Machine Learning in Multiple-Antenna Based Spectrum Sensing for Cognitive Radio Networks

Spectrum sensing is boosting the research to find more techniques to improve reliable spectrum utilization in cognitive radio networks. Machine learning can significantly contribute to developing the future of wireless networks by enabling flexible, efficient, and intelligent communication systems. On the other hand, multiple antenna systems at the transmitter and/or receiver are one of the most popular technologies in modern high-speed wireless communication to enhance performance. In this paper, we propose a machine learning technique in spectrum sensing for cognitive radio of users with multiple antennas, considering the non-cooperative approach to improve the spectrum sensing performance. Initially, we propose a synthetic dataset preparation method based on multiple antenna-assisted spectrum sensing for cognitive radio. After that, the popular linear classifiers, such as support vector machine (SVM) and logistic regression (LR) are used as supervised learning algorithms on the generated dataset for machine learning-based spectrum sensing. In the simulation, binary phase-shift keying (BPSK) modulation schemes over the Rayleigh fading channel with additive white Gaussian noise (AWGN) are studied. The significance and effectiveness of the proposed method are validated through simulation in terms of confusion matrix, accuracy, precision, recall, F1-score, probabilities of detection, miss detection, and false alarm. The simulation findings indicate that the proposed method provides better results compared to traditional and state-of-the-art methods. In particular, the proposed method provides the probability of detection (Pd) of 97.49% at a signal-to-noise ratio (SNR) of -25 dB with 4 antennas, and maintains the probability of false alarm (Pf) of 0.01.