两种改进的粒子群算法在皮肤电信号情感识别中的研究
|
摘要
目前可以采用相关的皮肤电导监控系统来检测人的生理状态,但是有关GSR信号中蕴含的情感信息方面的研究还很少。本文主要研究的是六种情感状态(高兴、惊奇、厌恶、悲伤、愤怒和恐惧)和GSR信号特征之间的对应关系,研究的过程主要分为训练和验证两个阶段。
为建立丰富的GSR情感生理数据库,长期招募被试,并利用精心挑选的能够代表高兴、惊奇、厌恶、悲伤、愤怒和恐惧情感色彩的电影片段激发相应情感,采用Biopac公司生产的多通道生理信号采集仪MP150记录各被试的GSR信号,实验过程中,为确保数据的有效性,主试应该密切关注被试在观看影片时的情况并实时标注,再对采集到的原始GSR信号数据进行滤波、标准化和归一化处理。根据主试的标记和电影片段最能激发相应情感的时间段,选取了若干组有效数据,包括：194组高兴数据、159组惊奇数据、82组厌恶数据、221组悲伤数据、224组愤怒数据和189组恐惧数据,并对上述各组数据进行特征提取,提取了能够代表GSR信号变化的30个统计特征,为下一步的特征选择过程做好准备。
在特征选择过程中,选用了传统的序列后向选择(SBS)算法和两种改进的粒子群智能优化算法,并选用Fisher分类器。在上述过程中,将目标情感看做第一类,而将其他情感看做第二类。针对基本PSO算法容易陷入局部极小的情况,选用改进的两种PSO算法,其中一种是在添加了惯性权重、邻域搜索和交叉变异算子的混合粒子群(Hybrid Particle Swarm Optimization, HPSO)算法,另一种是将生物免疫系统的自调节理念引入到HPSO算法中,将惯性权重设置成自适应调节形式的免疫混合粒子群算法(Immune Hybrid Particle Swarm Optimization, IH-PSO)1。
对比分析上述各特征选择算法寻找到的最优特征组合的验证识别效果,得到的结论如下：
(1)SBS算法和PSO算法均在识别恐惧和惊奇情感时效果尤为明显,在识别厌恶情感时效果不佳；
(2)在识别特定情感时,智能优化算法PSO获得的验证识别效果都优于传统的SBS算法;
(3)采用IH-PSO寻找到的解识别目标情感的正确识别率、第二类情感的正确识别率、最优特征组合的验证适应度都高于HPSO的情况,表明在添加了免疫机制后,能够有效地解决HPSO算法容易陷入局部极值的缺点。
(4)从六种情感中任意挑选两种进行一对一识别研究,共比较了15种组合,将与每种情感相关的最优特征组合结果进行对比,找出了在相应情感识别中的较优特征,然后将其与IH-PSO选择到的最优特征组合中特征组成成分进行了比较,找出相同特征,分析出这些特征时最能够反映各情感变化。
Now galvanic skin response (GSR) monitoring system can be used to detect human physiological states, however, few researches have been done on affective recognition from GSR signal. This paper mainly studies the corresponding relationship between six kinds of affects (happiness, surprise, disgust, grief, anger and fear) and GSR features, and the course of the research is mainly divided into two stages:training and validation.
To build rich GSR affective physiological database, long-term subject recruiting is needed, and carefully selected movie clips are used to stimulate the corresponding affects, namely, happiness, surprise, disgust, grief, anger and fear. then the multi-channel physiological signal acquisition instrument MP150 is used for GSR signal recording. To ensure the validity of data, the experimenters should pay close attention to the subject and make markers while the subject is watching movies. The collected GSR signals will be filtered, standardized and normalized. The selected valid data include:194 groups happiness data,159 group surprise data,82 groups disgust data,221 groups grief data,224 groups anger data and 189 groups fear data.30 statistical features that represent changes of GSR signal are extracted from the selected data, which makes preparation for feature selection.
