K-Means and Fuzzy based Hybrid Clustering Algorithm for WSN

Wireless Sensor Networks (WSN) acquired a lot of attention due to their widespread use in monitoring hostile environments, critical surveillance and security applications. In these applications, usage of wireless terminals also has grown significantly. Grouping of Sensor Nodes (SN) is called cluster...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International Journal of Electronics and Telecommunications Ročník 69; číslo 4; s. 793 - 801
Hlavní autori: Angadi, Basavaraj M., Kakkasageri, Mahabaleshwar S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Warsaw Polish Academy of Sciences 01.01.2023
Predmet:
Algorithms
cluster
Clustering
Fuzzy logic
k-means algorithm
Machine learning
Nodes
Sensors
Unsupervised learning
Wireless sensor networks
ISSN:2081-8491, 2300-1933
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Wireless Sensor Networks (WSN) acquired a lot of attention due to their widespread use in monitoring hostile environments, critical surveillance and security applications. In these applications, usage of wireless terminals also has grown significantly. Grouping of Sensor Nodes (SN) is called clustering and these sensor nodes are burdened by the exchange of messages caused due to successive and recurring re-clustering, which results in power loss. Since most of the SNs are fitted with nonrechargeable batteries, currently researchers have been concentrating their efforts on enhancing the longevity of these nodes. For battery constrained WSN concerns, the clustering mechanism has emerged as a desirable subject since it is predominantly good at conserving the resources especially energy for network activities. This proposed work addresses the problem of load balancing and Cluster Head (CH) selection in cluster with minimum energy expenditure. So here, we propose hybrid method in which cluster formation is done using unsupervised machine learning based kmeans algorithm and Fuzzy-logic approach for CH selection.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2081-8491
2300-1933
DOI:10.24425/ijet.2023.147703