An incremental three-way decisions soft clustering algorithm
- ZHANG Cong, YU Hong
JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2014, 49(08):
Related Articles |
Most of the clustering algorithms reported assume a data set always does not change. However, it is often observed that the analyzed data set changes over time in many applications. To combat changes, we introduce a new incremental soft clustering approach based on three-way decisions theory. Firstly, the interval sets are used to represent a cluster, wherein the upper bound, the border, the lower bound of interval sets corresponding to positive region, boundary region, negative region generated by the three-way decisions respectively, and an initial clustering algorithm is proposed by using representative points. Secondly, to eliminate the influence of the processing order on final incremental clustering results, the incremental data is pre-clustered used the same way. To quickly search similar areas for incremental data, a searching tree based on the representative points is constructed, and the strategies of searching and updating are presented. Finally, the three-way decisions strategy is used to incremental clustering. The results of the experiments show the approach is effective to incremental clustering.