Book ChapterDOI
Rough K-means Algorithm Based on the Boundary Object Difference Metric
Pengda Zhong,Tengfei Zhang,Xiang Zhang,Xinyuan Hu,Wenfeng Zhang +4 more
- pp 309-318
Reads0
Chats0
TLDR
Zhang et al. as discussed by the authors proposed a new rough k-means algorithm to measure the weight of boundary objects, which considers the distance from boundary objects to their neighbor points and the number of neighbor points together to dynamically calculate the weights of boundary object to clusters that may belong to.Abstract:
Rough k-means algorithm can effectively deal with the problem of the fuzzy boundaries. But traditional rough k-means algorithm set unified weight for boundary object, ignoring the differences between individual objects. Membership degree method of rough fuzzy k-means algorithm is used to measure the membership degree of boundary object to the clusters that they may belong to, ignoring the distribution of neighbor points of the boundary object. So, according to the distribution of neighbor points of the boundary object, we put forward a new rough k-means algorithm to measure the weight of boundary objects. The proposed algorithm considers the distance from boundary objects to their neighbor points and the number of neighbor points of boundary objects together to dynamically calculate the weights of boundary object to clusters that may belong to. Simulation and experiment, through examples verify the effectiveness of the proposed method.read more
References
More filters
Journal ArticleDOI
Enhanced rough-fuzzy c-means algorithm with strict rough sets properties
TL;DR: A modified partition criterion is proposed and Experimental results on synthetic datasets, real-life datasets, and image segmentation problems indicate that the proposed method outperforms its counterparts in most cases.
Book ChapterDOI
Survey of Improved k-means Clustering Algorithms: Improvements, Shortcomings and Scope for Further Enhancement and Scalability
Anand Khandare,A. S. Alvi +1 more
TL;DR: This paper studied some of literatures on improved k-means algorithms, summarized their shortcomings and identified scope for further enhancement to make it more scalable and efficient for large data.
Book ChapterDOI
An extension to rough c -means clustering algorithm based on boundary area elements discrimination
TL;DR: This paper considers the distinction between data points in the boundary area and presents an extended Rough c-means algorithm which benefits from this information and yields more desirable clustering results.
Book ChapterDOI
A New Rough-Fuzzy Clustering Algorithm and its Applications
Sushmita Paul,Pradipta Maji +1 more
TL;DR: A robust rough-fuzzy clustering algorithm is applied here to identify clusters having similar objects and it can find overlapping and vaguely defined clusters with arbitrary shapes in noisy environment.