Long-term stress assessment based on EEG signals : an empirical method for EEG feature importance | |
| Author | Rattaphong Laoharungpisit |
| Call Number | AIT Thesis no.IM-22-01 |
| Subject(s) | Electroencephalography Stress (Psychology) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | Long-term stress is a prolonged and constant feeling of stress which could lead to de pression and anxiety. There are several studies that have been successful in quantifying stress using EEG. However, these studies only evaluate short-term induced stress. On the other hand, EEG has not been widely used for long-term stress assessment. The purpose of this study is therefore to investigate the long-term stress classification with the aim to identify the important EEG features that contribute to long-term stress classi fication accuracy. In this study, EEG signals were recorded from 55 participants in the resting state eyes-closed condition for 5 minutes. The five frequency bands and asym metry were extracted as features. The important features were selected using t-test and coefficient/feature importance score from five classifiers. The SVM achieves a 10-cv score over 0.9 using top eight βf , F3δ , F4δ , F3β , P4δ , F3γ , P4θ , and C3θ as features. This study demonstrated the empirical method of feature selection and proposed that EEG can be used in long-term stress classification. |
| Year | 2022 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Chaklam Silpasuwanchai |
| Examination Committee(s) | Dailey, Matthew N.;Attaphongse Taparugssanagorn |
| Scholarship Donor(s) | Royal Thai Government Fellowship |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2022 |