Insightful stress detection from physiology modalities using Learning Vector Quantization

Abstract Stress in daily life can lead to severe conditions as burn-out and depression and has a major impact on society. Being able to measure mental stress reliably opens up the ability to intervene in an early stage. We performed a large-scale study in which skin conductance, respiration and electrocardiogram were measured in semi-controlled conditions. Using Learning Vector Quantization techniques, we obtained up to 88% accuracy in the classification task to separate stress from relaxation. Relevance learning was used to identify the most informative features, indicating that most information is embedded in the cardiac signals. In addition to commonly used features, we also explored various novel features, of which the very-high frequency band of the power spectrum was found to be a very relevant addition.

[1]  Sarah Hampson,et al.  Physiological correlates of human behaviour, vol. III: Individual differences and psychopathology A. Gale and J.A. Edwards (Eds.), (Academic Press, London, 1983) pp. xv + 298, £28.00. , 1985, Biological Psychology.

[2]  Herbert F. Voigt,et al.  IEEE Engineering in Medicine and Biology Society , 2019, IEEE Transactions on Biomedical Engineering.

[3]  Michael Biehl,et al.  Adaptive Relevance Matrices in Learning Vector Quantization , 2009, Neural Computation.

[4]  S. Folkman,et al.  Stress, appraisal, and coping , 1974 .

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[6]  Egon L. van den Broek,et al.  Prerequisites for Affective Signal Processing (ASP) - Part IV , 2016, B-Interface.

[7]  Egon L. van den Broek,et al.  Prerequisites for Affective Signal Processing (ASP) , 2009, BIOSIGNALS.

[8]  M. Dawson,et al.  The electrodermal system , 2007 .

[9]  Elisabeth André,et al.  Emotion recognition based on physiological changes in music listening , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Klaus Obermayer,et al.  Soft Learning Vector Quantization , 2003, Neural Computation.

[11]  A. Barreto,et al.  Stress Detection in Computer Users Based on Digital Signal Processing of Noninvasive Physiological Variables , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  J. Houtveen,et al.  Contribution of tonic vagal modulation of heart rate, central respiratory drive, respiratory depth, and respiratory frequency to respiratory sinus arrhythmia during mental stress and physical exercise. , 2002, Psychophysiology.

[13]  Christos D. Katsis,et al.  Toward Emotion Recognition in Car-Racing Drivers: A Biosignal Processing Approach , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[14]  Andrew Steptoe,et al.  Family history of cardiovascular disease is associated with cardiovascular responses to stress in healthy young men and women. , 2007, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[15]  G. Logan.  On the ability to inhibit thought and action , 1984 .

[16]  Christine L. Lisetti,et al.  Using Noninvasive Wearable Computers to Recognize Human Emotions from Physiological Signals , 2004, EURASIP J. Adv. Signal Process..

[17]  Michael Biehl,et al.  Window-Based Example Selection in Learning Vector Quantization , 2010, Neural Computation.

[18]  W PicardRosalind,et al.  Toward Machine Emotional Intelligence , 2001 .

[19]  Anke Bouma,et al.  Neuropsychologische diagnostiek : handboek , 1996 .

[20]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[21]  David Vernon,et al.  A novel self-guided approach to alpha activity training. , 2012, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[22]  Dimitrios Tzovaras,et al.  Subject-dependent biosignal features for increased accuracy in psychological stress detection , 2013, Int. J. Hum. Comput. Stud..

[23]  Sidney J Segalowitz,et al.  Autonomic predictors of Stroop performance in young and middle-aged adults. , 2010, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[24]  Rajita Sinha,et al.  Multivariate Response Patterning of Fear and Anger , 1996 .

[25]  Hao Liu,et al.  Towards mental stress detection using wearable physiological sensors , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  H. Vincent Poor,et al.  An Introduction to Signal Detection and Estimation , 1994, Springer Texts in Electrical Engineering.

[27]  Jennifer Healey,et al.  Toward Machine Emotional Intelligence: Analysis of Affective Physiological State , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  K. Quigley,et al.  Applications of Psychophysiological Recording , 2000 .

[29]  J. Lagopoulos.  Electrodermal activity , 2007, Acta Neuropsychiatrica.

[30]  Jennifer Healey,et al.  Detecting stress during real-world driving tasks using physiological sensors , 2005, IEEE Transactions on Intelligent Transportation Systems.

[31]  Chao Li,et al.  Realization of stress detection using psychophysiological signals for improvement of human-computer interactions , 2005, Proceedings. IEEE SoutheastCon, 2005..

