Abstract: This project presents an intelligent assistive system for stroke patients using a smart glove integrated with three flex sensors, heart rate and temperature sensors, a camera, and a Raspberry Pi 4B. The flex sensors are attached to three fingers to detect bending motions, representing binary combinations to trigger predefined commands. These commands, alongside vital signs such as temperature and heart rate, are displayed on an LCD screen and transmitted to an IoT platform (ThingSpeak) for remote monitoring. A camera module captures live video of the patient, which is streamed in real-time. Additionally, a MATLAB based GUI application is developed to display all sensor data and commands on a computer, providing real time monitoring and support. This system offers an efficient, low-cost solution to enhance communication and health tracking for stroke patients.
Keywords: Smart Glove, Stroke Rehabilitation, IoT Healthcare Monitoring, Real time Patient Assistance Security.
Downloads:
|
DOI:
10.17148/IJARCCE.2025.141178
[1] Aishwarya G V, Nithya T, Manoj K S, Sagar, Dr. Anand M, "Deep learning- driven myoelectric gesture classification for post-stroke rehabilitation," International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), DOI: 10.17148/IJARCCE.2025.141178
