Spectrum Sensing

Spectrum sensing aims to efficiently detect available frequency bands for secondary users while minimizing interference with primary users, a crucial task for optimizing spectrum utilization in increasingly crowded wireless environments. Current research heavily utilizes machine learning, particularly deep learning architectures like convolutional neural networks (CNNs), transformers, and recurrent neural networks (RNNs such as LSTMs), often within collaborative frameworks like federated learning, to improve sensing accuracy and robustness in diverse scenarios including mobile and satellite networks. These advancements are significant for enabling dynamic spectrum access, improving network efficiency, and facilitating the development of next-generation wireless communication systems.