Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

[1]  Q. Wang,et al.  Real-Time Mental Arithmetic Task Recognition From EEG Signals , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  U. Rajendra Acharya,et al.  Classification of myocardial infarction with multi-lead ECG signals and deep CNN , 2019, Pattern Recognit. Lett..

[3]  J. Blumenthal,et al.  Impact of psychological factors on the pathogenesis of cardiovascular disease and implications for therapy. , 1999, Circulation.

[4]  Francisco J. Pelayo,et al.  Portable System for Real-Time Detection of Stress Level , 2018, Sensors.

[5]  Timo Giesbrecht,et al.  The role of frontal EEG asymmetry in post-traumatic stress disorder , 2015, Biological Psychology.

[6]  A. Malik,et al.  Difference in brain dynamics during arithmetic task performed in stress and control conditions , 2016, 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[7]  E. Cadenas,et al.  Physiology and Neurobiology of Stress and Adaptation: Central Role of the Brain , 2007 .

[8]  Davide Carneiro,et al.  Monitoring Mental Stress Through Mouse Behaviour and Decision-Making Patterns , 2018, ISAmI.

[9]  Pham Lam Vuong,et al.  An EEG-based machine learning method to screen alcohol use disorder , 2017, Cognitive Neurodynamics.

[10]  Jessica Carlsson,et al.  Neurofeedback Treatment and Posttraumatic Stress Disorder: Effectiveness of Neurofeedback on Posttraumatic Stress Disorder and the Optimal Choice of Protocol , 2016, The Journal of nervous and mental disease.

[11]  V. Knott,et al.  EEG power, frequency, asymmetry and coherence in male depression , 2001, Psychiatry Research: Neuroimaging.

[12]  Wenjian Qin,et al.  Comparison of Transferred Deep Neural Networks in Ultrasonic Breast Masses Discrimination , 2018, BioMed research international.

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

[14]  Keiron O'Shea,et al.  An Introduction to Convolutional Neural Networks , 2015, ArXiv.

[16]  Rui Cao,et al.  Epileptic Seizure Detection Based on EEG Signals and CNN , 2018, Front. Neuroinform..

[17]  C. Tenke,et al.  Abnormality of EEG alpha asymmetry in female adolescent suicide attempters , 1996, Biological Psychiatry.

[18]  Hedayat Sahraei,et al.  The impact of stress on body function: A review , 2017, EXCLI journal.

[19]  P. Lehrer,et al.  Principles And Practice Of Stress Management , 1984 .

[20]  P. Ekman,et al.  Approach-withdrawal and cerebral asymmetry: emotional expression and brain physiology. I. , 1990, Journal of personality and social psychology.

[21]  Seung-Hwan Lee,et al.  Frontal Alpha Asymmetry, Heart Rate Variability, and Positive Resources in Bereaved Family Members with Suicidal Ideation after the Sewol Ferry Disaster , 2018, Psychiatry investigation.

[22]  Olga Sourina,et al.  EEG Based Stress Monitoring , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[23]  Taku Komura,et al.  Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology , 2017, Journal of Imaging.

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

[25]  J. E. Dise-lewis.  The life events and coping inventory: an assessment of stress in children. , 1988, Psychosomatic medicine.

[26]  Ke Li,et al.  Real-Time Detection of Acute Cognitive Stress Using a Convolutional Neural Network From Electrocardiographic Signal , 2019, IEEE Access.

[27]  D. Goldstein,et al.  Adrenal Responses to Stress , 2010, Cellular and Molecular Neurobiology.

[28]  U. Rajendra Acharya,et al.  An automated diagnosis of depression using three-channel bandwidth-duration localized wavelet filter bank with EEG signals , 2018, Cognitive Systems Research.

[29]  D. Palomba,et al.  Frontal alpha asymmetry neurofeedback for the reduction of negative affect and anxiety. , 2017, Behaviour research and therapy.

[30]  R. Kessler,et al.  Predicting posttraumatic stress disorder following a natural disaster. , 2018, Journal of psychiatric research.

[31]  A P Smith,et al.  Negative life events, perceived stress, negative affect, and susceptibility to the common cold. , 1993, Journal of personality and social psychology.

[32]  Samara L. Firebaugh,et al.  Single-Trial Cognitive Stress Classification Using Portable Wireless Electroencephalography , 2019, Sensors.

[33]  K. Dedovic,et al.  The Montreal Imaging Stress Task: using functional imaging to investigate the effects of perceiving and processing psychosocial stress in the human brain. , 2005, Journal of psychiatry & neuroscience : JPN.

[34]  Muhammad Moinuddin,et al.  Investigating Neurofeedback Protocols for Stress Mitigation: A Comparative Analysis of Different Stimulus Contents , 2019, IEEE Access.

[35]  Aamir Saeed Malik,et al.  A physiological signal-based method for early mental-stress detection , 2018, Biomed. Signal Process. Control..

[36]  P. Gooding,et al.  Post-traumatic stress disorder and suicidal behavior: A narrative review. , 2009, Clinical psychology review.

[37]  Vanitha,et al.  Real time stress detection system based on EEG signals , 2016 .

[38]  J. Potash,et al.  POSTTRAUMATIC STRESS DISORDER INCREASES RISK FOR SUICIDE ATTEMPT IN ADULTS WITH RECURRENT MAJOR DEPRESSION , 2013, Depression and anxiety.

[39]  Bruce S. McEwen,et al.  Stress, memory and the amygdala , 2009, Nature Reviews Neuroscience.

[40]  Xiaobo Zhang,et al.  A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection , 2018, Secur. Commun. Networks.

[41]  N. Jokić-begić,et al.  Electroencephalographic comparison of veterans with combat-related post-traumatic stress disorder and healthy subjects. , 2001, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[42]  N. Fox,et al.  Long-term stability of frontal electroencephalographic asymmetry in adults with a history of depression and controls. , 2006, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[43]  K. Koh,et al.  Development of the Stress Response Inventory and Its Application in Clinical Practice , 2001, Psychosomatic medicine.

[44]  B. Leonard,et al.  The psychoneuroimmunology of depression , 2009, Human psychopharmacology.

[45]  S. Debener,et al.  Is Resting Anterior EEG Alpha Asymmetry a Trait Marker for Depression? , 2000, Neuropsychobiology.

[46]  D. C. Howell,et al.  Daily and major life events: A test of an integrative model of psychosocial stress , 1988, American journal of community psychology.

[47]  A. Statnikov,et al.  Quantitative forecasting of PTSD from early trauma responses: a Machine Learning application. , 2014, Journal of psychiatric research.

[48]  Selim R. Benbadis,et al.  Errors in EEGs and the misdiagnosis of epilepsy: Importance, causes, consequences, and proposed remedies , 2007, Epilepsy & Behavior.