A Bayesian approach and probabilistic latent variable clustering based web services selection. (2017)

• Record Type: Journal Article
• Authors: Vaitheki, K.; Zayaraz, G.
• Is Part Of: International journal of knowledge engineering and soft data paradigms. Volume 6:Number 1(2017)
• Page Start: 82
• Page End: 93
• Publication Date: 2017
• Subjects: web service -- Bayesian network -- lexical analysis -- probabilistic latent variable clustering -- PLVC; Soft computing -- Periodicals; Statistics -- Periodicals; Information science -- Periodicals; 003.05
• Languages: English
• ISSNs: 1755-3210

Abstract

Web services are the product framework to help interoperable machine to machine connection over a system. There is a constant increase in the number of services and processing the large quantity of data over the web requires the exceptional and an improved service selection and classification approach. The requisite to recommend services are grounded on both functional and non-functional requirements. The user keyword extraction using the lexical analyser may give a better extraction than the traditional keyword based search. The lexical analysis process the input character sequences to produce symbol sequences called tokens. The subsequent tokens are then passed on to some other type of formulating and for use as contribution to different assignments, for example, parsers. The tradition of Bayesian system display that is comprehensively utilised for clustering and classifying, is productive for dealing with the non-missing of services. The probabilistic latent variable clustering (PLVC) technique enhanced with the Bayesian classification improves the probabilistic dependencies amongst the clusters and to carry out the clustering task. This may perform better in relations of parameters like precision, recall, and F-measure. The quality of the cluster is foreseeable to be better in terms of purity and entropy for the proposed algorithm.