CKmeans and FCKmeans : Two deterministic initialization procedures for Kmeans algorithm using a modified crowding distance
This paper presents two novel deterministic initialization procedures for K-means clustering based on a modified crowding distance. The procedures, named CKmeans and FCKmeans, use more crowded points as initial centroids. Experimental studies on multiple datasets demonstrate that the proposed approach outperforms Kmeans and Kmeans++ in terms of clustering accuracy. The effectiveness of CKmeans and FCKmeans is attributed to their ability to select better initial centroids based on the modified crowding distance. Overall, the proposed approach provides a promising alternative for improving K-means clustering.
Code (1)
Tasks
ClusteringSimilar Papers 제목 키워드 기반
Notes on using Determinantal Point Processes for Clustering with Applications to Text Clustering
In this paper, we compare three initialization schemes for the KMEANS clustering algorithm: 1) random initialization (KMEANSRAND), 2) KMEANS++, and 3) KMEANSD++. Both KMEANSRAND and KMEANS++ have a major that the value o…
ClusteringPoint ProcessesText Clusteringl1-norm regularized l1-norm best-fit lines
In this work, we propose an optimization framework for estimating a sparse robust one-dimensional subspace. Our objective is to minimize both the representation error and the penalty, in terms of the l1-norm criterion. G…
CPURecombinator-k-means: An evolutionary algorithm that exploits k-means++ for recombination
We introduce an evolutionary algorithm called recombinator-$k$-means for optimizing the highly non-convex kmeans problem. Its defining feature is that its crossover step involves all the members of the current generation…
ClusteringMSD-Kmeans: A Novel Algorithm for Efficient Detection of Global and Local Outliers
Outlier detection is a technique in data mining that aims to detect unusual or unexpected records in the dataset. Existing outlier detection algorithms have different pros and cons and exhibit different sensitivity to no…
ClusteringOutlier DetectionPre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks
We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the first forward pass, Pre-Warm extracts mean-centered local patches f…