Traditional sequential backward selection (SBS) algorithm and two improved particle swarm optimization (PSO) algorithms are used for feature selection, respectively. Fisher classifier is adopted in the process of classification, and feature selection results are analyzed and compared. Throughout the process above, the goal affect is seen as the first kind and five other affects as the second. According to the case that basic PSO algorithm is easily get into the local optimum, we choose two kinds of improved PSO algorithms, one is Hybrid Particle Swarm Optimization (HPSO) adding self-adapting inertia, neighborhood search and crossover-mutation operator, the other is called IH-PSO (Immune Hybrid Particle Swarm Optimization) which imports self-adjustment concept of biological immune system and self-adapting inertia set into the HPSO algorithms.
After comparing and analysing the optimal feature combination validation recognition effect of the foregoing feature selection algorithms, we attain the following conclusions:
(1) SBS and PSO algorithms can recognize fear and surprise obviously, while disgust affect recognition effect is not so beautiful.
(2) When we identify particular feelings, the method using intelligent optimization algorithm PSO can obtain superior validation recognition effects to that using traditional SBS algorithm.
(3) Identification verification results of the two improved PSO algorithms has showed that target emotion recognition correct rate, the second type of emotion recognition correct rate, and optimal feature combination validation fitness of IH-PSO solution are all finer than the HPSO situation, which state that it can effectively solve fault easily into local minimum of the HPSO when added immunity mechanism.
(4) In order to find out the optimal features which can represent changes of corresponding affects, we select 15 kinds of one-to-one individuals'identification from the six affects, after comparing each optimal feature combination in one-to-one results, we find out relatively optimal feature in the corresponding affective identification. Finally we compare the one-to-one results with IH-PSO solution to find some characteristics can most reflect the corresponding affective change.
为建立丰富的GSR情感生理数据库,长期招募被试,并利用精心挑选的能够代表高兴、惊奇、厌恶、悲伤、愤怒和恐惧情感色彩的电影片段激发相应情感,采用Biopac公司生产的多通道生理信号采集仪MP150记录各被试的GSR信号,实验过程中,为确保数据的有效性,主试应该密切关注被试在观看影片时的情况并实时标注,再对采集到的原始GSR信号数据进行滤波、标准化和归一化处理。根据主试的标记和电影片段最能激发相应情感的时间段,选取了若干组有效数据,包括：194组高兴数据、159组惊奇数据、82组厌恶数据、221组悲伤数据、224组愤怒数据和189组恐惧数据,并对上述各组数据进行特征提取,提取了能够代表GSR信号变化的30个统计特征,为下一步的特征选择过程做好准备。
在特征选择过程中,选用了传统的序列后向选择(SBS)算法和两种改进的粒子群智能优化算法,并选用Fisher分类器。在上述过程中,将目标情感看做第一类,而将其他情感看做第二类。针对基本PSO算法容易陷入局部极小的情况,选用改进的两种PSO算法,其中一种是在添加了惯性权重、邻域搜索和交叉变异算子的混合粒子群(Hybrid Particle Swarm Optimization, HPSO)算法,另一种是将生物免疫系统的自调节理念引入到HPSO算法中,将惯性权重设置成自适应调节形式的免疫混合粒子群算法(Immune Hybrid Particle Swarm Optimization, IH-PSO)1。
对比分析上述各特征选择算法寻找到的最优特征组合的验证识别效果,得到的结论如下：
(1)SBS算法和PSO算法均在识别恐惧和惊奇情感时效果尤为明显,在识别厌恶情感时效果不佳；
(2)在识别特定情感时,智能优化算法PSO获得的验证识别效果都优于传统的SBS算法;
(3)采用IH-PSO寻找到的解识别目标情感的正确识别率、第二类情感的正确识别率、最优特征组合的验证适应度都高于HPSO的情况,表明在添加了免疫机制后,能够有效地解决HPSO算法容易陷入局部极值的缺点。
(4)从六种情感中任意挑选两种进行一对一识别研究,共比较了15种组合,将与每种情感相关的最优特征组合结果进行对比,找出了在相应情感识别中的较优特征,然后将其与IH-PSO选择到的最优特征组合中特征组成成分进行了比较,找出相同特征,分析出这些特征时最能够反映各情感变化。
Now galvanic skin response (GSR) monitoring system can be used to detect human physiological states, however, few researches have been done on affective recognition from GSR signal. This paper mainly studies the corresponding relationship between six kinds of affects (happiness, surprise, disgust, grief, anger and fear) and GSR features, and the course of the research is mainly divided into two stages:training and validation.
