Ensemble Learning Models for Classification and Selection of Web Services: A Review

Muhammad Hasnain,Seung Ryul Jeong,Imran Ghani,Aitizaz Ali

doi:10.32604/csse.2022.018300

Abstract

This paper presents a review of the ensemble learning models proposed for web services classification, selection, and composition. Web service is an evolutionary research area, and ensemble learning has become a hot spot to assess web services’ earlier mentioned aspects. The proposed research aims to review the state of art approaches performed on the interesting web services area. The literature on the research topic is examined using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) as a research method. The study reveals an increasing trend of using ensemble learning in the chosen papers within the last ten years. Naïve Bayes (NB), Support Vector Machine’ (SVM), and other classifiers were identified as widely explored in selected studies. Core analysis of web services classification suggests that web services’ performance aspects can be investigated in future works. This paper also identified performance measuring metrics, including accuracy, precision, recall, and f-measure, widely used in the literature.

Highlights

Ensemble learning combines multiple classification techniques to achieve a high prediction accuracy than the single classification technique
This paper presents a review of the ensemble learning models proposed for web services classification, selection, and composition
We proposed to define a few research questions as follows: RQ1—What are state-of-the-art approaches that employed ensemble learning models in the context of web services classification and selection? RQ2—What are the challenges to the ensemble learning models in the studied approaches? RQ3—What are the performance metrics reported in the chosen studies?

Summary

Introduction

Ensemble learning combines multiple classification techniques to achieve a high prediction accuracy than the single classification technique. An ensemble learning model is either the same class of classification techniques or different classification techniques. A boosting classification technique similar to a ‘random forest’ (RF) technique can be used to build a more accurate and robust classification model that involves multiple iterations. Web services are designed to enable the interoperable interaction between machines over the network. They are designed loosely for complex distributed software systems with a “service-oriented architecture” framework. The SOA framework is used to build services for end-users or integrate them with other services distributed over a network. Naïve based approach utilizes the sliding window and information gain theory to train the sample collected from web services

Objectives

Methods

Results

Discussion

Conclusion