Radio Access Technology characterisation through object detection

Abstract

Radio Access Technology (RAT) classification and monitoring are essential for efficient coexistence of different communication systems in shared spectrum. Shared spectrum, including operation in license-exempt bands, is envisioned in the fifth generation of wireless technology (5G) standards (e.g., 3GPP Rel. 16). In this paper, we propose a Machine Learning (ML) approach to characterise the spectrum utilisation and facilitate the dynamic access to it. Recent advances in Convolutional Neural Networks (CNNs) enable us to perform waveform classification by processing spectrograms as images. In contrast to other ML methods that can only provide the class of the monitored RATs, the solution we propose can recognise not only different RATs in shared spectrum, but also identify critical parameters such as inter-frame duration, frame duration, centre frequency, and signal bandwidth by using object detection and a feature extraction module to extract features from spectrograms. We have implemented and evaluated our solution using a dataset of commercial transmissions, as well as in a Software-Defined Radio (SDR) testbed environment. The scenario evaluated was the coexistence of WiFi and LTE transmissions in shared spectrum. Our results show that our approach has an accuracy of 96% in the classification of RATs from a dataset that captures transmissions of regular user communications. It also shows that the extracted features can be precise within a margin of 2%, and can detect above 94% of objects under a broad range of transmission power levels and interference conditions.