Abstract
Electrocardiography (ECG) data acquisition, data preprocessing, feature extraction and emotion recognition based on ECG feature classification were effectively implemented. Joy and sad movies were selected and presented to 154 subjects whose ECG data were recorded at the movie presentation time. The automatic location of QRS complex, which is of critical importance for ECG feature extraction by the computer, was performed by non-linear transformation on the first derivative of the ECG. By means of tabu search, the best combination of the ECG features was selected for classification. The ECG data were classified into certain cluster by Fisher projection.