A Hybrid Algorithm Combined Genetic Algorithm with Information Entropy for Data Mining
This paper proposes a data mining algorithm based on genetic algorithm and entropy for rule discovery called Genetic- Miner. The goal of Genetic-Miner is to discover classification rules in data sets. We have compared the performance of Genetic-Miner with other two well-known algorithms in six public domain data sets. The results showed that, Genetic-Miner is particularly advantageous when it is important to minimize the number of discovered rules and rule terms in order to improve comprehensibility of the discovered knowledge.
data mining discover knowledge information entropy genetic algorithm
Hua TANG Jun LU
South China Normal University, China National University of Defense Technology, China
国际会议
2nd IEEE Conference on Industrial Electronics and Applications(ICIEA 2007)(第二届IEEE工业电子与应用国际会议)
哈尔滨
英文
2007-05-23（万方平台首次上网日期，不代表论文的发表时间）