
Abstract
A Comparative Study of Conversational AI
Tools: ChatGPT, Claude, and Gemini in, Dr.P.Bharathisindhu
DOI: 10.17148/IJARCCE.2026.15720
Abstract: The rapid advancement of large language models (LLMs) has led to the emergence of a few leading conversational AI platforms, with OpenAI's ChatGPT, Anthropic's Claude, and Google's Gemini being the most widely used. This paper provides a comprehensive comparison of these three AI tools by reviewing existing research, benchmark studies, and expert evaluations. The comparison focuses on key aspects such as coding performance, writing quality, context understanding, multimodal capabilities, ecosystem integration, and pricing.The analysis shows that all three platforms deliver high-quality performance, with only minor differences in their overall capabilities. Their strengths, however, vary depending on the intended application. Claude demonstrates excellent performance in coding tasks and produces well-structured, natural writing. ChatGPT stands out for its extensive ecosystem, flexibility, and strong multimodal features, making it suitable for a wide range of professional and educational applications. Gemini excels in multimodal understanding and integrates seamlessly with Google's productivity tools, making it particularly useful for users already working within the Google ecosystem.The study concludes that there is no single AI platform that is universally superior. Instead, the most suitable choice depends on the user's specific requirements and workflow. As a result, many professionals and organizations are increasingly adopting multiple AI platforms to leverage the unique strengths of each.
Keywords: Artificial Intelligence, Large Language Models, ChatGPT, Claude, Gemini, Comparative Analysis, Conversational AI, Benchmarking.
Keywords: Artificial Intelligence, Large Language Models, ChatGPT, Claude, Gemini, Comparative Analysis, Conversational AI, Benchmarking.
Abstract
An Empirical Assessment of Machine Learning Algorithms for Predicting Heart Disease
Dr. Anureet Kaur
DOI: 10.17148/IJARCCE.2026.15721
Abstract: Cardiovascular disorders remain a primary cause of mortality worldwide, emphasizing the urgent need for early diagnostic support systems. Machine learning (ML) techniques have emerged as promising tools for assisting clinical decision-making through data-driven prediction models. This study presents a comprehensive empirical evaluation of several supervised learning algorithms for heart disease prediction using structured clinical data. The performance of Logistic Regression, Support Vector Machine, k-Nearest Neighbours, Decision Tree, Random Forest, Gradient Boosting, and Artificial Neural Networks is systematically compared. Models are assessed using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The results of the study show that the k-Nearest Neighbours algorithm achieved the best overall performance with the highest accuracy and balanced evaluation metrics. The Support Vector Machine model also showed strong and consistent performance across different validation folds. Other models such as Logistic Regression and Random Forest produced competitive results, while Decision Tree and Gradient Boosting showed comparatively lower performance. Overall, the results demonstrate that machine learning techniques can be effective tools for predicting heart disease and can help support early diagnosis. In the future, the performance of these models could be improved by using larger datasets and applying advanced feature selection or optimization techniques. These findings demonstrate that machine learning techniques can be useful for supporting early detection of heart disease and assisting healthcare professionals in decision-making.
Keywords: Cardiovascular Disease, Predictive Modelling, Healthcare Analytics, Artificial Intelligence, Machine Learning.
Keywords: Cardiovascular Disease, Predictive Modelling, Healthcare Analytics, Artificial Intelligence, Machine Learning.
Abstract
Question Paper Generator
S Tharani, Dr. Nagaveni Biradar
DOI: 10.17148/IJARCCE.2026.15722
Abstract: The Question Paper Generator is a web-based application developed using Python, Flask, SQLite, HTML, CSS, and Report Lab. The system automates the process of generating university-style question papers by selecting questions from a database based on the chosen subject and module. It reduces the manual effort involved in preparing examination papers and minimizes repetition of questions. The administrator can add, edit, update, and delete questions through an admin panel. The generated question paper is exported as a PDF with proper formatting, including college details, subject information, page numbers, and question numbering. The system improves efficiency, accuracy, and confidentiality in examination management.
