An efficient decentralized clustering algorithm for aggregation of noisy multi-mean data

We describe VarClust , a gossip-based decentralized clustering algorithm designed to support multi-mean decentralized aggregation in energy-constrained wireless sensor networks. We empirically demonstrate that VarClust is at least as accurate as, and requires less node-to-node communication (and hen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of heuristics Jg. 21; H. 2; S. 301 - 328
Hauptverfasser: Buadhacháin, Séamus Ó, Provan, Gregory
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Boston Springer US 01.04.2015
Springer Nature B.V
Schlagworte:
Algorithms
Analysis
Artificial Intelligence
Calculus of Variations and Optimal Control; Optimization
Calibration
Clustering
Communication
Energy
Environmental monitoring
Gossip
Graph theory
Graphs
Localization
Management Science
Mathematics
Mathematics and Statistics
Network topologies
Operations Research
Operations Research/Decision Theory
Propagation
Sensors
Studies
Wireless networks
Wireless sensor networks
Gossip-based algorithms
Decentralized clustering
Decentralized aggregation
ISSN:1381-1231, 1572-9397
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We describe VarClust , a gossip-based decentralized clustering algorithm designed to support multi-mean decentralized aggregation in energy-constrained wireless sensor networks. We empirically demonstrate that VarClust is at least as accurate as, and requires less node-to-node communication (and hence consumes less energy) than, a state-of-the-art aggregation approach, affinity propagation. This superiority holds for both the clustering and aggregation phases of inference, and is demonstrated over a range of noise levels and for a range of random and small-world graph topologies.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:1381-1231
1572-9397
DOI:10.1007/s10732-014-9259-9