Quantitative and qualitative similarity measure for data clustering analysis

Tools

AlShaqsi, Jamil, Wang, Wenjia, Drogham, Osama and Alkhawaldeh, Rami S. (2024) Quantitative and qualitative similarity measure for data clustering analysis. Cluster Computing, 27 (10). pp. 14977-15002. ISSN 1386-7857

Full text not available from this repository. (Request a copy)

Abstract

This paper introduces a novel similarity function that evaluates both the quantitative and qualitative similarities between data instances, named QQ-Means (Qualitative and Quantitative-Means). The values are naturally scaled to fall within the range of − 1 to 1. The magnitude signifies the extent of quantitative similarity, while the sign denotes qualitative similarity. The effectiveness of the QQ-Means for cluster analysis is tested by incorporating it into the K-means clustering algorithm. We compare the results of the proposed distance measure with commonly used distance or similarity measures such as Euclidean distance, Hamming distance, Mutual Information, Manhattan distance, and Chebyshev distance. These measures are also applied to the classic K-means algorithm or its variations to ensure consistency in the experimental procedure and conditions. The QQ-Means similarity metric was evaluated on gene-expression datasets and real-world complex datasets. The experimental findings demonstrate the effectiveness of the novel similarity measurement method in extracting valuable information from the data.

Item Type:	Article
Uncontrolled Keywords:	clustering analysis,clustering purity,k-means clustering,quantitative and qualitative similarity,similarity measure,software,computer networks and communications ,/dk/atira/pure/subjectarea/asjc/1700/1712
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and AI
Related URLs:	http://www.scopus.com/inward/record.url?...
Depositing User:	LivePure Connector
Date Deposited:	29 Nov 2024 01:52
Last Modified:	02 Dec 2024 01:44
URI:	https://ueaeprints.uea.ac.uk/id/eprint/97824
DOI:	10.1007/s10586-024-04664-4

Actions (login required)

View Item