Real Time Mental Health Monitoring System using Machine Learning

Recent advancements in mobile health devices have spurred interest in leveraging them for monitoring mental health symptoms like stress. This project proposes an innovative system utilizing Arduino UNO and various sensors to detect physiological signs of stress. Machine learning techniques are integrated to enhance stress detection accuracy, despite the microcontroller's computational constraints. Simplified algorithms like decision trees offer lightweight solutions suitable for Arduino's capabilities, enabling proactive intervention strategies in mental health management. We have achieved the highest accuracy of 96.6% for stress detection and also the proposed hardware module effectively identifies mental health conditions.

Hali tarjima qilinmagan