Abstract
Quantum-Enhanced Intrusion Detection Systems for IoT Networks: Trends, Challenges, and Future Directions
Sivasubramanyam Medasani, M Neavruth Sai, Jhanavi C, Lakshmi B
DOI: 10.17148/IJARCCE.2026.15723
Abstract: This survey examines quantum-enhanced machine learning techniques for intrusion detection in Internet of Things (IoT) and fog environments, synthesizing recent work on hybrid quantum-classical models, quantum convolutional neural networks (QCNNs), quantum support vector machines (QSVMs), and quantum-assisted clustering. We review five recent primary studies that apply quantum methods to IoT security, summarize their methodological choices (encoding, circuit ansatz, classical-quantum interfaces), and evaluate reported benefits and limitations with respect to accuracy, computational cost, and deployability in resource-constrained settings. The literature indicates potential gains in feature expressivity and false-negative reduction from quantum encodings and variational circuits, but practical barriers remain: limited qubit counts, noisy hardware, encoding overhead, and scarce real-world deployment studies. We identify concrete research gaps and propose directions for lightweight encodings, noise-aware hybrid architectures, federated quantum-assisted Intrusion Detection System (IDS), and standardized benchmarks for reproducible evaluation. The survey aims to guide researchers and practitioners toward scalable, explainable, and deployable quantum-enhanced intrusion detection for IoT.
Keywords: Internet of Things, Intrusion Detection System, Quantum Machine Learning, Quantum Convolutional Neural Network, Quantum Support Vector Machine, Quantum K-Means, Hybrid Quantum Neural Network.
Keywords: Internet of Things, Intrusion Detection System, Quantum Machine Learning, Quantum Convolutional Neural Network, Quantum Support Vector Machine, Quantum K-Means, Hybrid Quantum Neural Network.
Abstract
Quantum Key Distribution for Secure IoT Communication: Recent Advances, Challenges, and Future Perspectives
Sivasubramanyam Medasani, Akhil Goutham K, Bhaskar S, H Vishnu
DOI: 10.17148/IJARCCE.2026.15724
Abstract: The rapid proliferation of Internet of Things devices (IoT) across healthcare, smart homes, transportation, and industrial automation has led to an unprecedented exchange of sensitive data over wireless channels, exposing these networks to cyberattacks, eavesdropping, and unauthorized access. Conventional cryptographic techniques, which rely on computational hardness assumptions, are increasingly vulnerable to the emerging capabilities of quantum computing. This paper explores the application of Quantum Key Distribution (QKD) as a means of enabling secure and dependable data communication for IoT devices. By exploiting the fundamental principles of quantum mechanics, QKD allows two communicating parties to generate a shared secret key while inherently detecting any attempt at interception. The proposed approach aims to enhance data privacy, ensure secure authentication, preserve confidentiality, and safeguard IoT systems against present and future quantum enabled threats. The integration of quantum based security techniques into existing IoT infrastructure is examined, along with its implications for improving the reliability and trustworthiness of wireless IoT communication systems. This work positions Quantum Enhanced Secure Data Communication as a forward looking security solution for next generation IoT networks.
Keywords: Quantum Key Distribution, Internet of Things, Quantum Internet of Things, Post Quantum Cryptography, BB84 protocol, Quantum Cryptography Framework.
Keywords: Quantum Key Distribution, Internet of Things, Quantum Internet of Things, Post Quantum Cryptography, BB84 protocol, Quantum Cryptography Framework.
