Anomaly Detection and Improvement of Clusters using Enhanced K-Means Algorithm

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shorewala, Vardhan, Shorewala, Shivam
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915313303420928
author Shorewala, Vardhan
Shorewala, Shivam
author_facet Shorewala, Vardhan
Shorewala, Shivam
contents This paper introduces a unified approach to cluster refinement and anomaly detection in datasets. We propose a novel algorithm that iteratively reduces the intra-cluster variance of N clusters until a global minimum is reached, yielding tighter clusters than the standard k-means algorithm. We evaluate the method using intrinsic measures for unsupervised learning, including the silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index, and extend it to anomaly detection by identifying points whose assignment causes a significant variance increase. External validation on synthetic data and the UCI Breast Cancer and UCI Wine Quality datasets employs the Jaccard similarity score, V-measure, and F1 score. Results show variance reductions of 18.7% and 88.1% on the synthetic and Wine Quality datasets, respectively, along with accuracy and F1 score improvements of 22.5% and 20.8% on the Wine Quality dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Anomaly Detection and Improvement of Clusters using Enhanced K-Means Algorithm
Shorewala, Vardhan
Shorewala, Shivam
Machine Learning
Performance
This paper introduces a unified approach to cluster refinement and anomaly detection in datasets. We propose a novel algorithm that iteratively reduces the intra-cluster variance of N clusters until a global minimum is reached, yielding tighter clusters than the standard k-means algorithm. We evaluate the method using intrinsic measures for unsupervised learning, including the silhouette coefficient, Calinski-Harabasz index, and Davies-Bouldin index, and extend it to anomaly detection by identifying points whose assignment causes a significant variance increase. External validation on synthetic data and the UCI Breast Cancer and UCI Wine Quality datasets employs the Jaccard similarity score, V-measure, and F1 score. Results show variance reductions of 18.7% and 88.1% on the synthetic and Wine Quality datasets, respectively, along with accuracy and F1 score improvements of 22.5% and 20.8% on the Wine Quality dataset.
title Anomaly Detection and Improvement of Clusters using Enhanced K-Means Algorithm
topic Machine Learning
Performance
url https://arxiv.org/abs/2505.24365