Selective multiple kernel fuzzy clustering with locality preserved ensemble

Chuanbin Zhang, Long Chen, Yu-Feng Yu, Yin-Ping Zhao, Zhaoyin Shi, Yingxu Wang, Weihua Bai

Abstract: Highlights•Fuzzification and kernel coefficients are selected through an MOO-based method.•Accurate candidate partitions are obtained from the Pareto non-dominated set.•An ensemble approach fuses diverse partitions to derive a consensus matrix.•A Laplacian regularization term is introduced to preserve the data locality.