To build rich GSR affective physiological database, long-term subject recruiting is needed, and carefully selected movie clips are used to stimulate the corresponding affects, namely, happiness, surprise, disgust, grief, anger and fear. then the multi-channel physiological signal acquisition instrument MP150 is used for GSR signal recording. To ensure the validity of data, the experimenters should pay close attention to the subject and make markers while the subject is watching movies. The collected GSR signals will be filtered, standardized and normalized. The selected valid data include:194 groups happiness data,159 group surprise data,82 groups disgust data,221 groups grief data,224 groups anger data and 189 groups fear data.30 statistical features that represent changes of GSR signal are extracted from the selected data, which makes preparation for feature selection.
Traditional sequential backward selection (SBS) algorithm and two improved particle swarm optimization (PSO) algorithms are used for feature selection, respectively. Fisher classifier is adopted in the process of classification, and feature selection results are analyzed and compared. Throughout the process above, the goal affect is seen as the first kind and five other affects as the second. According to the case that basic PSO algorithm is easily get into the local optimum, we choose two kinds of improved PSO algorithms, one is Hybrid Particle Swarm Optimization (HPSO) adding self-adapting inertia, neighborhood search and crossover-mutation operator, the other is called IH-PSO (Immune Hybrid Particle Swarm Optimization) which imports self-adjustment concept of biological immune system and self-adapting inertia set into the HPSO algorithms.
After comparing and analysing the optimal feature combination validation recognition effect of the foregoing feature selection algorithms, we attain the following conclusions:
(1) SBS and PSO algorithms can recognize fear and surprise obviously, while disgust affect recognition effect is not so beautiful.
(2) When we identify particular feelings, the method using intelligent optimization algorithm PSO can obtain superior validation recognition effects to that using traditional SBS algorithm.
(3) Identification verification results of the two improved PSO algorithms has showed that target emotion recognition correct rate, the second type of emotion recognition correct rate, and optimal feature combination validation fitness of IH-PSO solution are all finer than the HPSO situation, which state that it can effectively solve fault easily into local minimum of the HPSO when added immunity mechanism.
(4) In order to find out the optimal features which can represent changes of corresponding affects, we select 15 kinds of one-to-one individuals'identification from the six affects, after comparing each optimal feature combination in one-to-one results, we find out relatively optimal feature in the corresponding affective identification. Finally we compare the one-to-one results with IH-PSO solution to find some characteristics can most reflect the corresponding affective change.
引文
[1]. P.Salovery and J.D. Mayer. Emotional Intelligence. Imagination, Cognition and Personality. 1990,9(3):185-211.
[2]. D.Galeman. Emotion Intelligence. New York:Battam Book,1995.
[3]. B.Reeves and C.Nass. The Media Equation. Cambridge Univ. Press, Center for the study of language and Information,1996.
[4]. Rosalind W. Picard. Affective Computing. Perceptual Computing Selection Technical Report, TR 321, MIT Laboratory,1995.
[5]. Rosalind W. Picard情感计算.罗森林译,北京理工大学出版社,2005.
[6].罗森林,潘丽敏.情感计算理论与技术.系统工程与电子技术,2006,25(7)：905-909.
[7].毛峡.情感信息处理.遥测遥控,2000,21(6).
[8].张颖,罗森林.情感建摸与情感识别.计算机工程与应用,2003,33：98-102.
[9]. Rosalind W. Picard. Toward Machine Emotion Intelligence:Analysis of Affective Physiological State. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(10).
