A probability and integrated learning based classification algorithm for high-level human emotion recognition problems

In this paper, a probability and integrated learning (PIL) based classification algorithm is proposed for solving high-level human emotion recognition problems. Firstly, by simulating human thinking mode and construction, a novel topology of integrated learning is proposed to obtain the essential material basis for analyzing the complex human emotions. Secondly, classification algorithm based on PIL is presented to adapt the emotion classification fuzziness caused by the emotional uncertainty, which is realized by calculating the confidence interval of the classification probability. This paper also presented three new analyses methods based on classification probability including the emotional sensitivity, emotional decision preference and emotional tube. Our study expects that the proposed method could be used in the affective computing for video, and may play a reference role in artificial emotion established for robot with a natural and humanized way.