https://matjournals.net/engineering/index.php/JIBDSN/issue/feedJournal of IoT-based Distributed Sensor Networks2024-12-13T05:18:29+00:00Open Journal Systems<p><strong>JIBDSN</strong> is a peer reviewed journal in the discipline of Computer Science published by the MAT Journals Pvt. Ltd. It is a print and e-journal focused towards the rapid publication of fundamental research papers on all areas of IoT-based Distributed Sensor Networks. The Journal aims to promote high quality empirical Research, Review articles, case studies and short communications mainly focused on sensor networks, Sensor Network Tasking and Self-Organization, Distributed Sensor Networks , Networking / Caching Issues, Sensor Networks for Internet of Things (IoT), Architecture, Algorithms, and Complexity Issues,Information Fusion Methodologies Based on Statistical Decision Theory, Distributed Detection / Classification Methods,Learning Patterns from Distributed Sensor Sources, Coordination, Integration, and Synchronization in Distributed Sensor Networks</p>https://matjournals.net/engineering/index.php/JIBDSN/article/view/977Wireless Wheelchair Automation via Mobile Devices2024-09-27T08:26:05+00:00Mohammad Qais Yunus Shaikhdattatray.takale@viit.ac.inRupali A. Mahajandattatray.takale@viit.ac.inDattatray G. Takaledattatraygtakale1@gmail.com<p>The evolution of wheelchair technology has been transformative for millions facing mobility challenges, enhancing their quality of life and promoting independence. Traditional manual wheelchairs often require assistance from another person, significantly restricting the user's autonomy. Recognizing the need for more independence, this paper introduces an innovative approach to electric wheelchairs by integrating Bluetooth-based mobile application control. This system is designed to empower users by allowing them to control their wheelchairs remotely through a smartphone app, eliminating the need for physical assistance. Our proposed system comprises essential components, including electric motors, rechargeable batteries, an Arduino Uno microcontroller, a motor driver, and a Bluetooth module. The integration of these components allows for seamless communication between the mobile app and the wheelchair, enabling precise and effortless control. The mobile application is a user-friendly interface that allows users to navigate the wheelchair with simple commands, offering a convenient and accessible solution for those with mobility impairments. Experimental results from our study demonstrate the system's reliability and effectiveness, showcasing smooth manoeuvrability and responsive control through the app. This innovative approach to wheelchair mobility not only enhances the physical independence of individuals with disabilities but also fosters a sense of empowerment and self-sufficiency. By integrating modern technology with everyday mobility aids, our system marks a significant leap forward in wheelchair design, promising a future where mobility challenges are met with intelligent, user-centric solutions. This advancement represents a pivotal step toward improving the quality of life for millions who rely on wheelchairs for daily activities.</p>2024-09-27T00:00:00+00:00Copyright (c) 2024 Journal of IoT-based Distributed Sensor Networkshttps://matjournals.net/engineering/index.php/JIBDSN/article/view/1029Advanced Intelligent Bus Tracking System Technology2024-10-18T10:51:54+00:00Atharv Sabalesuzkhan135@gmail.comAtharv Bakaresuzkhan135@gmail.comSufiyan Khansuzkhan135@gmail.comSanket Bavdhanesuzkhan135@gmail.comUtkarsh Yadavsuzkhan135@gmail.comS. V. Balshetwarsuzkhan135@gmail.com<p>Ensuring student transportation is safe and efficient is essential for schools, yet many face significant challenges due to the absence of real-time bus tracking systems. This project introduces an innovative and affordable solution utilizing the ESP32 microcontroller and a GPS module to develop a comprehensive real-time school bus tracking system. The system comprises two critical components: a hardware module installed in each bus to collect GPS data and a user-friendly interface accessible to stakeholders via web or mobile platforms. The ESP32, known for its low cost and energy efficiency, works seamlessly with the GPS module to provide accurate and timely location tracking.</p> <p>The collected GPS data is transmitted to a central server and made available to school administrators, transportation staff, and parents in real-time, fostering transparency and communication. This system is designed to enhance safety by allowing parents to monitor their children's bus locations and improve operational efficiency through more effective route planning. By providing real-time updates, the system minimizes the uncertainty often associated with student transportation, enabling quicker responses to delays or emergencies. Ultimately, this project aims to revolutionize school transportation management, ensuring students can travel safely and efficiently while giving parents peace of mind and allowing schools to optimize their transportation resources. With the integration of technology into school transport systems, we can create a more secure and streamlined experience for all involved.