Ashlesha Akella1, Avinash Kumar Singh1, Daniel Leong1, Sara Lal2, Phillip Newton3, Roderick Clifton-Bligh4, Craig Steven Mclachlan5,6, Sylvia Maria Gustin7, Shamona Maharaj2, Ty Lees8, Zehong Cao9, Chin-Teng Lin1. 1. FEIT, School of Computer ScienceAustralian Artificial Intelligence Institute, University of Technology Sydney Ultimo NSW 2007 Australia. 2. Neuroscience Research Unit, School of Life SciencesUniversity of Technology Sydney Ultimo NSW 2007 Australia. 3. Centre for Cardiovascular and Chronic CareUniversity of Technology Sydney Ultimo NSW 2007 Australia. 4. Department of EndocrinologyRoyal North Shore HospitalThe University of Sydney Sydney NSW 2006 Australia. 5. Centre for Healthy Futures, Health VerticalTorrens University Australia, Pyrmont Campus Pyrmont NSW 2009 Australia. 6. Neuroscience Research Australia Randwick NSW 2031 Australia. 7. School of PsychologyUniversity of New South Wales Sydney NSW 2052 Australia. 8. Edna Bennett Pierce Prevention Research CenterPennsylvania State University State College PA 16801 USA. 9. Information and Communication Technology (ICT)University of Tasmania Hobart TAS 7005 Australia.
Abstract
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%.
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%.
Entities:
Keywords:
Autoencoder; electroencephalogram; stress classification; support vector machine