Stress Based Vehicle Speed Control Using IOT

Stress-related concerns have become increasingly prevalent in contemporary society, necessitating the development of accurate and non-intrusive detection methods. This paper proposes a multi-modal human stress detection system that integrates facial recognition and emotion analysis to provide a real-time, automated assessment of stress levels. The system employs OpenCV’s Haar cascade algorithm for facial detection, followed by stress estimation using a pre-trained Convolutional Neural Network (CNN) model. Additionally, a k-Nearest Neighbors (KNN) algorithm extracts emotional features to enhance the accuracy of stress level classification. By capturing both physiological and emotional cues, the proposed system offers a comprehensive and effective approach to stress monitoring. The integration of deep learning and machine learning techniques enables robust, real-time stress detection, making it applicable across various domains, including workplaces, healthcare, and personal well-being initiatives. The results demonstrate that the system achieves high accuracy in stress classification while ensuring a non-intrusive and user-friendly approach. This study contributes significantly to the field of mental health monitoring by providing a technologically advanced solution for stress assessment and early intervention.