Proposed new signal for real-time stress monitoring: Combination of physiological measures

Document Type : Research Article


1 Research Center of Development Advanced Technologies, Khaje Nasir al din Tusi, Tehran, Iran

2 Research Center of Development Advanced Technologies, Khaje Nasir al din Tusi, Tehran, Iran Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran


Human stress is a physiological tension that appears when a person responds to mental, emotional, or physical chal-lenges. Detecting human stress and developing methods to manage it, has become an important issue nowadays. Au-tomatic stress detection through physiological signals may be a useful method for solving this problem. In most of the earlier studies, long-term time window was considered for stress detection. Continues and real-time representation of the stress level is usually done through one physiological signal. In this paper, a real-time stress monitoring system is pro-posed which shows the user a new signal for feedback stress level. This signal is combined of weighted features of gal-vanic skin response and photoplethysmography signals. The features are defined in 20-sec time windows. Correlation feature selection and linear regression methods are used for feature selection and feature combination respectively. Furthermore, a set of experiments was conducted for training and testing of the proposed model. The proposed model can represent the relative stress level perfectly and has 79% accuracy for classifying the stress and relaxation phases into two categories by a determined threshold.


Main Subjects

[1]Liao, W., et al. A real-time human stress monitor-ing system using the dynamic bayesian network. in Computer Vision and Pattern Recognition-Workshops, 2005. CVPR Workshops. IEEE Com-puter Society Conference on. 2005. IEEE.
[2]Sun, F.-T., et al., Activity-aware mental stress de-tection using physiological sensors, in Mobile Computing, Applications, and Services, Springer. p. 211-230, 2012.
[3]Deng, Y., et al., An Investigation of Decision Ana-lytic Methodologies for Stress Identification. The International Journal on Smart Sensing and Intel-ligent Systems. 6(4), 2012.
[4]Kocielnik, R., et al. Smart technologies for long-term stress monitoring at work. in Computer-Based Medical Systems (CBMS), 2013 IEEE 26th International Symposium on. IEEE.2013
[5]Sharma, N. and T. Gedeon, Objective measures, sensors and computational techniques for stress recognition and classification: A survey. Comput-er Methods and Programs in Biomedicine, 108(3): p. 1287-1301, 2012
[6]Jovanov, E., et al., Stress monitoring using a dis-tributed wireless intelligent sensor system. Engi-neering in Medicine and Biology Magazine, IEEE, 22(3): p. 49-55, 2003
[7]Healey, J. and R. Picard. SmartCar: detecting driver stress. in Pattern Recognition, 2000. Pro-ceedings. 15th International Conference on, IEEE, 2000
[8]Shi, Y., et al. Personalized stress detection from physiological measurements. in International symposium on quality of life technology. 2010.
[9]Ohsuga, M., F. Shimono, and H. Genno, Assess-ment of phasic work stress using autonomic indi-ces. International Journal of Psychophysiology. 40(3): p. 211-220, 2001
[10]Angus, F., J. Zhai, and A. Barreto. Front-end ana-log pre-processing for real-time psychophysiolog-ical stress measurements. in Proceedings of the 9th World Multi- Conference on Systemics, Cybernetics, and Informatics (WMSCI 05). 2005.
[11]Healey, J.A., and R.W. Picard, Detecting stress during real-world driving tasks using physiological sensors. Intelligent Transportation Systems, IEEE Transactions on. 6(2): p. 156-166, 2005.
[12]Zhai, J., et al. Realization of stress detection using psychophysiological signals for improvement of human-computer interactions. in SoutheastCon, 2005. Proceedings. IEEE, 2005.
[13]Zhai, J. and A. Barreto. Stress detection in com-puter users based on digital signal processing of noninvasive physiological variables. in Engineer-ing in Medicine and Biology Society, 2006. EMBS’06. 28th Annual International Conference of the IEEE. 2006.
[14]Akbas, A., Evaluation of the physiological data indicating the dynamic stress level of drivers. Sci-entific Research and Essays. 6(2): p. 430-439, 2011.
[15]Zhang, L., et al. Hierarchical multiple sensor fu-sion using structurally learned Bayesian network. in Wireless Health 2010, ACM, 2010.
[16]Bakker, J., M. Pechenizkiy, and N. Sidorova. What’s your current stress level? Detection of stress patterns from GSR sensor data. in Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference on. IEEE, 2011.
[17]Storm, H., Development of emotional sweating in preterms measured by skin conductance changes. Early human Development, 62(2): p. 149-158, 2001
[18]De Santos, A., et al., Real-Time Stress Detection by Means of Physiological Signals, in Recent Ap-plication in Biometrics, J. Yang, Editor, p. 24-44, 2011.
[19]Wu, W.G., Yeongjoon; Lee, Jungtae, Combina-tion of Wearable Multi-Biosensor Platform and Resonance Frequency Training for Stress Man-agement of the Unemployed Population. Sensors, 12(10): p. 13225-13248, 2012.
[20]Deng, Y., et al., An Investigation of Decision Ana-lytic Methodologies for Stress Identification. The International Journal on Smart Sensing and Intel-ligent Systems (ISSN: 1178-5608), 6(4), 2013
[21]Harris, J.C. and A.D. McQuarrie, The preliminary credibility assessment system embedded algo-rithm description and validation results, in Johns Hopkins University Applied Physics Laboratory Report Number GED. 2009.
[22]Kircher, J. and D. Raskin, The computerized pol-ygraph system II (Software Version 4.01), in Sci-entific Assessment Technologies, Salt Lake City, Utah (USA). 2003.
[23]Kim, K.H.B., S. W. ;Kim, S. R. , Emotion recog-nition system using short-term monitoring of physiological signals. Medical and Biological En-gineering & Computing, 42: p. 419–427, 2004.