跳到主要內容

臺灣博碩士論文加值系統

(3.235.120.150) 您好!臺灣時間:2021/08/03 05:00
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:蕭宇純
研究生(外文):Hsiao, Yuchun
論文名稱:以心電圖訊號辨識情緒之特徵萃取與特徵選取之研究
論文名稱(外文):Feature Extraction and Feature Selection for Emotion Recognition Based on Electrocardiogram
指導教授:余松年余松年引用關係
指導教授(外文):Yu, Sungnien
口試委員:黃智宏陳自強江瑞秋余松年
口試委員(外文):Huang, ChihhungChen, TzuchiangChiang, JuichiuYu, Sungnien
口試日期:2012-07-06
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:66
中文關鍵詞:情緒辨識系統心電圖基因演算法支持向量機鑑別性分析
外文關鍵詞:emotion recognition systemelectrocardiogramgenetic algorithmssupport vector machinediscriminant analysis
相關次數:
  • 被引用被引用:3
  • 點閱點閱:765
  • 評分評分:
  • 下載下載:97
  • 收藏至我的研究室書目清單書目收藏:0
本篇論文提出一個基於心電圖(Electrocardiogram, ECG)訊號之情緒辨識系統,所分析的情緒為心理學上歸類的基本七種情緒:平常狀態(一般不受刺激的情緒狀態)、快樂、壓力、悲傷、噁心、生氣、驚訝。
本情緒辨識系統的類別為使用者獨立,系統可分為生理訊號擷取、特徵計算、特徵萃取、特徵選取與分類五個部分。在生理訊號擷取上,採用十個人當受測者擷取資料,實驗環境安靜不受外界打擾,使用的情緒刺激源為觀賞一段二至四分鐘的影片。在特徵計算上,心電圖的特徵包含從心電圖波形算出時域特徵與波形特徵,從HRV 序列算出RRI特徵、Poincare 圖區域特徵、基線區間特徵、非線性特徵、頻域特徵,共七類特徵。研究特別探討特徵萃取和特徵選取的效能,在特徵萃取部分,使用了主成分分析與鑑別性分析,獲取新的特徵矩陣來分類。在特徵選取上,利用逐次反向式搜尋法、逐次正向式搜尋法與基因演算法來保留有效的特徵且移除多餘的特徵,提升正確率。最後採用支持向量機為分類器,再用留一交叉驗證方式一次分出七種情緒。
結果顯示,使用全部特徵搭配支持向量機分類器,正確率可至85.71%,在單類別特徵的正確率中,以Poincare 圖區域特徵正確率最高為78.57%。若是將Poincare 圖區域特徵從全部特徵中移出,只看其餘特徵組合的效能,其正確率為70%。可見得Poincare 圖區域特徵對整體效能有很大的貢獻。以全部65個特徵來做進一步的分析,在特徵萃取的方式中,使用鑑別性分析的正確率較佳,其結果為77.14%。特徵選取的方式中,以使用基因演算法方式的情緒辨識率最好,可達98.57%。但特徵選取留下的特徵個數較多,而特徵萃取可至十個以下,要選擇哪種方式,可再依照設計者需求來決定哪種方式較好。

We proposed an emotion recognition system based on electrocardiogram (ECG) in this study which could recognize seven kinds of emotions, including “Neutral”, “Happy”, “Stress”, “Sad”, “Anger”, “Disgust”, “Surprise”. These emotions have been defined as basic emotions in the psychology.
Our user-independent emotion recognition system can be divided into five parts: data acquisition (physiological signals), feature calculation, feature extraction, feature selection, and classification. In the physiological signal acquisition part, we recorded ECG from10 participants who watched video films of two to four minutes in length for stimulating distinct emotions in a quiet room. Seven categories of features were calculated from the ECG segment, including time-domain features, HRV features, Poincare plot regional features, baseline features, nonlinear features, frequency-domain features, and waveform features. In our research, the performance of feature extractors and feature selectors were especially discussed. Two feature extractors, including principal component analysis (PCA) and discriminant analysis (DA) were applied to reduce feature dimensions from mapping the original data to new subspace. Three feature selectors, including sequential backward selection (SBS), sequential forward selection (SFS), and genetic algorithms (GA), proceeded to select useful features and reduce feature dimensions. Finally, the leave-one-out cross-validation was performed in combination with the support vector machine (SVM) classifier to recognize the seven emotions mentioned from above.
The emotion recognition system using all the 65 features led to a classification rate of 85.71%. When in the single feature category condition, the best system classification rate was 78.57% with Poincare plot regional features. If we removed Poincare plot regional features from the feature set, the classification rate only led to 70.00%, which was considered that the Poincare plot regional features contributed good performance to our system.
In our study, we used those 65 features for further research. When applying the two feature extractors for our system, the classification rates were 77.14% when using DA feature extractor and 72.86% when using PCA feature extractor. On the other side, applying the three feature selectors for the emotion recognition system, when applying the GA feature selector, the classification rate could achieve an average accuracy of 98.57%. Although applying feature selectors to our system led to a high classification rate, the time it took also quite long. As a result, when the designer decided which method to apply, the application purpose became a very important role.

