Development of physiological mouse for anxiety disorder identification system
Anxiety disorder has been known as one of mental disorder characterized by significant and uncontrollable feelings of anxiety and fear. Anxiety may cause physical and cognitive symptoms such as restlessness, irritability, easy fatigability, difficulty concentrating, increased heart rate, chest pai...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2023
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/28086/1/Development%20of%20physiological%20mouse%20for%20anxiety%20disorder%20identification%20system.pdf http://eprints.utem.edu.my/id/eprint/28086/ https://pubs.aip.org/aip/acp/article-abstract/2955/1/020019/2930458/Development-of-physiological-mouse-for-anxiety?redirectedFrom=fulltext |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Anxiety disorder has been known as one of mental disorder characterized by significant and uncontrollable
feelings of anxiety and fear. Anxiety may cause physical and cognitive symptoms such as restlessness, irritability, easy
fatigability, difficulty concentrating, increased heart rate, chest pain, abdominal pain, and many others. Motivated by current
research that accompanies anxiety and stress with physical reactions such as increased heart rate, blood flow, dilation of the
pupil and skin conductance, this work builds on the premise that real-time measurement of such reactions could indirectly
recognize older adult anxiety while interacting with the system. For this research, an in-house computer mouse with embedded
sensors circuit was constructed and simulated via Proteus environment to test the heart rate and skin conductance of the users.
In this project a rules-based algorithm for distinguishing the anxiety disorder events have been developed. The detection is
being processed based on the measured physiological data that being quantified via the embedded sensors in the mouse circuits.
The result shows that the developed system able to detect mental health state of the user at accuracy of 0.87, which defines a
good performance of the proposed system. |
|---|