Abstract
AI-Based Plagiarism Detection System Using Deep Learning and LLMs
Anitha J, Swathi, Vinanya V
DOI: 10.17148/IJARCCE.2026.15725
Abstract: Generative AI is shaking up how we think about academic honesty and professional integrity—and not always in a good way. Most old plagiarism checkers aren’t up to the task anymore. They catch copy-paste or obvious paraphrasing, but miss the tricky stuff: clever rewording, translations, or anything cooked up by modern AI tools. Add in all the weird formats—images, messy PDFs—and things get even more complicated. PlagiGuard AI bridges this gap. Instead of relying on a collection of different tools, it uses deep learning and large language models to spot when the meaning’s been stolen, not just the wording. It can even flag when AI wrote the text. You just upload your files—PDFs, Word docs, images—and PlagiGuard pulls out the content, compares it locally and online, and gives you a straight-up risk report. You’ll see which sentences are copied, paraphrased, or machine-generated. The architecture’s built for speed, security, and scale, handling more than twenty languages with no sweat.
Keywords: Artificial Intelligence, Plagiarism Detection, AI Content Detection, Natural Language Processing (NLP), Optical Character Recognition (OCR), FastAPI, React.js, Python, Supabase, Machine Learning, Document Analysis, Text-to-Speech, PDF Report Generation, Academic Integrity.
Keywords: Artificial Intelligence, Plagiarism Detection, AI Content Detection, Natural Language Processing (NLP), Optical Character Recognition (OCR), FastAPI, React.js, Python, Supabase, Machine Learning, Document Analysis, Text-to-Speech, PDF Report Generation, Academic Integrity.
Abstract
Code Generation and Debugging Assistant using Deep Learning and Large Language Models
Nikhitha H S, Priyarani Suramanji, Dr Indumathi S K
DOI: 10.17148/IJARCCE.2026.15726
Abstract: Novice programmers frequently struggle to translate cryptic compiler diagnostics into actionable understanding, while contemporary generative Artificial Intelligence (AI) assistants optimized for professional productivity tend to resolve reported errors by supplying complete corrected code immediately. This mode of instant resolution, though efficient for experienced developers, is pedagogically counterproductive for learners, as it discourages active engagement with the debugging process. This paper presents CodeMentor AI, a full-stack hybrid web application combining a locally hosted statistical Machine Learning (ML) pipeline with a cloud based Large Language Model (LLM) to deliver both rapid error triage and structured, Socratic-style tutoring. The FastAPI backend integrates a TF-IDF vectorizer with a Logistic Regression classifier for baseline error category prediction, and a cosine-similarity Nearest Neighbors model for code retrieval, with the Groq-hosted openai/gpt oss 120b LLM used for explanation, progressive hinting, and solution verification.The React frontend provides an integrated Monaco-based workspace, a three-tier Learning Mode hint system, and an administrative analytics dashboard with Firebase Authentication and a Supabase (PostgreSQL) backend for persistence. This paper documents the system's architecture, module design, and AI pipeline as implemented, and situates it within recent literature on AI-assisted programming education, retrieval-augmented debugging, and comparative studies of commercial AI coding tools. Formal empirical evaluation of learning outcomes and system accuracy has not yet been conducted and is identified as future work.
Keywords: Artificial Intelligence in Education, Large Language Models, Retrieval Augmented Generation, Programming Tutoring Systems, Automated Debugging, Hybrid Machine Learning, FastAPI, React, Supabase, Socratic Scaffolding
Keywords: Artificial Intelligence in Education, Large Language Models, Retrieval Augmented Generation, Programming Tutoring Systems, Automated Debugging, Hybrid Machine Learning, FastAPI, React, Supabase, Socratic Scaffolding
Abstract
Advanced time frequency approaches in SMOTFS and OTFS for wireless system
R. Prethesha and I. Muthumani
DOI: 10.17148/IJARCCE.2026.15727
Abstract: The fifth generation (5G) mobile communication system is looking forward to achieving much better spectral efficiency, higher mobility, and lower end-to-end latency in comparison with the fourth-generation (4G) system. To deal with the influence of the fast time-varying wireless mobile channels, orthogonal time frequency space (OTFS) modulation has been proposed. Orthogonal Time Frequency Space (OTFS) is a 2dimensional (2D) modulation technique designed in the delay-doppler domain which has the strong doppler-resilience over doubly selective channels and SM-OTFS system by the joint design of SM and OTFS modulation and to achieve the improved spectral efficiency and enhanced transmission reliability of the OTFS system when compared to OFDM and OTFS.
