点击次数：

论文类型：会议论文

发表时间：2014-08-08

收录刊物：EI、Scopus

页面范围：237-242

摘要：An attribute weighted fuzzy c-means algorithm for incomplete datasets is presented in this paper. The nearest-neighbor interval representation proposed in our previous researches is used here to describe the missing attribute values, and the widely used ReliefF algorithm is involved to determine the attribute weights. The proposed algorithm combines the attribute weights and fuzzy clustering by weighted Euclidean distance, and is successfully justified based on benchmark datasets. ? 2015 Taylor & Francis Group, London.