Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

WLAN Protocols Identification Using Machine Learning and Ensemble Models

Published

Author(s)

Akimun Jannat Alvina, Yao Ma, Mark Golkowski

Abstract

The growing demand for wireless communications has caused significant spectrum congestion, requiring multiple WLAN protocols to share limited spectrum resources. To address this, further research is necessary to optimize spectrum sharing and improve coexistence between various wireless technologies and protocols. This study introduces a software defined radio (SDR) and machine learning-based approach for classifying WLAN protocols—specifically IEEE 802.11a, 802.11ac, and 802.11ax—operating in the 5 GHz band. To enhance classification performance, we optimize the hyperparameters of several machine learning and ensemble models. Their performance is evaluated using metrics such as precision, recall, F1-score, and ROC-AUC, providing a comprehensive assessment of the models' effectiveness. Our findings show that the proposed classification method achieves up to 95% accuracy, with Random Forest, KNN, and Gradient Boosting models performing the best. These results are novel as they show that the use of intelligent sensing can achieve satisfactory protocol classification performance with low-cost devices.
Proceedings Title
2025 National Radio Science Meeting
Conference Dates
January 7-10, 2025
Conference Location
Boulder, CO, US

Keywords

cognitive radio, ensemble methods, machine learning, signal classification/identification, spectrum sensing

Citation

Alvina, A. , Ma, Y. and Golkowski, M. (2025), WLAN Protocols Identification Using Machine Learning and Ensemble Models, 2025 National Radio Science Meeting, Boulder, CO, US (Accessed February 11, 2025)

Issues

If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.

Created January 7, 2025, Updated January 24, 2025