Keywords: Orthogonal Time Frequency Space (OTFS), Delay Doppler, spatial modulation-OTFS (SM-OTFS), Orthogonal Frequency Division Multiplexing (OFDM), Sixth generation(6G), Delay doppler domain (DD domain), Time frequency domain (TF domain)
Keywords: Orthogonal Time Frequency Space (OTFS), Delay Doppler, spatial modulation-OTFS (SM-OTFS), Orthogonal Frequency Division Multiplexing (OFDM), Sixth generation(6G), Delay doppler domain (DD domain), Time frequency domain (TF domain)
Abstract
An IoT-Based Smart Umbrella for Weather Awareness, Renewable Energy Harvesting, and Emergency Location Tracking
Dr. Manu M N, Prof. Prarthana J V, Prof. Gayathri S
DOI: 10.17148/IJARCCE.2026.15728
Abstract: The Internet of Things (IoT) is a transformative technology that connects physical devices, sensors, and software to exchange data over the internet. It enables automation, realtime monitoring, and intelligent decision- making across various industries, including healthcare, transportation, agriculture, and smart homes. IoT enhances efficiency, reduces operational costs, and improves user experiences by enabling seamless communication between devices. Key components include sensors, cloud computing, artificial intelligence, and wireless networks. Despite its benefits, IoT poses challenges related to security, data privacy, and scalability. As technology advances, IoT continues to evolve, shaping the future of smart cities, industries, and daily life. The project is making of a "IOT based smart umbrella" with humidity sensors which will notify you the temperature & the umbrella being solar panel embedded by which u can charge your phone on the go and with GPS module being Attached the current location of the umbrella can be tracked anytime needed using IOT technology the gps tracker can result as a life saver in emergency situation, The loT-based Smart Umbrella Arduino project is a novel and innovative solution that combines the Internet of Things (loT) technology with an umbrella to enhance its functionality and provide various smart features. The project utilizes Arduino, a popular opensource electronics platform, to create a connected umbrella that can interact with its environment, gather data, and perform automated actions.
Keywords: Internet of Things (IoT), Smart Umbrella, Arduino, Humidity Sensor, Temperature Monitoring, Solar- Powered Charging, GPS Tracking, Real-Time Location Tracking, Embedded Systems, Wireless Communication, Environmental Monitoring, Renewable Energy, Mobile Charging, Smart Devices, Automation, Cloud Connectivity, Emergency Assistance, Sustainable Technology, Sensor Networks, Internet-Connected Systems.
Keywords: Internet of Things (IoT), Smart Umbrella, Arduino, Humidity Sensor, Temperature Monitoring, Solar- Powered Charging, GPS Tracking, Real-Time Location Tracking, Embedded Systems, Wireless Communication, Environmental Monitoring, Renewable Energy, Mobile Charging, Smart Devices, Automation, Cloud Connectivity, Emergency Assistance, Sustainable Technology, Sensor Networks, Internet-Connected Systems.
