Year: 2014
Type: dissertation
Abstract: Prolonged exposure to stress can cause serious mental and physical illnesses. Therefore, it is important that people are aware of stressful situations, so that they can take necessary actions to cope with them. We introduce a mobile system that is able to detect stress in individuals in real-time based on electrocardiogram and electrodermal activity. The system is built around an Android smartphone and uses wearable, unobtrusive sensors, which include a smart watch and a heart rate belt that gather skin conductance and heart rate data, respectively. When a stressful situation is detected, the system alerts the user and records an audio clip relevant to the stressful event. Both physiological and audio data are stored in the cloud, enabling the user to review past stress-related data offline. Small scale user tests show 82.9% 10-fold and 82.2% between-subject stress detection accuracy. Furthermore, algorithms for processing the skin conductance and heart rate data, as well as an automated method for labeling the collected ‘stress’ and ‘non-stress’ experimental data are developed.
Author: Vasileios Alexandratos
Language: English
Topic: Emotion and Mood Recognition
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W122550588