Journal of IoT-based Distributed Sensor Networks (e-ISSN: 3048-9202)

Smart Healthcare Systems Using IoT and Machine Learning for Early Disease Detection

S.V. Jagtap, Rumaysa K. Yadwad, Aqsa V. Pathan — Fri, 23 Jan 2026 00:00:00 +0000

Healthcare is swiftly moving from medical institution-targeted treatment in the direction of continuous, technology-pushed care. This study presents a smart healthcare framework that integrates Internet of Things (IoT) sensing with machine learning–based analytics to enable continuous monitoring and early disease detection. Wearable and ambient sensors gather actual-time physiological indicators such as coronary heart rate, oxygen saturation, temperature, and interest conduct. The captured statistics is securely transmitted to cloud or side structures, wherein learning fashions examine patterns, perceive unusual deviations, and are expecting potential health dangers earlier than they emerge as clinically vital. The device pursuits to move healthcare from reactive analysis to proactive prevention. It supports timely alerts, faraway monitoring, personalized insights, and decreased dependence on frequent medical institution visits, in the end improving patient consolation and scientific selection-making. Experimental assessment indicates that gadget mastering fashions can efficiently understand subtle physiological changes and generate significant predictions, even in complex and noisy environments. No matter its promise, the framework also highlights challenges consisting of facts privacy, interoperability, sensor reliability, and huge-scale deployment. Making sure transparency, sturdy protection practices, and regulatory compliance remains crucial for actual-international adoption. Ordinary, the proposed system demonstrates robust ability to convert conventional healthcare into a more predictive, available, and patient-centered surroundings, even as developing new opportunities for innovation in virtual health.

AI-Enabled Approach for Classification of Medical Waste in Healthcare Facilities

Sat, 28 Feb 2026 00:00:00 +0000

Medical waste needs to be handled with care, and their project, the AI-Based Smart Trash Bin, makes this process safer and smarter. Using Artificial Intelligence, the bin can automatically detect whether the waste is infectious, a sharp item, or general hospital waste, and then open the correct lid-all without any touch. This work presents the design and development of an AI trash bin capable of recognizing and categorizing medical waste using computer vision, deep learning algorithms, and automated actuation mechanisms. The system uses a camera to capture waste images, processes them with a trained Convolutional Neural Network (CNN), and directs the waste to the appropriate compartment using servo motors controlled by a microcontroller. The prototype was tested on a medical waste dataset and demonstrated classification accuracy above 90%, with response time under 2 seconds. They use an ESP32 or Arduino, a camera, and servo motors to control the lids. The Al model, trained using Teachable Machine or TensorFlow Lite, runs directly on the device, so no internet is required. The system also gives quick feedback using LEDs or voice prompts. This bin improves hygiene, ensures proper waste separation, and can be easily used in hospitals to make waste management smarter and safer. By minimizing human involvement in biomedical waste handling, the system not only reduces occupational hazards but also enhances segregation efficiency and supports sustainable healthcare waste management. This solution can be scaled for hospitals, diagnostic labs, and clinics to meet growing global healthcare challenges.

IoT-Based Energy-Efficient Home Automation Using PIR Motion Sensor and Arduino UNO Board

Ananya, Rohit, Chandra Kanta Samal, Preeti Marwaha — Sat, 28 Feb 2026 00:00:00 +0000

This paper presents a low-cost Internet of Things (IoT)-based home automation system developed using an Arduino UNO microcontroller, a Passive Infrared (PIR) motion sensor, and LED indicators to automate lighting control based on human presence detection. The proposed system is designed to enhance energy efficiency by activating lights only when motion is detected within a specified range, thereby minimizing unnecessary power consumption. Experimental evaluation indicates that the system can reduce energy waste by up to 40% compared to conventional manual switching methods. The hardware implementation is intentionally simplified, utilizing only jumper wire connections, eliminating the need for a breadboard or complex supporting infrastructure, which makes it cost-effective and easy to deploy. Real-time monitoring and control are achieved through serial communication, ensuring reliable and responsive operation. The prototype demonstrates the technical feasibility, affordability, and effectiveness of motion-activated lighting automation, particularly for energy conservation in Indian households, educational institutions, and other resource-constrained environments seeking practical smart home solutions.

Sense-N-Go: An Intelligent IoT-Based Hand Gesture Controlled Vehicle System

Pooja Patil, Omkar More, Purva Pansare, Manasi Patil, Parth More — Wed, 08 Apr 2026 00:00:00 +0000

This project presents the design and implementation of Sense-n-Go, a gesture-controlled vehicle system developed to replace conventional remotes with natural hand - based interaction. The aim is to provide a simple, intuitive, and wireless method of navigation, using low-cost electronic components and embedded programming to build a complete framework that moves the vehicle according to the orientation of the user’s hand. The system uses a transmitter designed as a wearable hand band, where an Arduino Nano detects directional movements and converts them into digital signals. These signals are transmitted wirelessly through the NRF24L01 module to the receiver mounted on the vehicle, which consists of an Arduino Uno, another NRF24L01, and an L298 motor driver. Wireless communication ensures reliable data transfer, while the motor driver supplies adequate power for efficient vehicle operation. The project demonstrates the seamless integration of embedded hardware and wireless technology in producing a responsive prototype that moves entirely through gestures. The system not only serves as an innovative alternative to joystick-based navigation but also shows practical potential in robotics, automation, and assistive devices where intuitive control is required. By highlighting how hand gestures can effectively replace traditional controllers, the project demonstrates strong competencies in embedded systems, wireless communication, and motor control, while delivering a functional, low-cost, and real-world solution with clear practical value.

BusBuddy: A Data-Driven Analytics Framework for Smart Bus Route Optimization

P. Dharun, V. Manimekalai — Wed, 08 Apr 2026 00:00:00 +0000

Public bus transportation networks are under tremendous strain due to rapid urbanization and rising passenger mobility, especially in heavily populated nations like India, where more than 70 million people depend on bus services every day. Conventional bus scheduling and allocation techniques rely more on past assumptions than on current demand trends, making them essentially static. As a result, buses on high-demand routes are overcrowded, buses on low-demand routes are underutilized, fuel consumption rises, and revenue inefficiencies occur. In order to dynamically improve fleet allocation, this article suggests BusBuddy, a data-driven bus optimization system that makes use of machine learning-based forecasting, IoT-enabled GPS monitoring, and ticketing data integration. Using a Python-based analytics engine, the system analyzes both historical and current passenger data and applies predictive models to forecast demand per route. An interactive dashboard gives transport administrators real-time monitoring and operational insights, while a dynamic allocation system modifies bus deployment in response to changing passenger volumes. The suggested approach seeks to increase passenger happiness, save operating costs, and increase fleet utilization. According to simulation-based estimates, there may be a 25% increase in revenue, up to 40% reduction in fuel consumption observed under simulated conditions costs, and a far quicker operational planning process. BusBuddy provides a flexible and scalable architecture that is appropriate for sustainable urban mobility development and smart city transportation projects.