為了朝向建構一個不受使用者限制的情緒識別系統。在這篇論文中，我們嘗試找出最能辨別多人情緒的生理特徵。有別於其它研究，我們提出新的特徵，並且找出引出情緒的生理信號片段。
我們在實驗室中透過影片撥放帶給受測者情緒刺激以取得含有情緒反應的生理信號，於情緒分類上使用Shaver提出來的6個人類原始情緒，即愛、傷心、快樂、驚訝、生氣與害怕。在生理信號的分析上，採用了4個生理指標，分別為呼吸(Respiration)，末稍血流量(Blood Volume Pulse)，指溫(Skin Temperature)與肌電位(EMG)。
根據心理學家James提出的問題，我們的研究假設為：情緒的特徵存在於相異人的生理信號上。然而人與人之間生理反應的差異極大，受測者感受到情緒的時間點與程度也不一致。為了發現最能區分情緒的特徵組合，首先於記錄的時序信號中找出受測激之生理信號時序片段的特徵向量，再進行特徵挑選與驗證，依序包含四個主要步驟。第一，採用呼吸做為生理信號切斷的標準，並提出一個基於統計信號變異量的切斷方法。第二，以統計技術、物理表現與建模等方式取出特徵，並進行特徵標準化。第三，根據共同特徵在空間上的群聚特性K-means法分別出受刺激的生理片段。最後，在挑選特徵上，整合線性識別分析(LDA)於循序搜尋演算法(Sequential search strategies)。結果發現，最好的特徵是在呼吸信號頻譜上線性預測建模所得的系數(LPC)，這個我們所提出的特徵使得內部資料交插驗證的識別率達到86%以上，在測試外部資料時達到73.5%。

For building a subject independent emotional recognition system, in this paper, we try to find out the physiological features that can best distinguish people's emotion. Different from other research, we proposed new features, and found out the emotional elicited intervals in physiological time series.
We gather physiological response signals from laboratory experiment through giving subjects six classes of emotional stimulus using movie-clips watch. Shaver’s primitive emotions were adopted for classification included love, sadness, joy, surprised, anger and fear. On analyzing of physiological signals, we adopt 4 indicators that are respiration, Blood Volume Pulse, skin temperature, and EMG.
According to the psychologist James' question, our study is based on the hypothesis: common features exist across individuals. But the difference of physiological responses is great between subjects; even the time points and the degree of experiencing emotion are inconsistent. In order to discover the best combination of features for distinguishing emotions, we find out the feature vector of the elicited part in the physiological time series at first and then select features and validate, mainly include four successive steps. Firstly, we adopt the respiration signal as the standard of physiology segmentation and propose a segmentation algorithm basis on evaluating the changing amount of the signal. Second, implement features through statistic techniques, physical motivation, and model method; and further normalize. Next, using K-means to mining out the elicited partitions according to clustering phenomenon of common features in the space. Finally, join the linear discriminate analysis in the course of Sequential search strategies for feature selection. The result shows, best features are the Linear Predictive Coefficients of respiration power spectrum, the proposed features make the classification rate of the inside data cross-validation more than 86% and up to 73.5% in testing the outside data.

[1] R. Picard, E Vyzaz, and J. Healey, “Toward Machine Emotional Intelligence: Analysis of Affective Physiological State”, IEEE Trans, Pattern Analysis and Machine Intelligence, vo1. 23, no 10, pp. 1175-1191, 2001

[2] J. Healey and R. Picard, “Detecting Stress During Real-World Driving Tasks Using Physiological Sensors”, IEEE Trans, Intelligent Transportation Systems, vol.6, no 2, 2005

[3] J.Scheirer, R. Fernandez, J. Klein, R. W. Picard, “Frustrating the user on purpose: a step toward building an affective computer”, Interacting with Computer 14, pp. 93-118, 2002

[4] K. H. Kim, S. W. Bang, S. R. Kim,“Emotion recognition system using short-term monitoring of physiological signals “, Medical & Biological Engineering & Computing, Vol. 42, 2004

[5] M. I. Restrapo, S. Bhandari, T. Ning, “Classification of Respiration Episodes using Fuzzy Logic”, 2006 IEEE

[6] M. Sardoshti, B. C. Wheeler, K. Badie, and R. Hashemi,” Evaluation of EMG features for movement control of prostheses”,1993 IEEE

[7] J. Healy, Wearable and Automotive Systems for Affect Recognition from Physiology, PHD Thesis, MIT, 2000

[8] L. F. Barrett, ”Discrete Emotions or Dimensions? The Role of Valence Focus and Arou sal Focus”, COGNITION AND EMOTION, 12 (4), pp. 579-599, 1998

[9] P. J. Lang. “The emotion probe: Studies of motivation and attention”, American Psychologist, 50(5): pp. 372-385, 1995

[10] W. Boucsein, Electrodermal Activity, Plenum Press, New York, NY, 1992

[11] P. J. Lang, M. M. Bradley, and B. N. Cuthbert. International affective picture system(IAPS): Technical manual and affective ratings. NIMH Center for the study of Emotion and Attention, University of Florida

[12] J. A. Russell. “A circumplex model of affect”, Journal of Personality and Social Psychology, 39(6):pp. 1161-1178,1980

[13] N. H. Frijda. “The Emotions”, chapter Physiology of Emotion, Cambridge University Press, Cambridge, pp. 124-175., 1986

[14] T. M Cover, P. E.Hart, “Nearest Neighbor Pattern Classification” IEEE Trans. on Information Theory, Vol IT-13, No. 1, pp. 21-27, 1967

