Machine Learning Based Protocol Classification in Unlicensed 5 GHz Bands

Wenhan Zhang, Marwan Krunz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To monitor RF activity and efficiently coordinate channel access for heterogeneous wireless systems over a shared channel, it is important to be able to classify observed transmissions accurately without decoding them. In this paper, we propose novel recurrent neural network (RNN) architectures for signal classification, considering as a use case on interleaving-based spectrum sharing model for Wi-Fi, LTE-LAA, and 5G-NRU over the unlicensed 5 GHz bands. Several classifiers are presented, which take raw in-phase/quadrature (I/Q) samples as input. First, we examine Simple RNNs, Long Short-term Memory (LSTM) networks, and Gated Recurrent Units (GRU) networks for protocol classification. These RNNs are used to capture the unique features in observed signals. To further improve the classification accuracy, we extend the RNN designs into a bidirectional structure, allowing an RNN cell to learn the temporal dependence in the waveform in both forward and backward directions. Bidirectionality can effectively increase the amount of information and the context available to the neural network. We then extend our designs to multi-layer RNNs, which allow the classifier to capture temporal correlations at multiple time scales, hence increasing the network's computational capacity. Finally, we propose further enhancements to reduce the over-fitting problem in RNN training, including regularization, recurrent weight constraints, and rate halving. Our simulation results show that the multi-layer and bidirectional designs can effectively improve the accuracy of the RNN-based RF signal classifier. Combining the two features, an RNN structure can achieve more than 92% accuracy in our protocol classification problem.

Original languageEnglish (US)
Title of host publication2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages752-757
Number of pages6
ISBN (Electronic)9781665426718
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022 - Seoul, Korea, Republic of
Duration: May 16 2022May 20 2022

Publication series

Name2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

Conference

Conference2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
Country/TerritoryKorea, Republic of
CitySeoul
Period5/16/225/20/22

Keywords

  • coexistence
  • Deep learning
  • dynamic spectrum access
  • recurrent neural networks
  • signal classification

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Signal Processing
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Machine Learning Based Protocol Classification in Unlicensed 5 GHz Bands'. Together they form a unique fingerprint.

Cite this