致謝辭 i
摘要 ii
Abstract iii
目錄 1
圖目錄 4
表目錄 6
第一章 緒論 7
1.1 研究動機 7
1.2 相關文獻回顧 8
1.3 論文架構 9
第二章 情緒辨識系統 10
2.1 情緒介紹 10
2.1.1情緒的定義 10
2.1.2情緒的分類 11
2.2 情緒辨識系統簡介 12
2.3 情緒辨識系統類別 13
2.3.1 使用者相依的情緒辨識系統 13
2.3.2 使用者獨立的情緒辨識系統 14
2.4 生理訊號情緒辨識系統 14
2.4.1 生理訊號情緒辨識系統簡介 14
2.4.2 心電圖 15
第三章 研究方法 18
3.1生理訊號擷取 18
3.1.1量測生理訊號的方法 18
3.1.2 訊號擷取的裝置 18
3.1.3 實驗流程 19
3.2特徵計算 21
3.2.1 時域特徵 22
3.2.2 HRV序列特徵 22
3.2.3 Poincare Plot Regional 特徵 23
3.2.4 基線區間特徵 25
3.2.5 非線性特徵 25
3.2.6 頻域特徵 27
3.2.7 波形特徵 28
3.3特徵正規化 31
3.4特徵萃取 31
3.4.1 主成分分析 31
3.4.2 鑑別性分析 32
3.5特徵選取 36
3.5.1 逐次反向式搜尋法 36
3.5.2 逐次正向式搜尋法 37
3.5.3 基因演算法 38
3.6 分類 40
3.6.1支持向量機 40
3.6.2 交叉驗證 43
第四章 實驗結果與討論 44
4.1各個類別特徵結果 44
4.2 特徵萃取的結果與討論 45
4.3 特徵選取的結果與討論 47
4.4 結合特徵萃取與特徵擷取的結果與討論 48
4.4.1 方法一:對特徵萃取結果作特徵選取 48
4.4.2 方法二:對特徵萃取中的映射矩陣作特徵選取 51
4.5 針對實驗結果的進一步分析 52
4.5.1選取到的特徵類別 52
4.6 情緒量表的結果 52
4.7 相關文獻比較 54
第五章 結論與未來發展 55
5.1 結論 55
5.2 未來發展 56
參考文獻 57
附錄 60

