Contrastive Study of Distributed Multitask Fuzzy C-means Clustering and Traditional Clustering Algorithms

Clustering has been widely used in every field,but traditional classical clustering unable to handle multiple tasks at the same time under the scenario of data sets.Comparing with the classical clustering algorithm,the clustering results of Distributed Multitask Fuzzy C-means Clustering(MT-FCM) and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2020 5th International Conference on Communication, Image and Signal Processing (CCISP) S. 239 - 245
Hauptverfasser: Guo, Yanlin, Zi, Yuan, Jiang, Yizhang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.11.2020
Schlagworte:
Clustering algorithms
comparison
Distributed databases
Distributed Multitask Fuzzy C-means Clustering
Indexes
Iterative algorithms
Linear programming
multitask learning
Phase change materials
Task analysis
traditional clustering algorithms
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Clustering has been widely used in every field,but traditional classical clustering unable to handle multiple tasks at the same time under the scenario of data sets.Comparing with the classical clustering algorithm,the clustering results of Distributed Multitask Fuzzy C-means Clustering(MT-FCM) and traditional clustering algorithms can be verified from different multitask scenarios according to the features of MT-FCM algorithm.MT-FCM algorithm is suitable for multitask environment with a moderate number of tasks,in which case the clustering effect is better than that of other traditional clustering algorithms,but there are also non-applicable scenarios by the analysis of experimental results.This experiment not only summarizes and improves the characteristics of the MT-FCM algorithm,but also finds out the shortcomings of the algorithm,which provides a valuable reference for the follow-up research of Distributed Multitask Fuzzy C-means Clustering.
DOI:10.1109/CCISP51026.2020.9273518