[32]  M. Kivimäki,et al.  Work stress in the etiology of coronary heart disease--a meta-analysis. , 2006, Scandinavian journal of work, environment & health.

[33]  G. Breithardt,et al.  Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. , 1996 .

[34]  John A. Edwards,et al.  Individual differences and psychopathology , 1983 .

[35]  A. Malliani,et al.  Heart rate variability. Standards of measurement, physiological interpretation, and clinical use , 1996 .

[36]  C. Eriksen,et al.  Effects of noise letters upon the identification of a target letter in a nonsearch task , 1974 .

[37]  W. Kirchner.  Age differences in short-term retention of rapidly changing information. , 1958, Journal of experimental psychology.

[38]  D. Vernon,et al.  Identifying Indices of Learning for Alpha Neurofeedback Training , 2009, Applied psychophysiology and biofeedback.

[39]  John T. Cacioppo,et al.  Heart Rate Variability: Stress and Psychiatric Conditions , 2007 .

[40]  K. H. Kim,et al.  Emotion recognition system using short-term monitoring of physiological signals , 2004, Medical and Biological Engineering and Computing.

[41]  Joyce H. D. M. Westerink,et al.  The Vitality Bracelet: Bringing Balance to Your Life with Psychophysiological Measurements , 2014 .

[42]  Egon L. van den Broek,et al.  Affective Man-Machine Interface: Unveiling Human Emotions through Biosignals , 2009, BIOSTEC.

[43]  R W Bohannon,et al.  Objective measures. , 1989, Physical therapy.

[44]  Tamás D. Gedeon,et al.  Objective measures, sensors and computational techniques for stress recognition and classification: A survey , 2012, Comput. Methods Programs Biomed..

[46]  Gert-Jan de Vries,et al.  Enhanced Method for Robust Mood Extraction from Skin Conductance , 2010, BIOSIGNALS.

[47]  Mohammad Soleymani,et al.  Short-term emotion assessment in a recall paradigm , 2009, Int. J. Hum. Comput. Stud..

[48]  P. Grossman,et al.  Toward understanding respiratory sinus arrhythmia: Relations to cardiac vagal tone, evolution and biobehavioral functions , 2007, Biological Psychology.

[49]  Jan Chomicki,et al.  Time Domain , 2018, Encyclopedia of Database Systems.

[50]  James McNames,et al.  Reliability and accuracy of heart rate variability metrics versus ECG segment duration , 2006, Medical and Biological Engineering and Computing.

[51]  A. Seidler,et al.  The role of psychosocial stress at work for the development of cardiovascular diseases: a systematic review , 2011, International Archives of Occupational and Environmental Health.

[52]  Changchun Liu,et al.  An empirical study of machine learning techniques for affect recognition in human–robot interaction , 2006, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[53]  V. Vuksanović,et al.  Heart rate variability in mental stress aloud. , 2007, Medical engineering & physics.

[54]  Mohammad A. Khalilzadeh,et al.  EMOTIONAL STRESS RECOGNITION SYSTEM FOR AFFECTIVE COMPUTING BASED ON BIO-SIGNALS , 2010 .

[55]  D. KatsisC.,et al.  Toward Emotion Recognition in Car-Racing Drivers , 2008 .

[56]  Heleen Riper,et al.  Efficacy and cost-effectiveness of a web-based and mobile stress-management intervention for employees: design of a randomized controlled trial , 2013, BMC Public Health.

[57]  Daniel Lemire,et al.  Streaming Maximum-Minimum Filter Using No More than Three Comparisons per Element , 2006, Nord. J. Comput..

[58]  S. de Waele,et al.  Experiences with adaptive statistical models for biosignals in daily life , 2009, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops.

[59]  H. Huikuri,et al.  Time domain, geometrical and frequency domain analysis of cardiac vagal outflow: effects of various respiratory patterns. , 2001, Clinical physiology.

[60]  G. Lohmann,et al.  Color-Word Matching Stroop Task: Separating Interference and Response Conflict , 2001, NeuroImage.

[61]  Ricardo Gutierrez-Osuna,et al.  Using Heart Rate Monitors to Detect Mental Stress , 2009, 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks.

[62]  David N. Towers,et al.  The many metrics of cardiac chronotropy: A pragmatic primer and a brief comparison of metrics , 2007, Biological Psychology.

[63]  Teuvo Kohonen,et al.  Improved versions of learning vector quantization , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[64]  rlene Minkiewicz,et al.  Objective measures , 1997 .

[65]  J. Gruzelier,et al.  A Review of the Impact of Hypnosis, Relaxation, Guided Imagery and Individual Differences on Aspects of Immunity and Health , 2002, Stress.