參考文獻
[1]Kim, K. H., Bang, S. W., Kim, S. R., “Emotion Recognition System Using Short-term Monitoring of Physiological Signals”, Medical & Biological Engineering & Computing, 2004, Vol. 42, Page(s): 419-427.
[2]Rosalind, W. P., “Toward Machine Emotional Intelligence: Analysis of Affective Physiological State”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 10, 2001, Page(s): 1175-1191.
[3] J. Cai, G. Liu, “The research on emotion recognition from ECG signal,” IEEE Information Technology and Computer Science, vol. 1, pp. 497-500, 2009.
[4] P. Rainville, A. Bechara, N. Naqvi, “Basic emotions are associated with distinct patterns of cardiorespiratory activity” International Journal of Psychophysiology, vol. 61, pp. 5-18, 2006.
[5] Arnold, M.B., “Emotion and Personality”, New York: Columbia Press, 1960.
[6] Mehrabian, A., Russell, J. A., “An Approach to Environmental Psychology”, MIT Press, Cambridge, MA, 1974.
[7]Schwartz, J., Shaver, P. R., “Emotions and emotion knowledge in interpersonal relations. In W. Jones & D. Perlman (Eds.), Advances in personal relationships”, Greenwich, CT: JAI Press, 1987, Vol. 1, Page(s): 197-241.
[8] Ekman, P. and Friesen, W. V., “Constants across cultures in the face and emotion,” Journal of Personality and Social Psychology, 1971, Vol. 17, Page(s): 124-129.
[9]Osgood, C. E., Suci, J. G., Tannenbaum, P.H., “The Measurement of Meaning”, The University of Illinois Press, Urbana, 1957.
[10]Russell, J.A., Pratt, G., “A Description of The Affective Quality Attributed to Environments”, Journal of Personality and Psychology, 1980, Vol. 38, No. 2, Page(s): 311-322.
[11]Russell, J.A., “Emotion Development Lab”, http://www2.bc.edu/~russeljm/
[12] Ekman, P. and Friesen, W. V., “Constants across cultures in the face and emotion,” Journal of Personality and Social Psychology, 1971, Vol. 17, Page(s): 124-129.
[13]Velten, E., “A laboratory task for induction of mood states”, Behavior, 1968.
[14]Lisetti, C., Nasozin, F., “Affective intelligent car interfaces with emotion recognition”, Proceedings of 11th International Conference on Human Computer Interaction, 2005, Vol. 2.
[15]Rosalind, W. P., “Toward Machine Emotional Intelligence: Analysis of Affective Physiological State”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 10, 2001, Page(s): 1175-1191.
[16]Lang, P. J., “Behavioral Treatment and Bio-Behavioral Assessment: Computer Appliances”, In J. H. Johnson J. B. Sidowski, & T. A. Williams (Eds.), Technology in Mental Health Care Delivery Systems., 1980, Page(s): 119-137.
[17]Molina, G.G., Tsoneva, T., Nijholt, A., “Emotional brain-computer interfaces”, Affective Computing and Intelligent Interaction and Workshops, 2009.
[18]周嘉陞, “心電圖學必備”, 合記圖書出版社, 2001.
[19]Brennan, M., Palaniswami, M., Kamen, P., “Do Existing Measures of Poincare Plot Geometry Reflect Nonlinear Features of Heart Rate Variability? “, IEEE Transactions on Biomedical Engineering, 2001, Vol. 48, No. 11, Page(s): 1342-1346.
[20]Pincus, S. M., “Heart rate control in normal and aborted-SIDS infants”, American Journal of Physiology, Vol. 33, 1991, Page(s): 638-646.
[21]Metin, A., “Approximate Entropy and Its Application in Biosignal Analysis “, Nonlinear Biomedical Signal Processing:Dynamic Analysis and Modeling, IEEE Press, 2001, Vol. 2, Page(s): 72-91.
[22]Katz, M. J, “Fractals and Analysis of Waveforms”, computers in biology and medicine 18, 1988, Page(s): 145–156.
[23]Balli, T. and Palaniappan, R., “A Combined Linear & Nonlinear Approach for Classification of Epileptic EEG Signals”, IEEE Engineering in Medicine and Biology Conference on Neural Engineering, 2009, Page(s): 714–717.
[24]Yalcin, I.; Mehmet, K.; “Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure”, Computers in Biology and Medicine 37, 2007, Page(s): 1502-1510.
[25] Rebecca Su, http://home.educities.edu.tw/rebecca0924/stat/pca/index.html
[26] Roger Jang, http://neural.cs.nthu.edu.tw/jang/books/dcpr/doc/lda_chinese.pdf, CS Dept., Tsing Hua University, Taiwan
[27]John Holland, “Adaptation in Natural an Artificial System,” University of Michigan Press, 1975.
[28] C. C. Chang and C. J. Lin, “LIBSVM: a library for support vector machines
”, Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001.
[29] Chang, C. C., Lin, C. J., “a Library for Support Vector Machines”, 2001.
[30]“LIBSVM – A Library for Support Vector Machines”, http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
[31]Shawe-Taylor, N.C.a.J., “An Introduction to Support Vector Machines and
Other Kernel-based Learning Methods”, Cambridge University Press, 2000.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