An Initialization Method for Clustering Mixed Numeric and Categorical Data Based on the Density and Distance

Ji, Jinchao; Pang, Wei; Zheng, Yanlin; Wang, Zhe; Ma, Zhiqiang

doi:10.1142/s021800141550024x

Cited by 21 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Ji et al proposed two initialization techniques designed for k‐prototypes algorithms . These two techniques were used in the first step of the 2FA‐kprototypes approach to find the initial cluster centers when applying the fuzzy k‐prototypes technique.…”

Section: Cluster Centers Initialization Techniquesmentioning

confidence: 99%

“…Ji et al developed another initialization method for clustering mixed data . The method they proposed is based on the use of density and distance to determine the initial cluster centers.…”

Section: Cluster Centers Initialization Techniquesmentioning

confidence: 99%

“…The membership degrees of each project to each of the generated clusters are then used to assess the similarity between software projects. In spite of their efficiency, fuzzy k‐prototypes type algorithms are known for their sensitivity to the initialization of clustering . In our previous work, 2FA‐kprototypes was implemented using a random initialization (RI).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, Ji et al proposed two techniques to find initial cluster centers for mixed data . Our study evaluates the performance of 2FA‐kprototypes using these two center initialization techniques and compares it with the same 2FA‐kprototypes using a RI over four datasets: ISBSG, COCOMO81, USP05‐FT, and USP05‐RQ.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Analysis of cluster center initialization of 2FA‐kprototypes analogy‐based software effort estimation

Amazal

Idri²,

Abran

2019

J Software Evolu Process

View full text Add to dashboard Cite

Analogy‐based estimation is one of the most widely used techniques for effort prediction in software engineering. However, existing analogy‐based techniques suffer from an inability to correctly handle nonquantitative data. To deal with this limitation, a new technique called 2FA‐kprototypes was proposed and evaluated. 2FA‐kprototypes is based on the use of the fuzzy k‐prototypes clustering technique. Although fuzzy k‐prototypes algorithms are well known for their efficiency in clustering numerical and categorical data, they are sensitive to the selection of initial cluster centers. In this paper, the impact of cluster center initialization on improving the prediction accuracy of 2FA‐kprototypes was analyzed and discussed using two cluster initialization techniques: centrality‐based initialization and density‐based initialization. The performance of 2FA‐kprototypes using these two initialization techniques was evaluated and compared with that of 2FA‐kprototypes using random initialization over four datasets: ISBSG, COCOMO81, USP05‐FT, and USP05‐RQ. The results showed an improvement in the performance of 2FA‐kprototypes in terms of estimation accuracy when the all‐in method is used.

show abstract

Section: Cluster Centers Initialization Techniquesmentioning

confidence: 99%

“…Ji et al developed another initialization method for clustering mixed data . The method they proposed is based on the use of density and distance to determine the initial cluster centers.…”

Section: Cluster Centers Initialization Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of cluster center initialization of 2FA‐kprototypes analogy‐based software effort estimation

Amazal

Idri²,

Abran

2019

J Software Evolu Process

View full text Add to dashboard Cite

show abstract

“…13 The distributed parallel approaches have greatly raised the clustering e±ciency, but these parallel approaches cannot give full play to the e®ect of parallel because of the speed limit of network communication. Sutter and Larus pointed out that, multicore computer systems mostly bene¯t concurrent applications, where little communication exists between the cores.…”

Section: Introductionmentioning

confidence: 99%

Parallel N-Path Quantification Hierarchical K-Means Clustering Algorithm for Video Retrieval

Liao

Zhao

Zheng

et al. 2017

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

Using clustering method to detect useful patterns in large datasets has attracted considerable interest recently. The HKM clustering algorithm (Hierarchical K-means) is very e±cient in large-scale data analysis. It has been widely used to build visual vocabulary for large scale video/image retrieval system. However, the speed and even the accuracy of hierarchical K-means clustering algorithm still have room to be improved. In this paper, we propose a Parallel N-path quanti¯cation hierarchical K-means clustering algorithm which improves on the hierarchical K-means clustering algorithm in the following ways. Firstly, we replace the Euclidean kernel with the Hellinger kernel to improve the accuracy. Secondly, the Greedy N-best Paths Labeling method is adopted to improve the clustering accuracy. Thirdly, the multi-core processors-based parallel clustering algorithm is proposed. Our results con¯rm that the proposed clustering algorithm is much faster and more e®ective.

show abstract

Min‐max kurtosis stratum mean: An improved K‐means cluster initialization approach for microarray gene clustering on multidimensional big data

Pandey

Shukla

2022

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARY Microarray gene clustering is a big data application that employs the K‐means (KM) clustering algorithm to identify hidden patterns, evolutionary relationships, unknown functions and gene trends for disease diagnosis, tissue detection and biological analysis. The selection of initial centroids is a major issue in the KM algorithm because it influences the effectiveness, efficiency and local optima of the cluster. The existing initial centroid initialization algorithm is computationally expensive and degrades cluster quality due to the large dimensionality and interconnectedness of microarray gene data. To deal with this issue, this study proposed the min‐max kurtosis stratum mean (MKSM) algorithm for big data clustering in a single machine environment. The MKSM algorithm uses kurtosis for dimension selection, mean distance for gene relationship identification, and stratification for heterogeneous centroid extraction. The results of the presented algorithm are compared to the state‐of‐the‐art initialization strategy on twelve microarray gene datasets utilizing internal, external and statistical assessment criteria. The experimental results demonstrate that the MKSMKM algorithm reduces iterations, distance computation, data comparison and local optima, and improves cluster performance, effectiveness and efficiency with stable convergence.

show abstract

An Initialization Method for Clustering Mixed Numeric and Categorical Data Based on the Density and Distance

Cited by 21 publications

References 24 publications

Analysis of cluster center initialization of 2FA‐kprototypes analogy‐based software effort estimation

Analysis of cluster center initialization of 2FA‐kprototypes analogy‐based software effort estimation

Parallel N-Path Quantification Hierarchical K-Means Clustering Algorithm for Video Retrieval

Min‐max kurtosis stratum mean: An improved K‐means cluster initialization approach for microarray gene clustering on multidimensional big data

Contact Info

Product

Resources

About