基因表达式编程(GEP)是基于遗传算法和遗传编程的具有更强数据处理和知识发现的进化算法。介绍了传统GEP算法的基本原理和关键技术,针对求解问题时传统GEP存在未成熟收敛和进化后期收敛速度慢等问题,提出了GEP算法的改进方法,并将改进算法应用于函数发现问题中。与传统GEP算法的对比试验表明改进的GEP算法具有更好的求解能力和更高的性能。
Gene Expression Programming (GEP) is a powerful evolutional method derived from genetic algorithm and genetic programming for modal learning and knowledge discovery. The basic principle and key technology of gene expression programming is introduced in this paper. According to the problems of premature convergence and lower convergence speed in later evolutionary period of traditional GEP, an improved GEP algorithm is presented. The new algorithm was applied to function finding problem, results based on a eontrastive experiment to traditional GEP show that the proposed algorithm has better solving ability and higher performance.