A Semi-Supervised Learning Approach to Quality-Based Web Service Classification

The Internet provides a platform for sharing services, and web service brokers help users to choose the suitable service among similar services based on ranking. The quality of service is important in evaluating the services the user needs. However, finding a quality-based data label in many fields...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehdi Nozad Bonab, Jafar Tanha, Mohammad Masdari
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10491237/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832575599289303040
author Mehdi Nozad Bonab
Jafar Tanha
Mohammad Masdari
author_facet Mehdi Nozad Bonab
Jafar Tanha
Mohammad Masdari
author_sort Mehdi Nozad Bonab
collection DOAJ
description The Internet provides a platform for sharing services, and web service brokers help users to choose the suitable service among similar services based on ranking. The quality of service is important in evaluating the services the user needs. However, finding a quality-based data label in many fields can be time-consuming and difficult. Thus, machine learning is required to classify and choose the best service in this field. The selection process is done through analysis and recommendations by the system. This article introduces the SSL-WSC algorithm, which classifies unlabeled data through semi-supervised self-training learning using a small amount of labeled data. This algorithm labels the data using a two-step method of calculating a score for each service and dynamic thresholding. The quality features of web services obtained from the QWS dataset were used to evaluate the performance of the proposed algorithm. The experimental results in different scenarios showed that using proposed semi-supervised learning algorithms to create classification models led to better results, so it improved the F1-score, accuracy, and precision, on average, by 11.26%, 9.43% and 9.53%, respectively, as compared to the supervised method.
format Article
id doaj-art-8d9ab7cce3d14034ac09cc9461102dbc
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8d9ab7cce3d14034ac09cc9461102dbc2025-01-31T23:04:24ZengIEEEIEEE Access2169-35362024-01-0112504895050310.1109/ACCESS.2024.338534110491237A Semi-Supervised Learning Approach to Quality-Based Web Service ClassificationMehdi Nozad Bonab0https://orcid.org/0000-0003-2398-2185Jafar Tanha1https://orcid.org/0000-0002-0779-6027Mohammad Masdari2https://orcid.org/0000-0002-7093-2204Department of Computer Engineering, Islamic Azad University, Urmia Branch, Urmia, IranElectrical and Computer Engineering Department, University of Tabriz, Tabriz, IranDepartment of Computer Engineering, Islamic Azad University, Urmia Branch, Urmia, IranThe Internet provides a platform for sharing services, and web service brokers help users to choose the suitable service among similar services based on ranking. The quality of service is important in evaluating the services the user needs. However, finding a quality-based data label in many fields can be time-consuming and difficult. Thus, machine learning is required to classify and choose the best service in this field. The selection process is done through analysis and recommendations by the system. This article introduces the SSL-WSC algorithm, which classifies unlabeled data through semi-supervised self-training learning using a small amount of labeled data. This algorithm labels the data using a two-step method of calculating a score for each service and dynamic thresholding. The quality features of web services obtained from the QWS dataset were used to evaluate the performance of the proposed algorithm. The experimental results in different scenarios showed that using proposed semi-supervised learning algorithms to create classification models led to better results, so it improved the F1-score, accuracy, and precision, on average, by 11.26%, 9.43% and 9.53%, respectively, as compared to the supervised method.https://ieeexplore.ieee.org/document/10491237/Classificationmachine learningqualitysemi-supervised learningweb services
spellingShingle Mehdi Nozad Bonab
Jafar Tanha
Mohammad Masdari
A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
IEEE Access
Classification
machine learning
quality
semi-supervised learning
web services
title A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
title_full A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
title_fullStr A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
title_full_unstemmed A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
title_short A Semi-Supervised Learning Approach to Quality-Based Web Service Classification
title_sort semi supervised learning approach to quality based web service classification
topic Classification
machine learning
quality
semi-supervised learning
web services
url https://ieeexplore.ieee.org/document/10491237/
work_keys_str_mv AT mehdinozadbonab asemisupervisedlearningapproachtoqualitybasedwebserviceclassification
AT jafartanha asemisupervisedlearningapproachtoqualitybasedwebserviceclassification
AT mohammadmasdari asemisupervisedlearningapproachtoqualitybasedwebserviceclassification
AT mehdinozadbonab semisupervisedlearningapproachtoqualitybasedwebserviceclassification
AT jafartanha semisupervisedlearningapproachtoqualitybasedwebserviceclassification
AT mohammadmasdari semisupervisedlearningapproachtoqualitybasedwebserviceclassification