[10]. Rosalind W. Picard. Affective Computing. Cambridge, Mass.:The MIT Press,1997.
[11]. K.R.Scherer. Speech and Emotion State. Speech Evaluation in Psychiatry, J.K.Darby, ed., chapter 10, pp:189-220, Grune and Stration, Inc.,1981.
[12]. R. Banse and K.R. Scherer. Acoustic Profiles in Vocal Emotion Expression. J. Personality and Social Psychology,1996,70(3):614-636.
[13]. T. Polzin. Detecting Verbal and Non-Verbal Cues in the Communication of Emotions. PhD thesis, School of Computer Science,2000,6.
[14]. J. Hansen, Comm. during ICASSP '99 Panel on Speech Under Stress. Proc. Int'l Conf. Acoustics, Speech, and Signal Processing '99,1999.
[15]. J.N. Bassili. Emotion Recognition:The Role of Facial Movement and the Relative Importance of Upper and Lower Areas of the Face. J. Personality and Social Psychology,1979,37:2049-2058.
[16]. I.A. Essa. Analysis, Interpretation and Synthesis of Facial Expressions. PhD thesis, Mass. Inst. of Technology, Media Lab,Cambridge, Mass.,1995,02.
[17]. J.F. Cohn, A.J. Zlochower, J. Lien, and T. Kanade. Automated Face Analysis by Feature Point Tracking has High Concurrent Validity with Manual FACS Coding. Psychophysiology,1999, 36:35-43.
[18]. M. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski. Measuring Facial Expressions by Computer Image Analysis. Psychophysiology,1999,36:253-263.
[19]. G. Donato, M.S. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski. Classifying Facial Actions. IEEE Trans. Pattern Analysis and Machine Intelligence, Oct.1999,21(10):974-989.
[20]. J.T. Cacioppo and L.G. Tassinary. Inferring Psychological Significance from Physiological Signals. Am. Psychologist, Jan.1990,45:16-28.
[21]. W. James. William James:Writings 1878-1899. The Library of Am.,1992:350-365.
[22]. W.B. Cannon. The James-Lange Theory of Emotions:A Critical Examination and an Alternative Theory. Am. J. Psychology,1927,39:106-124.
[23]. S. Schachter. The Interaction of Cognitive and Physiological Determinants of Emotional State. Advances in Experimental Psychology, L. Berkowitz, ed.,1964,1:49-80.
[24]. P. Ekman, R.W. Levenson, and W.V. Friesen. Autonomic Nervous System Activity Distinguishes Among Emotions. Science, Sept.1983,221:1208-1210.
[25]. W.M. Winton, L. Putnam, and R. Krauss. Facial and Autonomic Manifestations of the Dimensional Structure of Emotion. J. Experimental Social Psychology,1984,20:195-216.
[26]. A.J. Fridlund and C.E. Izard. Electromyographic Studies of Facial Expressions of Emotions and Patterns of Emotions. Social Psychophysiology:A Sourcebook, J.T. Cacioppo and R.E. Petty,eds.,1983:243-286.
[27]. P. Ekman. An argument for basic emotion. Cognition and Emotion.1992,6:169-200.
[28]. Elias Vyzas and Rosalind W. Picard. Affective Pattern Classification. Perceptual Computing Section Technical Report,1998,473.
[29]. R.W.Picard and J.Healey. Affective wearable. In Proceedings of the First International Symposium on Wearable Computers, Oct,1997, Cambridge, MA.
[30]. Jonghwa Kim and Elisabeth Andr. Emotion Recognition Using Physiological and Speech Signal in Short-Term Observation. E. Andr'e et al. (Eds.):PIT 2006, LNAI 4021, pp.53-64.
[31]. Lan Li and Ji-hua Chen. Emotion Recognition Using Physiological Signals. ICAT 2006. LNCS 4282,2006:437-446.
[32]. R. Edelberg. Electrical properties of the skin. Methods in Psychophysiology, C. C. Brown, Ed. Baltimore, MD:Williams and Wilkins,1967:1-53.
