EEG Based Classification of Long-Term Stress Using Psychological Labeling
Stress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/1886 |
| _version_ | 1797626441074999296 |
|---|---|
| author | Sanay Muhammad Umar Saeed Syed Muhammad Anwar Humaira Khalid Muhammad Majid Ulas Bagci |
| author_facet | Sanay Muhammad Umar Saeed Syed Muhammad Anwar Humaira Khalid Muhammad Majid Ulas Bagci |
| author_sort | Sanay Muhammad Umar Saeed |
| collection | DOAJ |
| description | Stress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study, long-term stress was classified with machine learning algorithms using resting state EEG signal recordings. The labeling for the stress and control groups was performed using two currently accepted clinical practices: (i) the perceived stress scale score and (ii) expert evaluation. The frequency domain features were extracted from five-channel EEG recordings in addition to the frontal and temporal alpha and beta asymmetries. The alpha asymmetry was computed from four channels and used as a feature. Feature selection was also performed to identify statistically significant features for both stress and control groups (via <i>t</i>-test). We found that support vector machine was best suited to classify long-term human stress when used with alpha asymmetry as a feature. It was observed that the expert evaluation-based labeling method had improved the classification accuracy by up to 85.20%. Based on these results, it is concluded that alpha asymmetry may be used as a potential bio-marker for stress classification, when labels are assigned using expert evaluation. |
| first_indexed | 2024-03-11T10:10:25Z |
| format | Article |
| id | doaj.art-f967efe8105c400b93637d06f15ad87a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T10:10:25Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f967efe8105c400b93637d06f15ad87a2023-11-16T14:34:43ZengMDPI AGSensors1424-82202020-03-01207188610.3390/s20071886EEG Based Classification of Long-Term Stress Using Psychological LabelingSanay Muhammad Umar Saeed0Syed Muhammad Anwar1Humaira Khalid2Muhammad Majid3Ulas Bagci4Department of Computer Engineering, University of Engineering and Technology, Taxila 47050, PakistanDepartment of Software Engineering, University of Engineering and Technology, Taxila 47050, PakistanDepartment of Psychology, Benazir Bhutto Hospital, Rawalpindi 46000, PakistanDepartment of Computer Engineering, University of Engineering and Technology, Taxila 47050, PakistanDepartment of Computer Science, University of Central Florida, Orlando, FL 32816, USAStress research is a rapidly emerging area in the field of electroencephalography (EEG) signal processing. The use of EEG as an objective measure for cost effective and personalized stress management becomes important in situations like the nonavailability of mental health facilities. In this study, long-term stress was classified with machine learning algorithms using resting state EEG signal recordings. The labeling for the stress and control groups was performed using two currently accepted clinical practices: (i) the perceived stress scale score and (ii) expert evaluation. The frequency domain features were extracted from five-channel EEG recordings in addition to the frontal and temporal alpha and beta asymmetries. The alpha asymmetry was computed from four channels and used as a feature. Feature selection was also performed to identify statistically significant features for both stress and control groups (via <i>t</i>-test). We found that support vector machine was best suited to classify long-term human stress when used with alpha asymmetry as a feature. It was observed that the expert evaluation-based labeling method had improved the classification accuracy by up to 85.20%. Based on these results, it is concluded that alpha asymmetry may be used as a potential bio-marker for stress classification, when labels are assigned using expert evaluation.https://www.mdpi.com/1424-8220/20/7/1886long-term stresselectroencephalographymachine learningperceived stress scaleexpert evaluation |
| spellingShingle | Sanay Muhammad Umar Saeed Syed Muhammad Anwar Humaira Khalid Muhammad Majid Ulas Bagci EEG Based Classification of Long-Term Stress Using Psychological Labeling Sensors long-term stress electroencephalography machine learning perceived stress scale expert evaluation |
| title | EEG Based Classification of Long-Term Stress Using Psychological Labeling |
| title_full | EEG Based Classification of Long-Term Stress Using Psychological Labeling |
| title_fullStr | EEG Based Classification of Long-Term Stress Using Psychological Labeling |
| title_full_unstemmed | EEG Based Classification of Long-Term Stress Using Psychological Labeling |
| title_short | EEG Based Classification of Long-Term Stress Using Psychological Labeling |
| title_sort | eeg based classification of long term stress using psychological labeling |
| topic | long-term stress electroencephalography machine learning perceived stress scale expert evaluation |
| url | https://www.mdpi.com/1424-8220/20/7/1886 |
| work_keys_str_mv | AT sanaymuhammadumarsaeed eegbasedclassificationoflongtermstressusingpsychologicallabeling AT syedmuhammadanwar eegbasedclassificationoflongtermstressusingpsychologicallabeling AT humairakhalid eegbasedclassificationoflongtermstressusingpsychologicallabeling AT muhammadmajid eegbasedclassificationoflongtermstressusingpsychologicallabeling AT ulasbagci eegbasedclassificationoflongtermstressusingpsychologicallabeling |