TY - JOUR
T1 - Classifying multi-level stress responses from brain cortical EEG in Nurses and Non-health professionals using Machine Learning Auto Encoder
AU - Akella, Ashlesha
AU - Singh, Avinash Kumar
AU - Leong, Daniel
AU - Lal, Sara
AU - Newton, Phillip
AU - Clifton-Bligh, Roderick
AU - McLachlan, Craig Steven
AU - Gustin, Sylvia Maria
AU - Maharaj, Shamona
AU - Lees, Ty
AU - Cao, Zehong
AU - Lin, Chin Teng
N1 - Publisher Copyright:
CCBY
PY - 2021
Y1 - 2021
N2 - Objective: Mental stress is a major problem in our society and has become an area of interest for many psychiatric researchers. One primary research focus area is the identification of bio-markers that not only identify stress but also predict the conditions (or tasks) that cause stress. Electroencephalograms (EEGs) have been used for a long time to study and identify bio-markers. While these bio-markers have successfully predicted stress in EEG studies for binary conditions, their performance is suboptimal for multiple conditions of stress. Methods: To overcome this challenge, we propose using latent based representations of the bio-markers, which have been shown to significantly improve EEG performance compared to traditional bio-markers alone. We evaluated three commonly used EEG based bio-markers for stress, the brain load index (BLI), the spectral power values of EEG frequency bands (alpha, beta and theta), and the relative gamma (RG), with their respective latent representations using four commonly used classifiers. Results: The results show that spectral power value based bio-markers had a high performance with an accuracy of 83%, while the respective latent representations had an accuracy of 91%.
AB - Objective: Mental stress is a major problem in our society and has become an area of interest for many psychiatric researchers. One primary research focus area is the identification of bio-markers that not only identify stress but also predict the conditions (or tasks) that cause stress. Electroencephalograms (EEGs) have been used for a long time to study and identify bio-markers. While these bio-markers have successfully predicted stress in EEG studies for binary conditions, their performance is suboptimal for multiple conditions of stress. Methods: To overcome this challenge, we propose using latent based representations of the bio-markers, which have been shown to significantly improve EEG performance compared to traditional bio-markers alone. We evaluated three commonly used EEG based bio-markers for stress, the brain load index (BLI), the spectral power values of EEG frequency bands (alpha, beta and theta), and the relative gamma (RG), with their respective latent representations using four commonly used classifiers. Results: The results show that spectral power value based bio-markers had a high performance with an accuracy of 83%, while the respective latent representations had an accuracy of 91%.
KW - Australia
KW - AutoEncoder
KW - Electroencephalogram
KW - Electroencephalography
KW - Indexes
KW - Physiology
KW - Stress
KW - Stress Classification
KW - Support Vector Machine
KW - Support vector machines
KW - Task analysis
UR - http://www.scopus.com/inward/record.url?scp=85105886587&partnerID=8YFLogxK
UR - https://doi.org/10.25905/21638207.v1
U2 - 10.1109/JTEHM.2021.3077760
DO - 10.1109/JTEHM.2021.3077760
M3 - Article
AN - SCOPUS:85105886587
JO - IEEE Journal of Translational Engineering in Health and Medicine
JF - IEEE Journal of Translational Engineering in Health and Medicine
SN - 2168-2372
ER -