</p>2024-10-18T00:00:00+00:00Copyright (c) 2024 Journal of IoT-based Distributed Sensor Networkshttps://matjournals.net/engineering/index.php/JIBDSN/article/view/1084Dynamic Facial Analysis: A Comparative Study of CNN, Haar Cascade, YOLO, SSD, and M TCNN Models for Age, Emotion, Gender, and Ethnicity Classification2024-11-08T11:48:55+00:00Aarth Anant Dahaleaarthdahale007@gmail.comNishtha Sapdhare1032211053@mitwpu.edu.inJanhavi Rathor1032211053@mitwpu.edu.inSahil Jain1032211053@mitwpu.edu.inPrashant Lahane1032211053@mitwpu.edu.in<p>Dynamic facial analysis has emerged as a critical area of research, with applications spanning security, marketing, and healthcare. This study investigates the classification of age, emotion, gender, and ethnicity using advanced machine-learning techniques. We implemented a comprehensive approach that involved feature extraction through Convolutional Neural Networks (CNNs) followed by facial detection and analysis using various models, including Haar Cascade, You Only Look Once (YOLO), Single Shot Detector (SSD), and Multi-task Cascaded Convolutional Networks (MTCNN).</p> <p>Our research utilized a diverse dataset comprising thousands of facial images, enabling robust training and evaluation of the models. The performance of each model was assessed based on accuracy in classifying the four attributes. Results indicated significant variations in classification performance, highlighting the strengths and weaknesses of each model. For instance, while YOLO and SSD demonstrated superior speed and efficiency in real-time applications, CNN-based approaches offered higher accuracy in emotion classification. Conversely, Haar Cascade is effective for face detection and showed limitations in nuanced attribute classification.</p> <p>The findings emphasize the importance of model selection based on specific application requirements in dynamic facial analysis. This study contributes to the ongoing discourse by providing insights into the comparative effectiveness of various facial analysis models, paving the way for future advancements in automated facial recognition technologies.</p>2024-11-08T00:00:00+00:00Copyright (c) 2024 Journal of IoT-based Distributed Sensor Networkshttps://matjournals.net/engineering/index.php/JIBDSN/article/view/1098Machine Learning and AI in IoT-Based Sensor Networks2024-11-16T08:18:32+00:00Pragya Rajvanshipragya.aeron2@gmail.com<p>The integration of Machine Learning (ML) and Artificial Intelligence (AI) into Internet of Things (IoT) sensor networks is revolutionizing the management and utilization of sensor-generated data. As IoT networks expand and generate increasingly vast volumes of data, the need for sophisticated And effective methods to handle and understand this data is growing. This paper delves into how ML and AI enhance IoT sensor networks, emphasizing their diverse applications, benefits, challenges, and potential future developments. It provides a comprehensive overview of various ML and AI methodologies, including supervised learning, which is used for anomaly detection and predictive modeling; unsupervised learning, which is crucial for pattern recognition and data clustering; reinforcement learning, which optimizes decision-making processes through dynamic feedback; and deep learning, which excels in handling unstructured data such as images and text. The paper illustrates these techniques' significant contributions to improving data analysis accuracy, predictive capabilities, and autonomous decision-making within IoT environments by analyzing these techniques. Furthermore, it discusses ongoing challenges and potential future directions for integrating ML and AI with IoT networks to achieve more intelligent, responsive, and efficient systems.</p>2024-11-16T00:00:00+00:00Copyright (c) 2024 Journal of IoT-based Distributed Sensor Networkshttps://matjournals.net/engineering/index.php/JIBDSN/article/view/1183Edge Computing for Real-Time Data Processing in IoT Sensor Networks2024-12-13T05:18:29+00:00Vinay Kumar SinghVinay.31700@lpu.co.in<p>By enabling connectivity between devices, sensors, and systems and enabling real-time decision-making, the Internet of Things (IoT) has drastically changed several industries. However, there are issues with latency, bandwidth usage, and data processing efficiency due to the massive amount of data produced by IoT devices. By enabling real-time data processing at the network's edge and lowering dependency on centralized cloud services, edge computing which moves computation and storage closer to the data source offers a viable answer to these problems. This paper explores the role of edge computing in enhancing the performance of IoT sensor networks by addressing issues such as latency, bandwidth optimization, and real-time data analysis. Many industries have seen significant change due to the Internet of Things (IoT), which enables connectivity between devices, sensors, and systems and real-time decision-making. However, because of the enormous volume of data generated by IoT devices, there are problems with latency, bandwidth consumption, and data processing efficiency. Edge computing, which shifts computation and storage closer to the data source, provides a workable solution to these issues by enabling real-time data processing at the network's edge and reducing reliance on centralized cloud services.</p>2024-12-13T00:00:00+00:00Copyright (c) 2024 Journal of IoT-based Distributed Sensor Networks