Psychological Stress Evaluation Focus on Individual Difference
1 Institute of Biomedical Engineering, Yanshan University, Qinhuangdao 066004，China
2 Measurement Technology and Instrumentation Key Lab of Hebei Province，Qinhuangdao 066004，China
3 The College of Life Science and BioEngineering, Beijing University of Technology Beijing,100124，China
Abstract：Chronic mental pressure will affect ones health directly by bring a series of pathology and physiology risks. Effective methods of evaluating psychological pressure can detect and assess realtime stress states, warning people to pay a close attention to their health. This paper is focused on the problem of individual difference in the stress evaluation process. An improved support vector machine (SVM) evaluation algorithm in automated valuation of stress/nonstress reaction was proposed based on the measurement of surface myoelectrogram signal. The algorithm clustered the samples and gave the clustering information to the loss function of SVM to achieve training samples’ screening. With the imbalance problem of the two kinds of samples after screening, the weight were given to the loss function to reduce classifier’s prediction tendentiousness, which decreases the error of training sample and makes up for the influence made by the unbalanced samples. The improved algorithm increased the classification accuracy from 70.34% to 79.31%, while algorithm running time was decreased from 2026.5 s to 541.3 s. Experimental results show that the algorithm can effectively avoid the influence resulting from the individual difference on stress appraisal effect. Meanwhile the algorithm reduces the computational complexity.
［1］梁宝勇.精神压力、应对与健康:应激与应对的临床心理学研究 ［M］. 北京:教育科学出版社, 2006: 10-12.
［2］马立骥. 心理评估技术在社区心理咨询中的应用 ［J］. 中国全科医学, 2007, 10(11): 873-875.
［3］Nandita S, Tom G. Objective measures, sensors and computational techniques for stress recognition and classification: a survey ［J］. Computer Methods and Programs in Biomedicine, 2012, 108(3): 1287-1301.
［4］Raul F, Rosalind WP. Modeling drivers’ speech under stress ［J］. Speech Communication, 2003, 40(1-2): 145-159.
［5］Jennifer AH, Rosalind WP. Detecting stress during realworld driving tasks using physiological sensors ［R］. HPL-2004-229, 2004.
［6］Johannes W. Augsburg Biosignal Toolbox ［DB/CP］. http://www.informatik,uniaugsburg.de/de/lehrstuehle/hcm/projects/tools/aubt/, 2013-02-15/2013-03-05.
［7］Gennaro T, Giovanni B, Daniele C, et al. Personal health system architecture for stress monitoring and support to clinical decisions ［J］. Computer Communications, 2012, 35(11): 1296-1305.
［8］Javier H, Rob RM, Rosalind WP. Call center stress recognition with personspecific models ［C］. //Sidney D, Arthur G, eds. Affective Computing and Intelligent Interaction. Berlin: SpringerVerlag, 2011: 125-134.
［9］Cheng Shixiang, Mo Qihong, He Hansong. Effects of office noise on staff health ［J］. Journal of Environment and Health, 2000, 17(3): 154-155.
［10］Helena J, Staffan H, Niklas H. Openplan office noise: cognitive performance and restoration ［J］. Journal of Environmental Psychology, 2011, 31(4): 373-382.
［11］Trevor C. The most terrible sounds of top 10 ［DB/OL］, http://www.sound101.com/, 2012-12-23/2013-03-05.
［12］Annie H, Ase MH, Eva GM, et al. Exposure to negative acts at work, psychological stress reactions and physiological stress response ［J］. Journal of Psychosomatic Research, 2012, 73(1): 47-52.
［13］Vapnik VN. The nature of statistical learning theory second edition ［M］. NewYork: Spinger Verlag, 2000: 132-136.
［14］吴洪兴, 彭宇, 彭喜元. 适用于不平衡样本数据处理的支持向量机方法 ［J］. 电子学报, 2006, 34(S1): 2395-2397.
［15］Li Xin, Wang Yueru. Research on classification method of combining support vector machine and genetic algorithm for motor imagery EEG ［J］. Journal of Computational Information System, 2011, 37(12): 4351-4358.
