系統識別號 U0026-0608201015091200
論文名稱(中文) 以高信任階層式策略進行心電訊號上的情緒偵測
論文名稱(英文) Using High Confidence Hierarchical Extraction Policy in ECG based Emotion Detection
校院名稱 成功大學
系所名稱(中) 電腦與通信工程研究所
系所名稱(英) Institute of Computer & Communication
學年度 98
學期 2
出版年 99
研究生(中文) 吳明翰
研究生(英文) Ming-Han Wu
學號 q3697122
學位類別 碩士
語文別 英文
論文頁數 45頁
口試委員 指導教授-詹寶珠
中文關鍵字 心電訊號  情緒辨識  pLDA  SFFS  mRMR  分類器 
英文關鍵字 ECG  emotion recognition  pLDA  SFFS  mRMR;classifiers 
中文摘要 為了建構一套情緒識別系統,在這篇論文中,我們分辨四種情緒且嘗試找出能夠精確分辨人類情緒的特徵。不同於其他的研究,我們更進一步分析情緒的三個程度大小且採用的生理訊號只有心電圖(ECG),因為心電圖在近日的發展下,容易測量且方便攜帶。
人與人之間對於情緒的生理反應不一定相同,受測者感受到的情緒程度也不一致。為了發現最能區分情緒的特徵組合,首先會從ECG的頻域 (frequency domain)和時域 (time domain)和nonlinear method中進行特徵萃取,再利用統計方式計算出各段情緒的值,最後這些特徵再經由z-score的方法作正規化。特徵經過正規化之後,我們將特徵選取結合pLDA進行分類。在分類中,大多數的分類器比較適合何處理兩類的問題。為了提高辨識率,我們將多類的問題轉換成兩類來處理。在C個類別中,總共會有C!⁄2種組合,如何決定出哪一種組合可以達到最高的辨識率將會是一個問題。如果我們先將最能區分的類別歸類為一組,剩下的類別為一組,由於這兩類較為分開,所以分類時可以得到較高的辨識率。基於這樣的想法,利用高信任階層式的策略,我們在inside-tests可以從77.65%上升到88.583%,提高將近9%的辨識率且在outside-tests可以達到79.349%。三個程度的情緒分類上,在outside-tests中,平靜,高興,悲傷和恐懼可以達到分別是76.19%, 69.6%, 73.214%和73.809%的辨識率。
英文摘要 For building a subject independent emotional recognition system, in this thesis, we classified four emotions and attempt to find the relevant features which can distinguish human’s emotion accurately. Different to other researches, we further classify three levels of each emotion and the physiological signal we adopt is only the ECG, due to the recent development of the ECG, it is much easier to measure and carry.
The reaction of physiological to emotions varies from person to person, the level of the emotion is hard to be consistent either. In order to find the combinations of the features which are the most distinguishable for classifying emotions, we first calculated features from frequency domain, time domain and nonlinear method in ECG. Then we applied statistical methods to calculate the value of each emotion segments and followed by z-score method for feature normalization. After features are normalized, we use feature selection combining pLDA for classification. In classification, most common classifiers are suited in handling the two-class classification. In order to raise the recognition rate, we turn the multiclass problem into a two-class issue. There are C!⁄2 combinations in C classes, the major problem needed to be addressed is how to decide the specific combination that can achieve the highest recognition rate. If we first separate the most distinguishable class as a group and the rest class as a group, the new data can be classified more accurately due to these two groups are much separate. Based on this consideration, by applying high confidence hierarchical extraction policy, we raise nearly 9% from the inside-tests that is 77.65% to 88.583%, and the outside-test is 79.349%. For three levels of each emotion classification, the emotion level of calm, joy, sad and fear in outside-test is 76.19%, 69.6%, 73.214% and 73.809%, respectively.
論文目次 1. Introduction 1
1.1 Related Research 2
2. Experiment Protocol 6
2.1 Emotion model 6
2.1.1 Hierarchical Structure 6
2.1.2 Basic Emotion Categories 7
2.2 Four Emotion Inducing Experiments 7
2.3 Subjects 9
3. Methodology 10
3.1 Overview 10
3.2 Electrocardiography (ECG) data gathering and preprocessing 11
3.3 Feature Calculation 12
3.4 Feature Normalization 15
3.5 Feature Selection and Classification 18
3.5.1 Feature transformation - pLDA 18
3.5.2 Feature Selection 20 Feature Selection based Mutual Information (mRMR) 21 Sequential Floating Forward Selection (SFFS) 22
3.5.3 Classifier 26 K nearest neighbor rule (KNN) 26 Support Vector Machine (SVM) 26
3.5.4 Classification 29 Classification for four emotions 29 Feature selection methods (SFFS, mRMR) combining with pLDA 29 High Confidence Hierarchical Extraction Policy 29 Classification for three levels of each emotions 34 Outside tests and selected features for four emotions and three levels of each emotion 35
4. Discussion 41
References 43
參考文獻 [1] Danner DD, Snowdon DA, Friesen WV, “Positive emotions in early life and longevity: findings from the nun study.”, J Pers Soc Psychol, 2001.