[33]. Liderberg L.Wallin G. Sympathetic skin nerve discharge in relation to amplitude of skin resistence responses. Psychophysiology 1981:18(3):268-270.
[34]. Jocelyn Scheirer, Paul Femandez, Jonathan Klein, Rosalind W. Picard. Frustrating the user on purpose:a step toward building an affective computer. Interacting with Computer.2002,14:93-118.
[35]. A. Haag, S.Goronzy, P. Schaich, and J. Williams. Emotion recognition using Bio-Sensors:First Steps towards an Automatic System. Springer Berlin/ Heidelberg:Emotion Recognition, vol.3068, May.2004, pp.36-48.
[36]. Cheng D F, Liu G Y, Qiu Y H. Application of Particle swarm optimization and K-nearest neighbors to emotion recognition from physiological signals. In pro Int. Computational Intelligence and Security(CIS'08),2008,pp.52-56.
[37]. P. Pudil, J. Novovicova, Kittle. Floating search methods in feature selection. Pattern Recognition Letters, November 1994,15(11):1119-1125.
[38]. Kennedy J, Eberhart C. Particle swarm optimization. Proc. Of IEEE International Conference on Neutral Network, USA:IEEE Press,1995(4):1942-1948.
[39].刘伟兵,王先甲.基于PSO神经网络的进化博弈研究.系统工程与电子技术,2007,29(8)：1282-1284.
[40].傅根跃,陈昌凯.传统测谎技术研究现状于趋势.心理科学与发展,2003,11(1)：108-115.
[41]. Wang GH, et al. Brainstem reticular system and galvanic skin reflex in acute decerebrare cats. J Neurophysiology,1945,8:323.
[42].向亦文,阎克乐,陆运青.大学生皮肤电反应、MMPI及其关系的初步研究.心理学报.2000,32(1)：95～98.
[43]. Nasoz F, Lisetti C L, Alvarez K, Finkelstein N. Emotion recognition from physiological signals for user modeling of affect. In proc.9th Int. International Conference on User Model, Pittsburg, USA, June 2003,22-26.
[44]. Jonghwa Kim and Elisabeth Andr. Emotion Recognition Using Physiological and Speech Signal in Short-Term Observation. E. Andr'e et al. (Eds.):PIT 2006, LNAI 4021, pp.53-64.
[45]. F.Glover and M.laguna, Tabu Search, Kluwer Academic Publishers, Boston,1997.
[46]. J. Kennedy and R. C. Eberhart, Swarm Intelligence. Morgan Kaufmann Publishers.2001.
[47]. Y. Shi and R. C. Eberhart. A modified particle swarm optimizer. Proceedings of the IEEE Congress on Evolutionary Computation (CEC 1998), Piscataway, NJ.1998:69-73.
[48]. M. Clerc and J. Kennedy. The Particle Swarm-Explosion, Stability and Convergence in a Multidimensional Complex Space. IEEE Transactions on Evolutionary Computation, February 2002, 6(1):58-73.
[49]. R.C. Eberhart and Y. Shi. Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization. The 2000 Congress on Evolutionary Computing,2000,1:84-88.
[50].冯林,颜世鹏,孙焘.邻域搜索的粒子群优化算法及其性能分析.计算机工程与科学,28(2006)12,72-73.
[51].杜荣华.一种促进PSO全局收敛的参数调整策略.系统工程与电子技术,2009.6,31(6).
[52].杨淑莹,李兰友.图像模式识别.清华大学出版社,北京交通大学出版社,2006.
[2]. D.Galeman. Emotion Intelligence. New York:Battam Book,1995.
[3]. B.Reeves and C.Nass. The Media Equation. Cambridge Univ. Press, Center for the study of language and Information,1996.
[4]. Rosalind W. Picard. Affective Computing. Perceptual Computing Selection Technical Report, TR 321, MIT Laboratory,1995.
[5]. Rosalind W. Picard情感计算.罗森林译,北京理工大学出版社,2005.
