Abstract: To efficiently mine the classification rule from database, a novel hybrid classification algorithm based on Particle Swarm Optimization(PSO) and Genetic Algorithm(GA) is proposed. The core idea of the proposed algorithm is as follows: a new rule code with fixed length is proposed, a novel fitness function combined with accuracy, confidence, support and simplicity is constructed, and a hybrid heuristic classifier is accomplished. Experimental results show that the proposed classification algorithm acheives higher classification accuracy and lower running time compared with other classification algorithms.

Key words: data mining, particle swarm, genetic algorithm, classifier, classification rule

摘要： 为了高效地从数据库中挖掘分类规则，提出一种将粒子群优化算法和遗传算法相结合的新算法。该算法的核心思想是对规则的前件进行固定长度编码，适应度函数的计算由分类规则的准确率、置信度、支持度和简洁度构成，从而实现基于两者混合算法的分类器设计。将该分类器与遗传算法分类器和粒子群算法分类器进行对比，实验结果表明，该分类器具有更高的分类准确率以及更快的收敛速度。

关键词: 数据挖掘, 粒子群, 遗传算法, 分类器, 分类规则

CLC Number: 

• TP311