基於短時間多生理訊號辨識情緒的特徵選取與特徵萃取方法研究

Feature Selection and Feature Extraction for Emotion Recognition Based on Multiple Short-Time Physiological Signals

戴欣浩(Shin-Hao Dai)

指導教授 ： 余松年

國立中正大學/工學院/電機工程學系/碩士(2015年)

摘要

本研究提出一個基於三種短時間生理訊號的情緒辨識系統，其中包含了心電圖(Electrocardiogram, ECG)、光體積變化描記圖(Photoplethysmprgraphy, PPG)及皮膚阻抗(Skin Impedance, SI)，分辨五種負面情緒，平常狀態(未受刺激的狀態)、傷心(Sadness)、壓力(Stress)、生氣(Anger)及噁心(Disgust)。
本研究所發展的情緒辨識系統為使用者獨立，系統流程依序為生理訊號擷取、特徵擷取、特徵選取或特徵萃取與分類五個部分。在生理訊號擷取上，共有50名受試者，共有22名男性與28名女性，並使用影像或視覺刺激使用者的情緒。在特徵擷取方面，從生理訊號之刺激區間取出其中20秒做擷取，從心電圖中擷取7大類的特徵；光體積變化描記圖中擷取10大類的特徵；皮膚阻抗中擷取3大類的特徵，使用上述三類生理訊號擷取出140個特徵，目的為找出能夠代表情緒，並排除個體差異的特徵。計算出特徵後將其正規化，使特徵規範在同一動態範圍內。在特徵選取上，利用基因演算法(GA)來進行特徵的選取，目的為找出能夠使準確率最高的特徵子集。而在特徵萃取的部分，本研究比較了主成份分析(PCA)、獨立成份分析(ICA)、線性鑑別分析(LDA)以及三種改良式LDA (OLDA、SLDA、RLDA)的效能，目的為將特徵映射到更具代表性或更有分辨性的維度上。最後分類時採用支持向量機(LIBSVM)，並使用Leave-one-out的方式進行交叉驗證。
在結果方面，特徵選取可以找到一組特徵使得所有資料組合平均準確率達到70.4%；特徵萃取方面將每組資料準確率最佳化後可以得到的平均最佳準確率為67.6%；若將特徵萃取的映射向量以特徵選取的方式挑選，再將每組資料準確率最佳化後之平均最佳準確率為95.2%。

關鍵字

特徵選取 ； 皮膚阻抗 ； 光體積變化描記圖 ； 心電圖 ； 情緒辨識系統 ； 特徵萃取 ； 支持向量機

並列摘要

In this paper, we proposed an emotion recognition system based on three short-time physiological signals. Electrocardiogram (ECG), Photoplethysmorgraphy (PPG) and Skin Impedance (SI) were used to recognize five kinds of negative emotions, including neutral (non-stimulated state), sad, stress, anger and disgust.
In our study, we aimed to develop a user-independent system. This emotion recognition system was composed of data acquisition (physiological signals), feature calculation, normalization, feature selection or feature extraction, and classification. First, in the data acquisition part, 50 subjects were recruited to participate in this study, including 22 males and 28 females. By employing visual and audio stimulation, the subject emotions were induced and the signals were recorded. Second, in the feature calculation part, we calculated 7 types ECG features from wave-form and HRV sequence, 10 types PPG features from wave-form and HRV sequence and 3 types SI features from wave-form and SCR sequence. Totally, 140 features were calculated. Third, we normalized our feature set to the same level. Fourth, in the feature selection part, we performed Genetic Algorithm (GA) to select the most effective feature set to enhance accuracy. On the other hand, the feature extraction part, we compared the performance of the Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA) and 3 modified LDA (OLDA, SLDA and RLDA) methods in reducing the feature dimensions by mapping the original data to the better subspace. Finally, we used SVM to classify emotions. And we performed leave-one-out scheme for cross validation.
According to the result, the accuracy were 70.4% when using GA feature selector, 67.6% when using OLDA feature extractor, 95.2% when using OLDA feature extractor in combination with the GA feature selector.

並列關鍵字

feature selection ； skin impedance(SI) ； photoplethysmorgraphy(PPG) ； electrocardiogram(ECG) ； emotion recognition system ； feature extraction ； support vector machine(SVM)

參考文獻

[2] K. H. Kim, S. W. Bang, S. R. Kim, "Emotion Recognition System Using Short-term Monitoring of Physiological Signals", Med. Biol. Eng. Compute. Vol. 42, 2004, Page(s): 419-427.

[3] J. Wagner, J. Kim, E. Andre, "From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification", Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on 6-6 July 2005, Page(s): 940–943.

[6] C. E. Osgood, J. G. Suci, P. H. Tannenbaum, "The Measurement of Meaning", The University of Illinois Press, Urbana, 1957.

[7] J. A. Russell, G. Pratt, "A Description of The Affective Quality Attributed to Environments", Journal of Personality and Psychology, Vol.38, No.2, 1980, Page(s): 311-322.

[9] R. W. Picard, E. Vyzas, J. Healey, "Toward Machine Emotional Intelligence: Analysis of Affective Physiological State", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 10, October 2001.