[6].罗森林,潘丽敏.情感计算理论与技术.系统工程与电子技术,2006,25(7)：905-909.
[7].毛峡.情感信息处理.遥测遥控,2000,21(6).
[8].张颖,罗森林.情感建摸与情感识别.计算机工程与应用,2003,33：98-102.
[9]. Rosalind W. Picard. Toward Machine Emotion Intelligence:Analysis of Affective Physiological State. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(10).
[10]. Rosalind W. Picard. Affective Computing. Cambridge, Mass.:The MIT Press,1997.
[11]. K.R.Scherer. Speech and Emotion State. Speech Evaluation in Psychiatry, J.K.Darby, ed., chapter 10, pp:189-220, Grune and Stration, Inc.,1981.
[12]. R. Banse and K.R. Scherer. Acoustic Profiles in Vocal Emotion Expression. J. Personality and Social Psychology,1996,70(3):614-636.
[13]. T. Polzin. Detecting Verbal and Non-Verbal Cues in the Communication of Emotions. PhD thesis, School of Computer Science,2000,6.
[14]. J. Hansen, Comm. during ICASSP '99 Panel on Speech Under Stress. Proc. Int'l Conf. Acoustics, Speech, and Signal Processing '99,1999.
[15]. J.N. Bassili. Emotion Recognition:The Role of Facial Movement and the Relative Importance of Upper and Lower Areas of the Face. J. Personality and Social Psychology,1979,37:2049-2058.
[16]. I.A. Essa. Analysis, Interpretation and Synthesis of Facial Expressions. PhD thesis, Mass. Inst. of Technology, Media Lab,Cambridge, Mass.,1995,02.
[17]. J.F. Cohn, A.J. Zlochower, J. Lien, and T. Kanade. Automated Face Analysis by Feature Point Tracking has High Concurrent Validity with Manual FACS Coding. Psychophysiology,1999, 36:35-43.
[18]. M. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski. Measuring Facial Expressions by Computer Image Analysis. Psychophysiology,1999,36:253-263.
[19]. G. Donato, M.S. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski. Classifying Facial Actions. IEEE Trans. Pattern Analysis and Machine Intelligence, Oct.1999,21(10):974-989.
[20]. J.T. Cacioppo and L.G. Tassinary. Inferring Psychological Significance from Physiological Signals. Am. Psychologist, Jan.1990,45:16-28.
[21]. W. James. William James:Writings 1878-1899. The Library of Am.,1992:350-365.
[22]. W.B. Cannon. The James-Lange Theory of Emotions:A Critical Examination and an Alternative Theory. Am. J. Psychology,1927,39:106-124.
[23]. S. Schachter. The Interaction of Cognitive and Physiological Determinants of Emotional State. Advances in Experimental Psychology, L. Berkowitz, ed.,1964,1:49-80.
[24]. P. Ekman, R.W. Levenson, and W.V. Friesen. Autonomic Nervous System Activity Distinguishes Among Emotions. Science, Sept.1983,221:1208-1210.
[25]. W.M. Winton, L. Putnam, and R. Krauss. Facial and Autonomic Manifestations of the Dimensional Structure of Emotion. J. Experimental Social Psychology,1984,20:195-216.
[26]. A.J. Fridlund and C.E. Izard. Electromyographic Studies of Facial Expressions of Emotions and Patterns of Emotions. Social Psychophysiology:A Sourcebook, J.T. Cacioppo and R.E. Petty,eds.,1983:243-286.
[27]. P. Ekman. An argument for basic emotion. Cognition and Emotion.1992,6:169-200.
[28]. Elias Vyzas and Rosalind W. Picard. Affective Pattern Classification. Perceptual Computing Section Technical Report,1998,473.
[29]. R.W.Picard and J.Healey. Affective wearable. In Proceedings of the First International Symposium on Wearable Computers, Oct,1997, Cambridge, MA.
