臺灣博碩士論文加值系統

在本論文中提出以模糊向量量化(Fuzzy Vector Quantization, FVQ)建立離散隱藏式馬可夫模型(Discrete Hidden Markov Model, DHMM)進行情緒心電圖信號的辨識，由於不同情緒擁有著不同類型的心電圖，因此利用心電圖來做情緒狀態分析。隱藏式馬爾可夫模型(DHMM)進行情緒判讀，由於該模型可以對一連串時間序列的狀態轉移機率及觀察狀態機率來分析，因此DHMM適合階段特性的情緒階段辨識，而模糊向量量化(FVQ)於本論文主要用來提升情緒辨識系統的辨識率，在情緒辨識系統的訓練以FVQ建立DHMM模型並做DHMM模型的訓練，而在情緒辨識系統的辨識方面以模糊集合找出特徵向量與特徵向量之間的比例並代入以FVQ建立DHMM的訓練模型，以此方式來提升情緒系統的辨識率。從實驗結果可得知，以模糊向量量化(FVQ)建立離散隱藏式馬可夫模型(DHMM)與只有離散隱藏式馬可夫模型(DHMM)相較之下，各情緒的辨識率以及整體正確辨識率皆提升不少。

In our research we propose a Discrete Hidden Markov model (DHMM) for ECG signal recognition method combined with Fuzzy Vector Quantization(FVQ) in ECG signal recognition, because different emotions have different types of electrocardiogram, therefore we use the ECG signals to do emotional state analysis. Discrete Hidden Markov model (DHMM) allows for the analysis of non-stationary multivariate time series by modeling both the emotions state transition probabilities and the probability of observation of a state. Hence, the DHMM is suitable for emotions staging which possesses the properties of successive stage. And the Fuzzy Vector Quantization(FVQ) can improve the recognition rate of emotions staging. The FVQ is used to model DHMM to improve the performance of the DHMM. Finally, Discrete Hidden Markov model (DHMM) for ECG signal recognition method combine with Fuzzy Vector Quantization(FVQ) total classification accuracy recognition rate of the emotion is better than only Discrete Hidden Markov model (DHMM).

目錄
第1章 緒論 1
1.1 研究動機與目的 1
1.2 研究方法 1
第2章 心電圖簡介 3
2.1 心臟構造功能介紹 3
2.2 心電圖量測 4
第3章 心電圖信號處理 10
3.1 情緒定義 10
3.2 情緒狀態資料庫 11
3.3 定位QRS波 12
3.4 心電圖特徵值介紹 13
第4章 情緒辨識研究方法 15
4.1 隱藏式馬可夫模型(HMM) 15
4.1.1 向量量化 16
4.1.2 DHMM模型機率計算 17
4.1.3 DHMM模型訓練 18
4.1.4 DHMM情緒辨識架構 21
4.2 模糊向量量化 21
第5章 實驗方式與結果 26
5.1 實驗資料 26
5.2 實驗流程 29
5.3 實驗數據 30
5.4 實驗結果 31
第6章 結論與展望 47
6.1 結論 47
6.2 未來展望 47
參考文獻 48

