Machine learning based biosignals mental stress detection

Adel Ali Al-Jumaily, Nafisa Matin, Azadeh Noori Hoshyar

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

Mental Stress can be defined as a normal physiological and biological reaction to an incident or a situation that makes a person feel challenged, troubled, or helpless. While dealing with stress, some changes occur in the biological function of a person, which results in a considerable change in some bio-signals such as, Electrocardiogram (ECG), Electromyography (EMG), Electrodermal Activity (EDA), respiratory rate. This paper aims to review the effect of mental stress on mental condition and health, the changes in biosignals as an indicator of the stress response and train a model to detect stressed states using the biosignals. This paper delivers a brief review of mental stress and biosignals correlation. It represents four Support Vector Machine (SVM) models trained with ECG and EMG features from an open access database based on task related stress. After performing comparative analysis on the four types of trained SVM models with chosen features, Gaussian Kernel SVM is selected as the best SVM model to detect mental stress which can predict the mental condition of a subject for a stressed and relaxed condition having an accuracy of 93.7%. These models can be investigated further with more biosignals and applied in practice, which will be beneficial for the physician.

Original languageEnglish
Title of host publicationSoft Computing in Data Science
Subtitle of host publication6th International Conference, SCDS 2021, Virtual Event, November 2–3, 2021, Proceedings
EditorsAzlinah Mohamed, Bee Wah Yap, Jasni Mohamad Zain, Michael W. Berry
PublisherSpringer Science and Business Media Deutschland GmbH
Pages28-41
Number of pages14
ISBN (Print)9789811673337
DOIs
Publication statusE-pub ahead of print - 26 Oct 2021
Event6th International Conference on Soft Computing in Data Science: SCDS 2021 - Virtual
Duration: 02 Nov 202103 Nov 2021
https://aaec.uitm.edu.my/scds2021/home/#:~:text=29%20August%202019.-,The%206th%20International%20Conference%20on%20Soft%20Computing%20in%20Data%20Science,Statistics%2C%20Faculty%20of%20Science%20and (Conference website)
https://aaec.uitm.edu.my/scds2021/static/media/SCDS2021-ProgramBook_Abstract.edc38ba8.pdf (Program)
https://link.springer.com/book/10.1007/978-981-16-7334-4 (Proceedings)

Publication series

NameCommunications in Computer and Information Science
Volume1489 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th International Conference on Soft Computing in Data Science
Abbreviated titleScience in Analytics: Harnessing Data and Simplifying Solutions
Period02/11/2103/11/21
OtherThe 6th International Conference on Soft Computing in Data Science 2021 (SCDS2021) will be hosted virtually by IBDAAI (Institute for Big Data Analytics and Artificial Intelligence), UiTM, with the collaborations of Faculty of Computer and Mathematical Sciences, UiTM, Department of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember (ITS), Surabaya, Indonesia, and Research Nexus, UiTM from 2-3 November 2021. The theme of the conference is ‘Science in Analytics: Harnessing Data and Simplifying Solutions’. SCDS2021 have invited renowned international and local keynote speakers who are academia or practitioners to share their knowledge and experience in the area in the applications of soft computing in various disciplines. This conference aims to provide a platform for researchers and practitioners to share their research work and to create rigorous international research collaborations.

SCDS2021 targets participants from universities, government agencies and industries with the ultimate aim of bridging the gap between academia and the industry. Research collaborations between the academia and industry can lead to the advancement of useful analytics and computing applications for providing real time insights and solutions.
Internet address

Fingerprint

Dive into the research topics of 'Machine learning based biosignals mental stress detection'. Together they form a unique fingerprint.

Cite this