کنفرانس مهندسی برق ایران

صفحه اصلی / سی امین کنفرانس بین المللی مهندسی برق

Clustering of Fuzzy Data Based on Particle Swarm Optimization

نویسندگان :

Najme Ghanbari¹ Seyed-hamid Zahiri² Hadi Shahraki³

1- دانشگاه بیرجند 2- دانشگاه بیرجند 3- دانشگاه سیستان و بلوچستان

کلمات کلیدی :

Clustering،Particle swarm clustering method،Uncertain data،fuzzy data،Similarity value

چکیده :

In this paper, a particle swarm clustering method is suggested for clustering triangular fuzzy data. This clustering method can find fuzzy cluster centers in the proposed method, where fuzzy cluster centers contain more points from the corresponding cluster, the higher clustering accuracy. To compare triangular fuzzy numbers, a similarity criterion based on the intersection area of the fuzzy numbers is used. The performance of the suggested clustering method has been experimented on both fuzzy benchmark and artificial datasets. The experiential results represent that the suggested clustering method can cluster triangular fuzzy datasets well. Experimental results demonstrate that, in almost all datasets, the proposed clustering method provides better results in accuracy when compared to Uncertain K-Means and Uncertain K-medoids algorithms.