Physiological Signals and Recognition of Negative Emotions

In this paper, we try to recognize negative emotions (sadness and disgust) of human affecting driving by using physiological signals that are commonly used to deal with human emotions. To do this, emotional stimuli are used to induce sadness and disgust, and emotion recognition is performed based on the feature vector extracted from the physiological signals collected on the induced emotion by a stimulus. The results of each machine learning algorithm are compared and analyzed for accuracy of emotion recognition. To induce negative emotions, the stimuli are composed 10 set for each emotion and have 95% appropriateness and 9.6 effectiveness. EDA, SKT, ECG and PPG are measured as physiological signals of an emotion and 28 features are extracted through analysis. A machine learning algorithm is applied to emotion recognition based on 28 features and the preferred algorithm is confirmed by comparing recognition results of each algorithm. As a result of emotional recognition, SVM shows the highest in training accuracy and the highest testing accuracy is obtained in LDA. A study of the emotion recognition in this study can be used to analysis the driving situation according to driver 's emotion.