IoT-Enhanced Stress-Adaptive Reading: A Machine Learning Approach with Galvanic Skin Response

In today's fast-paced educational landscape, understanding and addressing students' stress levels are paramount for fostering effective learning environments. This research introduces a novel approach to stress detection and adaptive reading, leveraging the Internet of Things (IoT), galvanic skin response (GSR) sensors, and machine learning techniques. By collecting real-time physiological data from students wearing GSR sensors during tests, our system aims to dynamically adapt reading materials based on individual stress levels. This paper details the methodology, including the creation of a customized dataset, data preprocessing, clustering, and the development of an IoT infrastructure using Raspberry Pi. The integration of Django web applications, WebSocket communication, and machine learning models further enhances the adaptability and responsiveness of the system. Our work contributes to the intersection of IoT, GSR, and machine learning in education, offering a promising avenue for personalized and stress-aware learning experiences.