[30]. Jonghwa Kim and Elisabeth Andr. Emotion Recognition Using Physiological and Speech Signal in Short-Term Observation. E. Andr'e et al. (Eds.):PIT 2006, LNAI 4021, pp.53-64.
[31]. Lan Li and Ji-hua Chen. Emotion Recognition Using Physiological Signals. ICAT 2006. LNCS 4282,2006:437-446.
[32]. R. Edelberg. Electrical properties of the skin. Methods in Psychophysiology, C. C. Brown, Ed. Baltimore, MD:Williams and Wilkins,1967:1-53.
[33]. Liderberg L.Wallin G. Sympathetic skin nerve discharge in relation to amplitude of skin resistence responses. Psychophysiology 1981:18(3):268-270.
[34]. Jocelyn Scheirer, Paul Femandez, Jonathan Klein, Rosalind W. Picard. Frustrating the user on purpose:a step toward building an affective computer. Interacting with Computer.2002,14:93-118.
[35]. A. Haag, S.Goronzy, P. Schaich, and J. Williams. Emotion recognition using Bio-Sensors:First Steps towards an Automatic System. Springer Berlin/ Heidelberg:Emotion Recognition, vol.3068, May.2004, pp.36-48.
[36]. Cheng D F, Liu G Y, Qiu Y H. Application of Particle swarm optimization and K-nearest neighbors to emotion recognition from physiological signals. In pro Int. Computational Intelligence and Security(CIS'08),2008,pp.52-56.
[37]. P. Pudil, J. Novovicova, Kittle. Floating search methods in feature selection. Pattern Recognition Letters, November 1994,15(11):1119-1125.
[38]. Kennedy J, Eberhart C. Particle swarm optimization. Proc. Of IEEE International Conference on Neutral Network, USA:IEEE Press,1995(4):1942-1948.
[39].刘伟兵,王先甲.基于PSO神经网络的进化博弈研究.系统工程与电子技术,2007,29(8)：1282-1284.
[40].傅根跃,陈昌凯.传统测谎技术研究现状于趋势.心理科学与发展,2003,11(1)：108-115.
[41]. Wang GH, et al. Brainstem reticular system and galvanic skin reflex in acute decerebrare cats. J Neurophysiology,1945,8:323.
[42].向亦文,阎克乐,陆运青.大学生皮肤电反应、MMPI及其关系的初步研究.心理学报.2000,32(1)：95～98.
[43]. Nasoz F, Lisetti C L, Alvarez K, Finkelstein N. Emotion recognition from physiological signals for user modeling of affect. In proc.9th Int. International Conference on User Model, Pittsburg, USA, June 2003,22-26.
[44]. Jonghwa Kim and Elisabeth Andr. Emotion Recognition Using Physiological and Speech Signal in Short-Term Observation. E. Andr'e et al. (Eds.):PIT 2006, LNAI 4021, pp.53-64.
[45]. F.Glover and M.laguna, Tabu Search, Kluwer Academic Publishers, Boston,1997.
[46]. J. Kennedy and R. C. Eberhart, Swarm Intelligence. Morgan Kaufmann Publishers.2001.
[47]. Y. Shi and R. C. Eberhart. A modified particle swarm optimizer. Proceedings of the IEEE Congress on Evolutionary Computation (CEC 1998), Piscataway, NJ.1998:69-73.
[48]. M. Clerc and J. Kennedy. The Particle Swarm-Explosion, Stability and Convergence in a Multidimensional Complex Space. IEEE Transactions on Evolutionary Computation, February 2002, 6(1):58-73.
[49]. R.C. Eberhart and Y. Shi. Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization. The 2000 Congress on Evolutionary Computing,2000,1:84-88.
[50].冯林,颜世鹏,孙焘.邻域搜索的粒子群优化算法及其性能分析.计算机工程与科学,28(2006)12,72-73.
[51].杜荣华.一种促进PSO全局收敛的参数调整策略.系统工程与电子技术,2009.6,31(6).
[52].杨淑莹,李兰友.图像模式识别.清华大学出版社,北京交通大学出版社,2006.