Abstract
Smart IDS: Reducing False Alarms in Real-Time and Live Network Intrusion Detection Using Machine Learning
Kusumuru Mounika, Mandakuriti Sai Charan, Pyla Jyothi, Mukkera Akhil, Kindal Ashok Kumar
DOI: 10.17148/IJARCCE.2026.15729
Abstract: Smart Intrusion Detection System (IDS) plays a vital role in recognizing network malicious activities in the present network environment. The traditional signature-based methods are usually ineffective towards detecting zero- day and new cyber threats. This paper has presented SMART IDS, as a machine learning based intrusion detection system that attempts to minimize the false alarms and preserve the detection accuracy of the system in both simulated and real network environments. The system is running in simulation mode whereby the CICIDS2017 dataset is used to train and test the model and live capture mode whereby real time packet analysis is performed. An extensive preprocessing pipeline is used. This involves cleaning of data, selection of features, encoding and standardization to provide an assuring model performance. A variety of machine learning models are utilized and considered: Decision Tree, Random Forest, XGBoost, and Logistic Regression. To improve the detection capability, a custom weighted ensemble method is suggested. It has an attack override feature, which puts the emphasis on threat detection and minimizes false negatives. In the experimental area, the accuracy of the Random Forest model is high (99.86). At the same time, the ensemble approach enhances recall and reduces the number of missed attacks as compared to the single models. Real-time packet capture, which is added with the help of PyShark, and deployment with a Flask-based API make the system applicable to dynamic network environments. The SMART IDS is a scaled, adaptable, and efficient framework, which could be applied to handle the cybersecurity reality in contemporary times. It uses machine learning methods with real-time analysis, which greatly improves the performance of intrusion detection and decreases the number of false alarms.
Keywords: Cybersecurity, Intrusion Detection System, Machine Learning, Network Security, Real-Time Detection
Keywords: Cybersecurity, Intrusion Detection System, Machine Learning, Network Security, Real-Time Detection
Abstract
A Hybrid Self-Supervised Denoising and Attention-Guided Segmentation Framework for Robust Medical Image Analysis
Swarna N
DOI: 10.17148/IJARCCE.2026.15730
Abstract: Medical image analysis plays a fundamental role in modern clinical diagnosis and treatment planning. However, the presence of acquisition noise, low contrast, and indistinct anatomical boundaries often degrades image quality, thereby reducing the reliability of automated image analysis systems. Conventional denoising techniques are effective in suppressing noise but frequently compromise fine structural details that are essential for accurate medical interpretation. Similarly, segmentation models trained on degraded images often struggle to identify complex anatomical structures and pathological regions with high precision. To address these challenges, this paper proposes a hybrid medical image processing framework that integrates a self-supervised image denoising network with an attention-guided U-Net segmentation architecture. The denoising stage is designed to remove noise while preserving structural information and edge continuity, producing high-quality intermediate representations for subsequent analysis. The restored images are then processed by an attention-enhanced segmentation network that selectively focuses on diagnostically significant regions while suppressing irrelevant background features. This integrated strategy improves the interaction between image restoration and segmentation, leading to enhanced robustness under challenging imaging conditions. The effectiveness of the proposed framework is evaluated using widely accepted quantitative metrics, including Peak Signal- to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Mean Squared Error (MSE), Dice Similarity Coefficient (DSC), and Intersection over Union (IoU). The proposed methodology provides a scalable and reproducible solution for medical image enhancement and segmentation and offers potential applicability across multiple imaging modalities, including Magnetic Resonance Imaging (MRI), Computed Tomography (CT), ultrasound, and chest X-ray imaging.
Keywords: Medical image processing, image denoising, semantic segmentation, attention-guided U-Net, self- supervised learning, deep learning, structural similarity, Dice similarity coefficient, PSNR, IoU, MRI image analysis, CT image segmentation.
Keywords: Medical image processing, image denoising, semantic segmentation, attention-guided U-Net, self- supervised learning, deep learning, structural similarity, Dice similarity coefficient, PSNR, IoU, MRI image analysis, CT image segmentation.
