K-Means Clustering: Implementation, Issues, and Approaches in WSN
Computational Intelligence and Machine Learning · 2026 · 7 (1)
DOI: 10.36647/ciml/07.01.a005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Intelligence and Machine Learning, 2026. Verfasst von Ab Wahid Bhat und 1 weiteren Autor:innen.
Abstract (Originalsprache)
In wireless Sensor Networks (WSNs), energy optimization and efficient routing are NP-Hard problems. Organizing sensor nodes into small clusters with a local coordinator for the collection, aggregation, and transmission of data can reduce energy consumption and prolong the lifetime of WSNs. However, the uniform and balanced clustering of nodes is a challenging task in designing an energy-efficient clustering and routing protocol. One of the simplest yet efficient clustering algorithms that can be employed in WSNs is the K-means algorithm. The paper presents a detailed discussion on the implementation of the K-means algorithm, limitations, and solutions that can be adopted to enhance its performance. The primary objective is to provide a detailed insight into the various approaches employed in WSNs for addressing the limitations of the K-means algorithm. In addition to it, different metrics for evaluating the clustering efficiency of an algorithm are discussed in detail. A tabular review of the characteristics of various modified algorithms, which combine K-means and probabilistic, deterministic, and metaheuristic techniques, is also presented at the end of the work.
Zitieren
APA
Bhat, A. W., & Passi, A. (2026). K-Means Clustering: Implementation, Issues, and Approaches in WSN. Computational Intelligence and Machine Learning, 7(1). https://doi.org/10.36647/ciml/07.01.a005
Vancouver
Bhat AW, Passi A. K-Means Clustering: Implementation, Issues, and Approaches in WSN. Computational Intelligence and Machine Learning. 2026;7(1). doi:10.36647/ciml/07.01.a005
BibTeX
@article{Bhat2026,
author = {Bhat, Ab Wahid and Passi, Abhiruchi},
title = {K-Means Clustering: Implementation, Issues, and Approaches in WSN},
journal = {Computational Intelligence and Machine Learning},
year = {2026},
volume = {7},
number = {1},
doi = {10.36647/ciml/07.01.a005}
}
EUVIMED