Transmitting Frequency Selection for HF Radar based on Convolutional Deep Belief Network

This paper proposes a transmitting frequency selection method for HF radar based on convolutional deep belief network (CDBN), which is applied to select relatively quiet frequency band for radar in order to improve the detection ability and survivability. This method employs CDBN to extract the features from spectrum data and classify the availability of frequency band to select the quiet band. The nodes of hidden layers are also visualized, and the physical explanation of visualizing result is given. Compared with convolutional neural network (CNN), deep belief network (DBN) and support vector machine (SVM), the proposed method has a better performance in the classification results.