Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement
Wireless communication channel scenario classification is crucial for new modern wireless technologies. Reducing the time consumed by the data preprocessing phase for such identification is also essential, especially for multiple-scenario transitions in 6G. Machine learning (ML) has been used for sc...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/19/3253 |
_version_ | 1797479756520751104 |
---|---|
author | Amira Zaki Ahmed Métwalli Moustafa H. Aly Waleed K. Badawi |
author_facet | Amira Zaki Ahmed Métwalli Moustafa H. Aly Waleed K. Badawi |
author_sort | Amira Zaki |
collection | DOAJ |
description | Wireless communication channel scenario classification is crucial for new modern wireless technologies. Reducing the time consumed by the data preprocessing phase for such identification is also essential, especially for multiple-scenario transitions in 6G. Machine learning (ML) has been used for scenario identification tasks. In this paper, the least absolute shrinkage and selection operator (LASSO) is used instead of ElasticNet in order to reduce the computational time of data preprocessing for ML. Moreover, the computational time and performance of different ML models are evaluated based on a regularization technique. The obtained results reveal that the LASSO operator achieves the same feature selection performance as ElasticNet; however, the LASSO operator consumes less computational time. The achieved run time of LASSO is 0.33 s, while the ElasticNet corresponding value is 0.67 s. The identification for each specific class for K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and k-Means and Gaussian Mixture Model (GMM) is evaluated using Receiver Operating Characteristics (ROC) curves and Area Under the Curve (AUC) scores. The KNN algorithm has the highest class-average AUC score at 0.998, compared to SVM, k-Means, and GMM with values of 0.994, 0.983, and 0.989, respectively. The GMM is the fastest algorithm among others, having the lowest classification time at 0.087 s, compared to SVM, k-Means, and GMM with values of 0.155, 0.26, and 0.087, respectively. |
first_indexed | 2024-03-09T21:50:23Z |
format | Article |
id | doaj.art-e8c7e703ce4b445c93b897f12473becd |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T21:50:23Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-e8c7e703ce4b445c93b897f12473becd2023-11-23T20:08:58ZengMDPI AGElectronics2079-92922022-10-011119325310.3390/electronics11193253Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance EnhancementAmira Zaki0Ahmed Métwalli1Moustafa H. Aly2Waleed K. Badawi3College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria 1029, EgyptCollege of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria 1029, EgyptCollege of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria 1029, EgyptCollege of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria 1029, EgyptWireless communication channel scenario classification is crucial for new modern wireless technologies. Reducing the time consumed by the data preprocessing phase for such identification is also essential, especially for multiple-scenario transitions in 6G. Machine learning (ML) has been used for scenario identification tasks. In this paper, the least absolute shrinkage and selection operator (LASSO) is used instead of ElasticNet in order to reduce the computational time of data preprocessing for ML. Moreover, the computational time and performance of different ML models are evaluated based on a regularization technique. The obtained results reveal that the LASSO operator achieves the same feature selection performance as ElasticNet; however, the LASSO operator consumes less computational time. The achieved run time of LASSO is 0.33 s, while the ElasticNet corresponding value is 0.67 s. The identification for each specific class for K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and k-Means and Gaussian Mixture Model (GMM) is evaluated using Receiver Operating Characteristics (ROC) curves and Area Under the Curve (AUC) scores. The KNN algorithm has the highest class-average AUC score at 0.998, compared to SVM, k-Means, and GMM with values of 0.994, 0.983, and 0.989, respectively. The GMM is the fastest algorithm among others, having the lowest classification time at 0.087 s, compared to SVM, k-Means, and GMM with values of 0.155, 0.26, and 0.087, respectively.https://www.mdpi.com/2079-9292/11/19/32536Gmachine learningcomputational timefeature selectionROC curvesAUC scores |
spellingShingle | Amira Zaki Ahmed Métwalli Moustafa H. Aly Waleed K. Badawi Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement Electronics 6G machine learning computational time feature selection ROC curves AUC scores |
title | Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement |
title_full | Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement |
title_fullStr | Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement |
title_full_unstemmed | Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement |
title_short | Wireless Communication Channel Scenarios: Machine-Learning-Based Identification and Performance Enhancement |
title_sort | wireless communication channel scenarios machine learning based identification and performance enhancement |
topic | 6G machine learning computational time feature selection ROC curves AUC scores |
url | https://www.mdpi.com/2079-9292/11/19/3253 |
work_keys_str_mv | AT amirazaki wirelesscommunicationchannelscenariosmachinelearningbasedidentificationandperformanceenhancement AT ahmedmetwalli wirelesscommunicationchannelscenariosmachinelearningbasedidentificationandperformanceenhancement AT moustafahaly wirelesscommunicationchannelscenariosmachinelearningbasedidentificationandperformanceenhancement AT waleedkbadawi wirelesscommunicationchannelscenariosmachinelearningbasedidentificationandperformanceenhancement |