Web Service Ranking and Classification using Intelligent Techniques

In the fastidious ever-growing world of businesses when the constant exchange of web services takes place, it is important for the buyer and seller to understand where their web service stands. A web service is a set of open protocols and standards that allow data to be exchanged between different applications or systems. Web services can be used by software programs written in a variety of programming languages and running on a variety of platforms to exchange data via computer networks such as the Internet in a similar way to inter-process communication on a single computer. The QWS dataset version II is collected from literature which is not having class level. The dataset is normalized using min-max method and employ stratified cross validation to make different fold systems. To make the different web services into different class levels, we employ two different clustering algorithm viz. K-means, and Fuzzy C-means to cluster different web services into different clusters. To test the different class level simulated by clustering algorithm, machine learning algorithm is employed i.e. Genetic Programming (GP), and Random Forest to test the efficacy of the model. From our experimental results, it is observed that C-Fuzzy means clustering provided the best clustering level compared to other techniques. The average accuracy of 99.23% provided by Genetic programming.