[2] Robert W. Levenson, “Autonomic Nervous System Differences among motions.”, Psychological Science, Vol. 3, No. 1, pp. 23-27, 1992.

[3] J.F. Cohn, A.J. Zlochower, J. Lien, and T. Kanade, ªAutomated Face Analysis by Feature Point Tracking has High Concurrent Validity with Manual FACS Coding, Psychophysiology, vol. 36, pp. 35-43, 1999.

[4] M. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski, ªMeasuring Facial Expressions by Computer Image Analysis, Psychophysiology, vol. 36, pp. 253-263, 1999.

[5] Yongjin Wang, Ling Guan. “Recognizing Human Emotional State From Audiovisual Signals”, IEEE Transactions on multimedia, nol. 10, no. 4, June 2008

[6] Christos D. Katsis, Nikolaos Katertsidis, George Ganiatsas, and Dimitrios 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, May 2008

[7] J. W. Shin, J.S. Lee1, A.R. Sul, C.G. Lee, Y. R. Yoon, Hiroko Takeuch, Haruyuki Minamitani, “Chronic Stress Evaluation using Neuro-Fuzzy”, Proceedings of the 26th Annual International Conference of the IEEE EMBS San Francisco, CA, USA, September 1-5, 2004

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

[9] 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

[10] S. Schachter, “The Interaction of Cognitive and Physiological Determinants of Emotional State”, Advances in Experimental Psychology, L. Berkowitz, ed., vol. 1, pp. 49-80, 1964.

[11] P. Ekman, R.W. Levenson, and W.V. Friesen, “Autonomic Nervous System Activity Distinguishes Among Emotions”, Science, vol. 221, pp. 1208-1210, Sept. 1983.

[12] 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., pp. 243-286, 1983.

[13] Terrence Fong, Illah Nourbakhsh, Kerstin Dautenhahn, “A survey of socially interactive robots”, Robotics and Autonomous Systems 42 2003

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

[15] 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

[16] 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

[17] Jonghwa Kim, Elisabeth Andre’, “Emotion Recognition Based on Physiological Changes in Music Listening”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 12 Dec. 2008.

[18] Hao Min, Liu Guang Yuan, Ma Chang-wei, Cai Jing, “An Application of Electrocardiography to emotion recognition”, Natural Computation, 2009. ICNC '09. Fifth International Conference on Volume: 5 Digital Object Identifier: 10.1109/ICNC.2009.338 Publication Year: 2009

[19] 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

[20] Lee, C.K.,Yoo, S.K., Park, Y.J., NamHyun Kim, KeeSam Jeong, ByungChae Lee, ” Using Neural Network to Recognize Human Emotions from Heart Rate Variability and Skin Resistance ” Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the Digital Object Identifier: 10.1109/IEMBS.2005.1615734 Publication Year: 2005

[21] Cornelia Setz, Johannes Schumm, Claudia Lorenz, Bert Arnrich, Gerhard Tr¨oster, “Using Ensemble Classifier Systems for Handling Missing Data in Emotion Recognition from Physiology: One Step Towards a Practical System”

[22] 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

[23] R. E. Thayer, The Biopsychology of Mood and Arousal. New York: Oxford Univ. Press, 1989

[24] Jiapu Pan and Willis J. Tompkins. “A Real-time QRS Detection Algorithm.” IEEE transaction on biological Engineering, VOL. BME-32, No. 3, March 1985

[25] M. Brennan, M.Palaniswami, and P. Kamen, “Do Exisiting Measures of Poincare’ Plot Geometry Reflect Nonlinear Features of Heart Rate Variability?” IEEE Transactions On Biomedical Engineering, vol. 48, No. 11, November 2001.

[26] Balakrishnama, S.; Ganapathiraju, A.; Picone, J., “Linear discriminant analysis for signal processing problems”, Southeastcon '99. Proceedings. IEEE Page(s):78 – 81 25-28 March 1999.

[27] Hanchuan Peng, Fuhui Long, and Chris Ding, “Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 8 Aug. 2005.

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

[29] Parthasarathy, G.; Chatterji, B.N., “A class of new KNN methods for low sample problems”, Systems, Man and Cybernetics, IEEE Transactions on Volume 20, Issue 3, pp. 715 – 718, 1990.

[30] Jacobson M., “Time-frequency analysis of heart rate variability.”, Signal Processing and Its Applications, 9th International Symposium pp. 1 – 4, 2007.

[31] Saul JP, Albrecht P, Berger RD, Cohen RJ., “Analysis of long term heart rate variability: methods, 1/f scaling and implications.” IEEE Computer Society, 1987.
  • 同意授權校內瀏覽/列印電子全文服務,於2015-08-20起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2015-08-20起公開。

  • 如您有疑問,請聯絡圖書館