Galvanic Skin Response based Stress Detection System using Machine Learning and IoT

Abstract

The primary objective of this study is to construct an Internet of Things (IoT)-based stress detection system that uses Galvanic Skin Response (GSR) and pulse sensors. In today's contemporary world, stress has developed into a widespread problem and early recognition of the condition is necessary for efficient intervention and treatment. The suggested system utilizes GSR and pulse sensors in conjunction with the IoT technologies to continuously monitor and analyze an individual's stress levels. The GSR sensor analyzes changes in the electrical conductance of the skin, which is known to occur during times of stress; in contrast, the pulse sensor identifies patterns in heart rate related to stress. Signal processing methods are used to process the newly collected sensor data, after which useful characteristics are retrieved. After the data has been analyzed, it is wirelessly sent to a cloud platform so that machine learning algorithms may be used for further analysis and categorization. The system displays the current amount of stress in real-time and can send warnings if the current stress level reaches a certain threshold. To guarantee that the system conforms to the rules, the system has established privacy and data security precautions. Our goal is to contribute, via this study, to the creation of an accurate and reliable stress detection system that may aid people in efficiently controlling the amounts of stress that they are experiencing in their lives.