classification of web services using bayesian network使用贝叶斯网络分类的web服务.pdfVIP

Journal of Software Engineering and Applications, 2012, 5, 291-296 291 /10.4236/jsea.2012.54034 Published Online April 2012 (http://www.SciRP.org/journal/jsea) Classification of Web Services Using Bayesian Network 1* 2 3 Ramakanta Mohanty , V. Ravi , M. R. Patra 1Computer Science Department, MLR Institute of Technology, Hyderabad, India; 2Institute for Development and Research in Bank- ing Technology, Hyderabad, India; 3Computer Science Department, Berhampur University, Berhampur, India. * Email: ramakanta5a@, rav_padma@, mrpatra12@ th st th Received December 17 , 2011; revised January 31 , 2012; accepted February 15 , 2012 ABSTRACT In this paper, we employed Naïve Bayes, Markov blanket and Tabu search to rank web services. The Bayesian Network is demonstrated on a dataset taken from literature. The dataset consists of 364 web services whose quality is described by 9 attributes. Here, the attributes are treated as criteria, to classify web services. From the experiments, we conclude that Naïve based Bayesian network performs better than other two techniques comparable to the classification done in literature. Keywords: Web Services; Quality of Services (QoS); Bayesian Network; Naïve Based Bayesian; Markov Blanket and Tabu Search 1. Introduction with the service over HTTP attributes [2]. In this study, we address this problem of efficiently Services are tendered and availed in almost all the busi- identifying a set quality