Deep Learning-Based Spectrum Sensing for Cognitive Radio Applications

Abstract

In order for cognitive radios to identify and take advantage of unused frequency bands, spectrum sensing is essential. Conventional techniques for spectrum sensing rely on extracting features from received signals at specific locations. However, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have recently demonstrated promise in improving the precision and efficacy of spectrum sensing. Our research introduces a groundbreaking approach to spectrum sensing by leveraging convolutional neural networks (CNNs) to significantly advance the precision and effectiveness of identifying unused frequency bands. We treat spectrum sensing as a classification task and train our model with diverse signal types and noise data, enabling unparalleled adaptability to novel signals. Our method surpasses traditional techniques such as the maximum-minimum eigenvalue ratio-based and frequency domain entropy-based methods, showcasing superior performance and adaptability. In particular, our CNN-based approach demonstrates exceptional accuracy, even outperforming established methods when faced with additive white Gaussian noise (AWGN).