Visible to the public Recognition of Overlapped Frequency Hopping Signals Based on Fully Convolutional Networks

TitleRecognition of Overlapped Frequency Hopping Signals Based on Fully Convolutional Networks
Publication TypeConference Paper
Year of Publication2021
AuthorsLiu, Pengcheng, Han, Zhen, Shi, Zhixin, Liu, Meichen
Conference Name2021 28th International Conference on Telecommunications (ICT)
Date Publishedjun
Keywordsconvolution, Deep Learning, Fourier transforms, Fully Convolutional Networks, Metrics, overlapped frequency hopping signal, Prediction algorithms, Predictive models, pubcrawl, resilience, Resiliency, Scalability, security, signal separation, Time Frequency Analysis, Time-frequency Analysis, Training
AbstractPrevious research on frequency hopping (FH) signal recognition utilizing deep learning only focuses on single-label signal, but can not deal with overlapped FH signal which has multi-labels. To solve this problem, we propose a new FH signal recognition method based on fully convolutional networks (FCN). Firstly, we perform the short-time Fourier transform (STFT) on the collected FH signal to obtain a two-dimensional time-frequency pattern with time, frequency, and intensity information. Then, the pattern will be put into an improved FCN model, named FH-FCN, to make a pixel-level prediction. Finally, through the statistics of the output pixels, we can get the final classification results. We also design an algorithm that can automatically generate dataset for model training. The experimental results show that, for an overlapped FH signal, which contains up to four different types of signals, our method can recognize them correctly. In addition, the separation of multiple FH signals can be achieved by a slight improvement of our method.
Citation Keyliu_recognition_2021