Accurate identification of the signal type in shared-spectrum networks is critical for efficient resource allocation and fair coexistence. It can be used for scheduling transmission opportunities to avoid collisions and improve system throughput, especially when the environment changes rapidly. In this paper, we develop deep neural networks (DNNs) to detect coexisting signal types based on In-phase/Quadrature (I/Q) samples without decoding them. By using segments of the samples of the received signal as input, a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) are combined and trained using categorical cross-entropy (CE) optimization. Classification results for coexisting Wi-Fi, LTE LAA, and 5G NR-U signals in the 5-6 GHz unlicensed band show high accuracy of the proposed design. We then exploit spectrum analysis of the I/Q sequences to further improve the classification accuracy. By applying Short-time Fourier Transform (STFT), additional information in the frequency domain can be presented as a spectrogram. Accordingly, we enlarge the input size of the DNN. To verify the effectiveness of the proposed detection framework, we conduct over-the-air (OTA) experiments using USRP radios. The proposed approach can achieve accurate classification in both simulations and hardware experiments.

Wi-Fi networks are susceptible to aggressive behavior caused by selfish or malicious devices that reduce their minimum contention window size (CWmin) to below the standard CWmin. In this paper, we propose a scheme called Minimum Contention Window Estimation (CWE) to detect aggressive stations with low CWmin’s, where the AP estimates the CWminvalue of all stations transmitting uplink by monitoring their backoff values over a period of time and keeping track of the idle time each station spends during backoff. To correctly estimate each backoff value, we present a cross-correlation based technique that uses the frequency offset between the AP and each station to identify stations involved in uplink collisions. The AP constructs empirical distributions for the monitored backoff values and compares them with a set of nominal PMF’s, created via Markov analysis of the DCF protocol to estimate CWminof various stations. After detecting the aggressive stations, the AP can choose to stop serving those stations. Simulation results show that the accuracy of our collision detection technique is 96%, 94%, and 88% when there are 3, 6, and 9 stations in the WLAN, respectively. For the former WLAN settings, the estimation accuracy of CWE scheme is 100%, 98.81%, and 96.3%, respectively.