Abstract
For passive radar detection system, radar waveform recognition is an important research area. In this paper, we explore an automatic radar waveform recognition system to detect, track and locate the low probability of intercept (LPI) radars. The system can classify (but not identify) 12 kinds of signals, including binary phase shift keying (BPSK) (barker codes modulated), linear frequency modulation (LFM), Costas codes, Frank code, P1-P4 codesand T1-T4 codeswith a low signal-to-noise ratio (SNR). It is one of the most extensive classification systems in the open articles. A hybrid classifier is proposed, which includes two relatively independent subsidiary networks, convolutional neural network (CNN) and Elman neural network (ENN). We determine the parameters of the architecture to make networks more effectively. Specifically, we focus on how the networks are designed, what the best set of features for classification is and what the best classified strategy is. Especially, we propose several key features for the classifier based on Choi–Williams time-frequency distribution (CWD). Finally, the recognition system is simulated by experimental data. The experiments show the overall successful recognition ratio of 94.5% at an SNR of −2 dB.
Highlights
Modern radars usually have low instantaneous power, called low probability of intercept (LPI)radars, which are used in electronic warfare (EW)
Experimental results show that convolutional neural network (CNN) reduce the error rate by 6%–10% compared with deep neural networks (DNNs) on the speech recognition tasks
99.81%, in which support vector machine (SVM) performs as a classifier and CNN works as a feature extractor
Summary
Modern radars usually have low instantaneous power, called low probability of intercept (LPI). We investigate the convolutional neural network (CNN) for radar waveform recognition. We explore a wide radar waveform recognition system to classify, but not identify. The major contributions can be summarized as follows: (1) build the framework of signals processing; establish the label data for testing the system; (2) the proposed recognition system can classify as many as 12 kinds of waveforms, which are described in the context; previous articles can seldom reach such a wide range of classification of radar signals; especially, four kinds of polytime codes are classified together for the first time in the published literature;. (3) almost all interested parameters and all features will be estimated by received data without a priori knowledge; (4) propose a hybrid classifier that has two different networks (CNN and ENN).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
