Real-Time Stress Detection and Management Using IoT Sensors and Virtual Reality Technology

In recent years, the issue of stress, especially academic stress has emerged as a growing problem, especially among students, who face problems of both physical and mental health due to stress. This paper proposes a new method for stress detection and management using Internet of Things (IoT) based system equipped with Virtual Reality (VR) technology and physiological sensors. Real physiological stress signals included in this system include Electromyography (EMG) and Galvanic Skin Response (GSR). Advanced signal processing technique is applied on these signals, after which a deep learning model is used for stress classification. Interventions that induce and alleviate stress in VR are incorporated to gain insights into the physiological response to stress in a controlled environment. Transfer Learning Model Networks (TLMN) is used to extract deep learning model that improve the accuracy of classifying stress levels from complex physiological data. The system shows the ability to detect stress with high accuracy, which makes it applicable in the field of real time stress monitoring and intervention in academic and clinical settings. In the future, we will scale the system for more sample size and for broader applications, such as wearable devices and huge deployment.