An accurate emotion recognition system using ECG and GSR signals and matching pursuit method

• Published in: Biomedical Journal Vol. 40; no. 6; pp. 355 - 368
• Main Authors: Goshvarpour, Atefeh, Abbasi, Ataollah, Goshvarpour, Ateke
• Format: Journal Article
• Language: English
• Published: United States Elsevier Limited 01.12.2017; Chang Gung University; Elsevier
• Subjects: Accuracy; Adult; Algorithms; Arousal; Classification; Decomposition; Dictionaries; Discrete cosine transform; Discriminant analysis; EKG; Electrocardiogram; Electrocardiography; Electroencephalography; Emotion recognition; Emotions; Entropy; Female; Fourier transforms; Galvanic Skin Response; Galvanic skin responses; Heart; Humans; Matching; Matching pursuit; Music; Neural networks; Neural Networks (Computer); Original; Physiology; Principal Component Analysis; Principal components analysis; Probabilistic neural network; Quadrants; Respiration; Skin; Sleep; Statistical analysis; Time series; Wavelet transforms; Emotion recognition; Probabilistic neural network; Galvanic skin responses; Electrocardiogram; Matching pursuit
• ISSN: 2319-4170; 2320-2890; 2320-2890
• DOI: 10.1016/j.bj.2017.11.001

The purpose of the current study was to examine the effectiveness of Matching Pursuit (MP) algorithm in emotion recognition. Electrocardiogram (ECG) and galvanic skin responses (GSR) of 11 healthy students were collected while subjects were listening to emotional music clips. Applying three dictionaries, including two wavelet packet dictionaries (Coiflet, and Daubechies) and discrete cosine transform, MP coefficients were extracted from ECG and GSR signals. Next, some statistical indices were calculated from the MP coefficients. Then, three dimensionality reduction methods, including Principal Component Analysis (PCA), Linear Discriminant Analysis, and Kernel PCA were applied. The dimensionality reduced features were fed into the Probabilistic Neural Network in subject-dependent and subject-independent modes. Emotion classes were described by a two-dimensional emotion space, including four quadrants of valence and arousal plane, valence based, and arousal based emotional states. Using PCA, the highest recognition rate of 100% was achieved for sigma = 0.01 in all classification schemes. In addition, the classification performance of ECG features was evidently better than that of GSR features. Similar results were obtained for subject-dependent emotion classification mode. An accurate emotion recognition system was proposed using MP algorithm and wavelet dictionaries.