[1]https://web.fg.tp.edu.tw/~tfghdb/blog/wp-content/uploads/2016/01/WL19_pp498-pp519_%E5%BE%9E%E7%94%9F%E7%90%86%E8%A8%8A%E8%99%9F%E5%88%8%E6%9E%90%E5%88%A4%E6%96%B7%E6%83%85%E7%B7%92.pdf
[2]I. Christov, G. Gómez-Herrero, V. Krasteva, I. Jekova, A. Gotchev, and K. Egiazarian,“Comparative Study of Morphological and Time-Frequency ECG Descriptors for Heartbeat Classification,” Med. Eng. Phys., vol. 28, pp. 876-887, 2006.
[3]P. Chazal, M. O’Dwyer, and R. B. Reilly, “Automatic Classification of Heart-beats Using ECG Morphology and Heartbeat Interval Features,” IEEE Trans. on Biomed. Eng., vol. 51, pp. 1196-1206, 2004.
[4]T. Baby shalini, L. Vanitha, “Emotion Detection in Human Beings Using ECG Signals,” International Journal of Engineering Trends and Technology, vol. 4,2013.
[5]T. Mar, S. Zaunseder, J. P. Martinez, M. Llamedo, and R. Poll, “Optimiztion of ECG Classification by Means of Feature Selection,” IEEE Trans. on Biomed. Eng., vol. 58, no. 8, pp. 2168-2177, 2011.
[6]J. Dai, “Hybrid Approach to Speech Recognition Using Hidden Markov Models and Markov Chains,” IEE Proc.-Vis. Image Signal Process., vol. 141, pp. 273-279, 1994.
[7]V. Krishnamurthy, J. B. Moore, and S. H. Chung, “Hidden Markov Model Signal Processing in Presence of Unknown Deterministic Interferences,” IEEE Trans. On Automatic Control, vol. 38, no. 1, pp. 146-152, 1993.
[8]D. J. Miller, and M. S. Park, “A Sequence-Based Approximate MMSE Decoder for Source Coding Over Noisy Channels Using Discrete Hidden Markov Models,” IEEE Trans. on Communications, vol. 46, no. 2, pp. 222-231, 1998.
[9]Y. Bengio, V. P. Lauzon, and R. Ducharme, “Experiments on the Application of IOHMMs to Model Financial Returns Series,” IEEE Trans. on Neural Networks, vol. 12, no. 1, pp. 113-123, 2001.
[10]https://activity.ntsec.gov.tw/lifeworld/doc/62%E5%BF%83%E8%87%9F%E7%%9A%84%E6%A7%8B%E9%80%A0%E8%88%87%E5%8A%9F%E8%83%BD.pdf
[11]“Heart Function,” The Permanente Medical Group
https://www.permanente.net/homepage/kaiser/pages/f63363.html
[12]https://www.dcbiomed.com/proimages/materials/Brochures_and_related_Articles/Introductory_guide_to_ECG_C2_0-950820.pdf
[13]https://zh.wikipedia.org/wiki/%E5%BF%83%E7%94%B5%E5%9B%BE
[14]https://smallcollation.blogspot.tw/2013/07/electrocardiogram-ekgecg.html#gsc.tab=0
[15]https://www.sci.utah.edu/~macleod/bioen/be6000/labnotes/ecg/descrip.html
[16]https://compharm.net/ecg_scanner/basics/
[17]https://www.nottingham.ac.uk/nursing/practice/resources/cardiology/function/chest_leads.php
[18]K. Grauer, “ECG Interpretation Review #34,” ECG Interpretation, 2012. http://ecg-interpretation.blogspot.tw/2012/01/ecg-interpretation-review-34-acute- mi.html
[19]J. Wagner, J. Kim, E. André. “From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification,” In IEEE International Conference on Multimedia & Expo, 2005.
[20]“ECG Segments,” wb-CME: Electrocardiography Primer
https://www.education.science-thi.org/edu_ecg/ecginclinicalpractice/normalecg/ecgsections/index.html
[21]https://www.shute.kh.edu.tw/~healthcare/U20030302001/
[22]https://nccur.lib.nccu.edu.tw/bitstream/140.119/39193/6/102506.pdf
[23]A. Ortony, T. J. and Turner. “What’s basic about basic emotions?, ” Psychological Review, Vol. 97, No. 3, 315-331, 1990
[24]Pediatric ECG Cases,” Medscape Reference
http://reference.medscape.com/features/slideshow/ped-ecg
[25]J. A. Healey: Wearable and Automotive Systems for Affect Recognition from Physiology, PhD thesis, MIT, Cambridge, MA, May 2000
[26]R. W. Picard, E. Vyzas, and J. Healey: Toward Machine Emotional Intelligence : Analysis of Affective Physiological State, IEEE Transactions Pattern Analysis and Machine Intelligence, Vol.23, No.10, pp.1175-1191, Oct. 2001
[27]A. Haag, S. Goronzy, P. Schaich, J. Williams: Emotion Recognition Using Bio-Sensors: First Step Towards an Automatic System, Affective Dialogue Systems, Tutorial and Research Workshop, Kloster Irsee, Germany, June 14-16, 2004.
[28]E. Vyzas, R.W. Picard: Affective pattern classification. Florida, MIT Media Laboratory Perceptual Computing Section Technical Report, pp.473, 1998.
[29]R. W. Picard, E. Vyzas, J. EY “Toward machine emotional intelligence analysis of affective physiological state,” IEEE Transactions Pattern Analysis and Machine Intelligence,1175-1191, 2001.
[30]L. Li, J. Chen. “Emotion Recognition Using Physiological Signals from Multiple Subjects”. Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP'06), 355-358, 2006.
[31]L. Xun, G. Zheng, “ECG Signal Feature Selection for Emotion Recognition,” TELKOMNIKA, Vol.11, No.3, pp. 1363 ~ 1370, March 2013
[32]M. Dorigo, G. di Caro, “The ant colony optimization meta-heuristic,” New Ideas in Optimization, McGraw-Hill, London, pp. 11-32, 1999.
[33]P. Blunsom, “Hidden Markov Model,” The University of Melbourne, Department of Computer Science and Software Engineering, 19th August 2004.
https://www.cs.mu.oz.au/460/2004/materials/hmm-tutorial.pdf
[34]W. Pedrycz, and K. Hirota, “Fuzzy vector quantization with the particle swarm optimization: A study in fuzzy granulation–degranulation information processing,” Signal Processing, Vol. 87, pp. 2061–2074, 2007.