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, 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 t-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.

[1]  H Selye,et al.  The Stress Syndrome , 1965, [Kango gijutsu] : [Nursing technique].

[2]  L C Sobell,et al.  A procedure for reducing errors in reports of life events. , 1990, Journal of psychosomatic research.

[3]  J. S. Barlow,et al.  Changes in EEG mean frequency and spectral purity during spontaneous alpha blocking. , 1990, Electroencephalography and clinical neurophysiology.

[4]  R. Kessler,et al.  Chronic stress, acute stress, and depressive symptoms , 1990, American journal of community psychology.

[5]  Ellen Frank,et al.  Toward the standardization of life stress assessment: Definitional discrepancies and inconsistencies in methods , 1992 .

[6]  W. Maixner,et al.  Beta-endorphin response to exercise and mental stress in patients with ischemic heart disease. , 1993, Journal of psychosomatic research.

[7]  K Matsunami,et al.  Generator sources of EEG large waves elicited by mental stress of memory recall or mental calculation. , 2001, The Japanese journal of physiology.

[8]  Günter Schulter,et al.  Covariations of EEG asymmetries and emotional states indicate that activity at frontopolar locations is particularly affected by state factors. , 2002, Psychophysiology.

[9]  C. Nemeroff,et al.  Neurobiology of early life stress: clinical studies. , 2002, Seminars in clinical neuropsychiatry.

[10]  Wolzt,et al.  World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. , 2003, The Journal of the American College of Dentists.

[11]  Christiane,et al.  World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. , 2004, Journal international de bioethique = International journal of bioethics.

[12]  R. Davidson What does the prefrontal cortex “do” in affect: perspectives on frontal EEG asymmetry research , 2004, Biological Psychology.

[13]  H. Praag,et al.  Can stress cause depression? , 2004, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[14]  H. M. Praag Can stress cause depression? , 2004, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[15]  S. Kotsiantis Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[16]  Nicole Y. Weekes,et al.  The effect of a naturalistic stressor on frontal EEG asymmetry, stress, and health , 2007, Biological Psychology.

[17]  Sheldon Cohen,et al.  Psychological stress and disease. , 2007, JAMA.

[18]  Johannes Knaus,et al.  THE PROCESSING OF WORD STRESS: EEG STUDIES ON TASK-RELATED COMPONENTS , 2007 .

[19]  Ssanghee Seo,et al.  The Relation between Affective Style of Stressor on EEG Asymmetry and Stress Scale during Multimodal Task , 2008, 2008 Third International Conference on Convergence and Hybrid Information Technology.

[20]  Tzyy-Ping Jung,et al.  Noninvasive Neural Prostheses Using Mobile and Wireless EEG , 2008, Proceedings of the IEEE.

[21]  Leiv Sandvik,et al.  Long-Term Stability of Cardiovascular and Catecholamine Responses to Stress Tests: An 18-Year Follow-Up Study , 2010, Hypertension.

[22]  S. Seo,et al.  Stress and EEG , 2010 .

[23]  Kai Keng Ang,et al.  A Brain-Computer Interface for classifying EEG correlates of chronic mental stress , 2011, The 2011 International Joint Conference on Neural Networks.

[24]  M. Hariharan,et al.  Mental tasks classifications using S-transform for BCI applications , 2011, 2011 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (STUDENT).

[25]  Bin Hu,et al.  A method of identifying chronic stress by EEG , 2012, Personal and Ubiquitous Computing.

[26]  Andrew Steptoe,et al.  Stress and cardiovascular disease , 2012, Nature Reviews Cardiology.

[27]  P. Aspinall,et al.  The urban brain: analysing outdoor physical activity with mobile EEG , 2013, British Journal of Sports Medicine.

[28]  S. Grimm,et al.  Frontal midline theta oscillations during mental arithmetic: effects of stress , 2015, Front. Behav. Neurosci..

[29]  Steven M. Thompson,et al.  Measurement of Chronic Stress , 2015 .

[30]  Kimihiko Nakano,et al.  Biosignal Analysis to Assess Mental Stress in Automatic Driving of Trucks: Palmar Perspiration and Masseter Electromyography , 2015, Sensors.

[31]  Isabela Lobo,et al.  EEG correlates of the severity of posttraumatic stress symptoms: A systematic review of the dimensional PTSD literature. , 2015, Journal of affective disorders.

[32]  Michael Doppelmayr,et al.  Electroencephalogram alpha asymmetry in geriatric depression , 2018, Zeitschrift für Gerontologie und Geriatrie.

[33]  Kavallur Gopi Smitha,et al.  EEG based stress level identification , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[34]  J. Kuhl,et al.  Relative frontal brain asymmetry and cortisol release after social stress: The role of action orientation , 2016, Biological Psychology.

[35]  Francisco J. Pelayo,et al.  Stress Assessment by Prefrontal Relative Gamma , 2016, Front. Comput. Neurosci..

[36]  Adel M. Alimi,et al.  Efficient Human Stress Detection System Based on Frontal Alpha Asymmetry , 2017, ICONIP.

[37]  Nasreen Badruddin,et al.  Towards multilevel mental stress assessment using SVM with ECOC: an EEG approach , 2017, Medical & Biological Engineering & Computing.

[38]  Wei Liu,et al.  A game player expertise level classification system using electroencephalography (EEG) , 2017 .

[39]  Aamir Saeed Malik,et al.  Machine Learning Framework for the Detection of Mental Stress at Multiple Levels , 2017, IEEE Access.

[40]  Syed Muhammad Anwar,et al.  Quantification of Human Stress Using Commercially Available Single Channel EEG Headset , 2017, IEICE Trans. Inf. Syst..

[41]  Syed Muhammad Anwar,et al.  Emotion recognition in response to traditional and tactile enhanced multimedia using electroencephalography , 2018, Multimedia Tools and Applications.

[42]  Syed Muhammad Anwar,et al.  Selection of Neural Oscillatory Features for Human Stress Classification with Single Channel EEG Headset , 2018, BioMed research international.

[43]  Bin Hu,et al.  A Pervasive Approach to EEG-Based Depression Detection , 2018, Complex..

[44]  Syed Muhammad Anwar,et al.  Classification of Perceived Mental Stress Using A Commercially Available EEG Headband , 2019, IEEE Journal of Biomedical and Health Informatics.

[45]  Syed Muhammad Anwar,et al.  A Hybrid Scheme for Drowsiness Detection Using Wearable Sensors , 2019, IEEE Sensors Journal.

[46]  Hee Chan Kim,et al.  A Novel Wearable EEG and ECG Recording System for Stress Assessment , 2019, Sensors.

[47]  Syed Muhammad Anwar,et al.  Human stress classification using EEG signals in response to music tracks , 2019, Comput. Biol. Medicine.