Identifying Emotion from Natural Walking

To provide a means of identification of human emotion in walking, this paper analyzes the capability of walking activity to reveal a person’s affective states. We obtain pure wrist and ankle accelerometer data, because of redundant information existing in high dimension data, then we set different w(moving average filter window size) and utilize principal component analysis(PCA) to reduce dimension, respectively compare classification accuracy for wrist and ankle with respect to different w value with specific models. In fact, emotion identification from ankle has better performance than wrist. Best accuracy of anger is achieved for Decision Tree with 74% when w is 5, best accuracy of happiness is 85%, and the identification ratio of anger-happy is 85.34%. It is concluded that gait of walking is capable to reveal and identify the emotional state of person when walking.