An Efficient Approach for Selecting QoS-Based Web Service Machine Learning Models Using Topsis

Miguel Angel Quiroz Martinez, Josue Leonardo Moncayo Redin, Erick David Alvarado Castillo, Luis Andy Briones Peñafiel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

With the advancement of Service Oriented Architecture (SOA), web services have gained great popularity playing a vital role in performing daily transactions and information exchange based on the interaction of different applications within or outside through communication protocols, allowing to support the business requirements and data consolidation of any company. With the increase in the number of web services with the same functionalities, the problem that arises is that not all of them are efficient, which makes it difficult to make a decision to select the best ones that meet all the user’s requirements. The problem can be solved by considering the quality of web services to distinguish web services with similar functionality. The objective of this paper proposes several automatic learning models to classify web services in categories according to QoS attributes using a refined data set, then select the best model based on performance criteria through the TOPSIS method. The deductive method and exploratory research technique were applied to study the QWS dataset.

Original languageEnglish
Title of host publicationProceedings of the 27th International Conference on Systems Engineering, ICSEng 2020
EditorsHenry Selvaraj, Grzegorz Chmaj, Dawid Zydek
PublisherSpringer Science and Business Media Deutschland GmbH
Pages172-182
Number of pages11
ISBN (Print)9783030657956
DOIs
StatePublished - 2021
Event27th International Conference on Systems Engineering, ICSEng 2020 - Las Vegas, United States
Duration: 14 Dec 202016 Dec 2020

Publication series

NameLecture Notes in Networks and Systems
Volume182
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference27th International Conference on Systems Engineering, ICSEng 2020
Country/TerritoryUnited States
CityLas Vegas
Period14/12/2016/12/20

Bibliographical note

Funding Information:
Acknowledgments. This work has been supported by the GIIAR research group and the Salesian Polytechnic University of Guayaquil.

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Keywords

  • Machine learning
  • QoS
  • QWS dataset
  • TOPSIS
  • Web services

Fingerprint

Dive into the research topics of 'An Efficient Approach for Selecting QoS-Based Web Service Machine Learning Models Using Topsis'. Together they form a unique fingerprint.

Cite this