Robust Deep Sensing Through Transfer Learning in Cognitive Radio

Abstract

We propose a robust spectrum sensing framework based on deep learning. The received signals at the secondary user's receiver are filtered, sampled and then directly fed into a convolutional neural network. Although this deep sensing is effective when operating in the same scenario as the collected training data, the sensing performance is degraded when it is applied in a different scenario with different wireless signals and propagation. We incorporate transfer learning into the framework to improve the robustness. Results validate the effectiveness as well as the robustness of the proposed deep spectrum sensing framework.

References in corpus (5)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• End to End Learning for Self-Driving Cars
• Over the Air Deep Learning Based Radio Signal Classification
• Deep Sensing: Cooperative Spectrum Sensing Based on Convolutional Neural Networks