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 data preprocessing phase such identification also essential, especially multiple-scenario transitions in 6G. Machine learning (ML) has been used tasks. In this paper, least absolute shrinkage and selection operator (LASSO) instead of ElasticNet order to reduce computational ML. Moreover, performance different ML models are evaluated based on a regularization technique. The obtained results reveal that LASSO achieves same feature as ElasticNet; however, consumes less time. achieved run 0.33 s, while corresponding value 0.67 s. each specific class K-Nearest Neighbor (KNN), Support Vector (SVM), k-Means Gaussian Mixture Model (GMM) using Receiver Operating Characteristics (ROC) curves Area Under Curve (AUC) scores. KNN algorithm highest class-average AUC score at 0.998, compared SVM, k-Means, GMM with values 0.994, 0.983, 0.989, respectively. fastest among others, having lowest 0.087 0.155, 0.26, 0.087,