New Fuzzy k-NN Classification by Using Genetic Algorithm

摘要：

Fuzzy k-NN classification is well-known in data mining, and genetic algorithm is ever been applied to calculate the parameter k and m of fuzzy k-NN1, named IFKNN. This paper proposes a new fuzzy k-NN classification method by using genetic algorithm(NFKNN), which need less time and increases classification correct rate. We have verified the efficiency of our methods by theoretical analysis and experiments. The experiments are extensive and comprehensive, we compared each improvement with IFKNN, and we also executed the NFKNN on real datasets and obtained the useful results .

关键词： fuzzy k-NN genetic algorithm sample-inside-class sample-edge-of-class

作者: Junli Lu Guang Zhao Cheng Yang Junjia Lu

作者单位: Department of Mathematics and Computer Science,Yunnan University of Nationalities Kunming China Academic Administration Yunnan University of Nationalities Kunming China Academic Administration Southwest Forestry University Kunming China

会议类型: 国际会议

会议名称: 2011 Seventh International Conference on Natural Computation(第七届自然计算国际会议 ICNC 2011)

会议地点: 上海

会议语种:英文

页码: 1137-1141

在线出版日期: 2011-07-26（万方平台首次上网日期，不代表论文的发表时间）