Abstract
PERIPHERAL ARTERIAL DISEASE DETECTION USING MACHINE LEARNING
Ayesha Sayed, Ayishath Raheesha, Isha M Bhandary, Ishita P Acharya, Ms. Shwetha Kamath
DOI: 10.17148/IJARCCE.2026.15731
Abstract: Peripheral Arterial Disease (PAD) is a serious vascular condition that is often underdiagnosed due to reliance on manual interpretation of Doppler ultrasound reports. Early detection is critical to prevent complications such as critical limb ischemia and amputation. This study presents an automated PAD detection system that integrates Optical Character Recognition (OCR) with machine learning to analyze Color Doppler reports. The system extracts key clinical parameters, including the Ankle-Brachial Index (ABI), using text parsing techniques from reports in PDF and image formats. A hybrid decision framework combining a Random Forest classifier with rule-based clinical logic is employed to determine PAD presence and severity. A clinical override rule ensures that PAD is flagged when ABI ≤ 0.90, improving diagnostic reliability. To address class imbalance, Synthetic Minority Oversampling Technique (SMOTE) is applied, resulting in improved accuracy, precision, recall, and F1-score. The proposed system reduces manual effort, enhances diagnostic consistency, and enables real-time clinical decision support, making it suitable for practical healthcare applications.
Keywords: Peripheral Arterial Disease (PAD), Machine Learning, Optical Character Recognition (OCR), Random Forest, Ankle-Brachial Index (ABI), SMOTE, Healthcare Automation, Doppler Report Analysis.
Keywords: Peripheral Arterial Disease (PAD), Machine Learning, Optical Character Recognition (OCR), Random Forest, Ankle-Brachial Index (ABI), SMOTE, Healthcare Automation, Doppler Report Analysis.
Abstract
Hyperloop: Revolutionizing Modern Transportation
Vishwa Tigari, Yashwanth V, Yogesh K N, Prof. Anitha J
DOI: 10.17148/IJARCCE.2026.15732
Abstract: Conventional modes of transportation — rail, road, water, and air — tend to be either relatively slow, expensive, or both, and each carries its own footprint of congestion, emissions, and infrastructure cost. Hyperloop is a proposed mode of transport that seeks to overcome this long-standing trade-off by moving people and goods at very high speed inside a sealed, low-pressure tube while the transport pod is magnetically levitated above the guideway. Because the tube is maintained at low pressure, aerodynamic drag is drastically reduced, which in turn lowers the energy required to sustain high velocity. This paper reviews the origins and operating principle of Hyperloop, surveys prior literature on its design, and explains the construction and working of the core subsystems — the tube, capsule, compressor, suspension, and propulsion. It further discusses potential applications, compares Hyperloop against existing modes of transport on the dimensions of speed, cost, and environmental impact, and examines the safety and engineering challenges that must be resolved before commercial deployment. A proposed constructional model addressing the Kantrowitz limit and levitation is presented, along with a summary of advantages, limitations, and directions for future enhancement.
Keywords: Hyperloop, Pod, Magnetic Levitation, Linear Induction Motor, Kantrowitz Limit, Vacuum Tube Transportation, High-Speed Transit
Keywords: Hyperloop, Pod, Magnetic Levitation, Linear Induction Motor, Kantrowitz Limit, Vacuum Tube Transportation, High-Speed Transit
Abstract
Electronic Voting System Using Web Technology
Anusha S M, Kumar Siddamallappa U, Shreedevi Prakash Gotur
DOI: 10.17148/IJARCCE.2026.15733
Abstract: Electronic voting (E-voting) systems have become an essential part of modern democratic processes due to their ability to provide secure, efficient, and transparent elections. Traditional paper-based voting systems suffer from issues such as long waiting times, ballot tampering, human errors, and delayed result processing. This research proposes a secure E-voting system using web technologies integrated with biometric verification techniques. The proposed system employs web frameworks, databases, image processing, and facial recognition to authenticate voters and ensure that only authorized users participate in the election process. The system architecture consists of voter registration, authentication, vote casting, result computation, and administrative management modules. Image preprocessing and feature extraction techniques are used to improve voter verification accuracy. Experimental results demonstrate that the proposed model achieves high accuracy, enhanced security, and faster vote counting while maintaining voter privacy and election integrity.
Keywords: E-voting, Web Technology, Biometric Authentication, Face Recognition, Image Processing.
Keywords: E-voting, Web Technology, Biometric Authentication, Face Recognition, Image Processing.