Abstract | ||
---|---|---|
This paper presents an improved single-pass fuzzy c-means algorithm, which is referred to as Weighted Single-Pass Fuzzy c-Means Algorithm Based on Density Peaks (dpwSPFCM). The classical clustering methods can deal with the small-scale data problems rather than the large-scale data problems. In addition, the traditional single-pass fuzzy c-means algorithm is sensitive to the order of input data. In the proposed algorithm, the samples are weighted and reordered according to the density peaks of the data. The dpwSPFCM combines data segmentation and sample weighting technique based on density characteristics, which contributes to getting better clustering results. Experimental results on several UCI datasets have shown that dpwSPFCM has better performance than several well-known algorithms, i.e., FCM, online FCM(OFCM) and single-pass FCM(SPFCM). |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/tencon.2018.8650348 | TENCON IEEE Region 10 Conference Proceedings |
Keywords | Field | DocType |
clustering,single-pass,FCM,weighted,density peaks | Single pass,Kernel (linear algebra),Approximation algorithm,Data segment,Weighting,Computer science,Fuzzy logic,Algorithm,Linear programming,Cluster analysis | Conference |
ISSN | Citations | PageRank |
2159-3442 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yangyang Li | 1 | 209 | 20.02 |
Qi Wang | 2 | 73 | 40.49 |
Kun Ran | 3 | 0 | 0.34 |
Licheng Jiao | 4 | 5698 | 475.84 |