[15] D.L. Davies and D.W. Bouldin, “A cluster separation measure”, IEEE Trans. Pattern Analysis. Mach. Intel., vol. 1, pp. 224-227, April 1979

[16] R. W. Levenson, P. Ekman, W.V. Friesen, “Voluntary facial action generates emotion-specific autonomic-nervous system activity”. Psychophysiology, 27, pp. 363-384, 1990

[17] S. Schacter, J. E. Singer. “Cognitive social and physiological determinants of emotional state” Psychological review, 69, pp. 379-399, 1962

[18] R, Plutchik,A. F.Ax, A critique of “Determinants of emotional state by Schachter, J., & Singer, J. E.” Psychophysiology, 4, pp. 79-82, 1967

[19] J. Wagner, J. Kim, E. Andre “From Physiological signals to emotions: implementing and comparing selected methods for feature extraction and classification”, 2005 IEEE

[20] D. Kulic, Elizabeth, Croft, “Affective State Estimation for Human-Robot Interaction”, IEEE Transactions on robotics, vol.23, No.5, October 2007

[21] J. W. Shin, H. M. Seong, D.I. Cha, Y. R. Yoon and H. R. Yoon, “Estimation of stress status using Biosignal and fuzzy theory”, 20th annual international conference of the IEEE Engineering in Medicine and Medicine and Biology Society, Vol.20. No 3, 1998

[22] C. L. Lisetti, F. Nasoz, “Using Noninvasive Wearable Computers to Recognize human emotions from physiological signals”, EURASIP Journal on applied signal processing 11:pp. 1672-1687, 2004

[23] O. Villon, C. Listetti, “Toward Recognizing Individual’s Subjective Emotion from Physiological Signals in Practical Application”, Twentieth IEEE international Symposium on Computer-Based Medical Systems, 2007

[24] C.D. Katsis, N. Katertsidis, G. Ganiatsas, and D. I. Fotiadis, “Toward Emotion Recognition In Car-Racing Drivers:A Biosignal Processing Approach”, “IEEE Transactions on systems, Man and Cybernetics- Part A: Systems and Humans”, Vol. 38, No. 3, 2008

[25] E. Leon, G. Clarke, and V. Callaghan, “Towards a robust real-time emotion detection system for intelligent buildings”, IEE International Workshop, Intelligent Environments, 2005

[26] W.K. Pratt, Digital Image Processing, John Wiley & Sons, pp. 330-333, 1978

[27] P. A. OBrist, A. H. Black, J. Brener, & L. V. Dicara, Cardiovascular psychophysiology (pp. 60-84). Chicago, Aldine,1974

[28] W. James, W. James: Writings 1878-1899, pp. 350-365, The Library of Am.,1992 Original published in 1890

[29] W.B. Cannon,”The James-Lange Theory of Emotions: A Critical Examination and an Alternative Theory,” Am. J. Psychology, vol.39, pp. 106-124,1927

[30] J. Healey and R. Picard, “Digital processing of affective signals”, in “Perceptual computing session”, M.I.T. Medial Lab., Seattle, WA, Tech. Rep. No. 444, 1998

[31] Ortony, A., & Turner, T. J. What's basic about basic emotions? Psychological Review, 97, pp. 315-331, 1999

[32] T. Kailath, "The Divergence and Bhattacharyya Distance Measures in Signal Selection", IEEE Trans. on Communication Technology, vol. 15, pp. 52-60, Feb. 1967.

[33] S. Kullback, and R. A. Leibler, “On information and sufficiency”, Annals of Mathematical Statistics 22: pp. 79-86. 1951

[34] F. Goudail, P Refregier, G Delyon, ”Bhattacharyya distance as a contrast parameter for statistical processing of noisy optical images”, Optical Society of America, 2004

[35] K. A. Brownley, “Cardiovascular psychophysiology”, in Handbook of Psychophysiology, J. T. Cacioppo, L. G. Tassinary, and G. G. Berntson, Eds. Cambridge, U.K. Cambridge University Press, 2000

[36] M. M. Bradley and P. J. Lang, “Measuring emotion: Behavior, feeling and physiology,” in Cognitive Neuroscience of Emotion, New York, NY: Oxford University Press, 2000

[37] A.V. Oppenheim, R.W. Schafer, Discrete-Time Signal Processing, Prentice-Hall, 1989, pp. 447-448.

[38] P. Shaver, J. Schwartz , D. Kirson, O’Connor, “Emotion Knowledge : Further exploration of a prototype approach. Journal of Personality and Social Psychology, 52, pp. 1061-1086

[39] P. Pudil, J. Novovicova, J. Kittler, “Floating Search Method in Feature Selection”, Pattern Recognition Letters, 1994

[40] A. Jain and D. Zongker, “Feature Selection: Evaluation, Application, and Small Sample Performance”, IEEE trans, Pattern Analysis and Machine Intelligence, vol. 19, no.2, 1997

[41] P.D. Wasserman,” Advanced Methods in Neural Computing”, New York: Van Nostrand Reinhold, pp. 35-55, 1993.

[42] M.I. Schlesinger ans V. Hlavac, Ten lectures on statistical and structural pattern recognitin, Kluwer Academic Publishers, 2002

[43] C.W. Hsu and C.J. Lin. “A comparison of methods for multiclass support vector machines”, IEEE Trans. on Neural Network, 13(2),2002

[44] J. Kittler. Feature set search algorithms. In Pattern Recognition and Signal Processing, C.H. Chen, Ed.,Pages41-60, The Netherlands: Sijthoff and Noordhoff, 1978