Anomaly Detection of Spectrum in Wireless Communication via Deep Autoencoder

摘要

Anomaly detection has been a typical task in many fields, as well as spectrum monitoring in wireless communication. In this paper, we apply a deep-structure autoencoder neural network to spectrum anomaly detection, and the time-frequency diagram is used as the feature of the learning model. In order to evaluate the performance of the model, the accuracy of the output is considered. We compare the performance of both our proposed model and conventional one-layer autoencoder. The results of numerical experiments illustrate that our model outperforms the one-layer autoencoder based method.