Optimization and Analysis of Clustering Algorithm Based on FCM

Tu, Min; Xu, Yan

doi:10.1109/ecice52819.2021.9645602

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final output fuzzy matrix reflects all the information of the data set, so the distribution and overall characteristics of the data set can be accurately examined [25]. Although, the traditional FCM algorithm has some weaknesses, such as initializing the cluster center, determining the optimal number of clusters and being sensitive to noise, and the realization of FCM depends on the value of the fuzzy index, and the results obtained by using different indexes may be different [26 ]. The most studied is the fuzzy clustering algorithm based on the objective function, which describes the clustering problem as a constrained optimization problem, and determines the fuzzy division and clustering results of the data set by seeking the solution of the optimization problem.…”

Section: Fuzzy C-means (Fcm) Methodsmentioning

confidence: 99%

Research on Efficient Fuzzy Clustering Method Based on Local Fuzzy Granular balls

Xie¹,

Qiao²,

Xia³

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years, the problem of fuzzy clustering has been widely concerned. The membership iteration of existing methods is mostly considered globally, which has considerable problems in noisy environments, and iterative calculations for clusters with a large number of different sample sizes are not accurate and efficient. In this paper, starting from the strategy of large-scale priority, the data is fuzzy iterated using granularballs, and the membership degree of data only considers the two granular-balls where it is located, thus improving the efficiency of iteration. The formed fuzzy granular-balls set can use more processing methods in the face of different data scenarios, which enhances the practicability of fuzzy clustering calculations.

show abstract

Section: Fuzzy C-means (Fcm) Methodsmentioning

confidence: 99%