人工情感进化模型及其学习算法的研究

Research of artificial emotion evolutionary model and learning algorithm

情感模型的建立可以使计算机具备基本的情感识别和表达能力,在和谐人机交互方面有着广泛的应用。文中对人类情感进行了分析,在此基础上提出了人工情感模型,为了更精确地表达人类情感模型的进化过程,提出改进的遗传算法对模型进行参数的估计,为了克服实数编码遗传算法进化过程易于停滞的缺点,结合个体以及种群的平均适应度两个方面的优点,提出了一种新的改进型交叉算子——启发式加权交叉算子。仿真试验结果表明该算法估计的情感模型符合人类情感的基本规律。

The establish of emotional model can let the computer be equipped with the basic identification and the ability to express emotion, and it has a wide range of applications in the harmony human-machine interaction.This paper has an analysis in human emotion,and proposes artificial emotion models.In order to more accurately express the evolutionary process of the human emotion model,we propose improved genetic algorithm to estimate the parameters of the model.In order to overcome premature convergence of real-coded Genetic Algorithms （GAs）,we combines advantages of the two aspects of individual and population to propose a new crossover operator named Heuristic Weighted Crossover Operator （HWCO）.Simulation results show that the emotional model estimated by the algorithm is in line with the basic law of human emotion.