Physiological Signals based Day-Dependence Analysis with Metric Multidimensional Scaling for Sentiment Classification in Wearable Sensors

The interaction of the affective has emerged in implicit human-computer interaction. Given the physiological signals in the recognition process of the affective, the different positions by which the physiological signal sensors are installed in the body, along with the daily habits and moods of human beings, influence the affective physiological signals. The scalar product matrix was calculated in this study based on metric multidimensional scaling with dissimilarity matrix. Subsequently, the matrix of individual attribute reconstructs was obtained using the principal component factor. The method proposed in this study eliminates day dependence, reduces the effect of time in the physiological signals of the affective, and improves the accuracy of affection classification.