Neural Networks for Radar Waveform Recognition

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.

LPI Radar Waveform Recognition Based on Features from Multiple Images

“…In current research, there have been some LPI waveform recognition technologies (LWRT), which use feature extraction and classification techniques. Time-frequency analysis (TFA) is widely used in the feature extraction since LPI radar signals are usually non-stationary signals, such as Smoothed Pseudo-Wigner Distribution (SPWD) [7], Wigner Ville Distribution (WVD) [8], Short-Time Fourier Transform (STFT) [9][10][11], and Choi-Williams Distribution (CWD) [6,[12][13][14][15][16]. Combined with deep learning in the field of computer vision [17] and models of neural network structures, researchers have obtained better recognition results from the time-frequency feature of signals [18].…”

“…The radar signal is first time-frequency transformed into a two-dimensional time-frequency image (TFI), which then is preprocessed and sent to a neural network for training. In the area of classifier design, classification methods include multi-Layer Perceptron (MLP) [11], conditional decision for different features [11,15], Convolutional Neural Networks (CNN) [14], Elman Neural Networks (ENN) [6], and support vector machines (SVM) [6,16]. In addition, there have been hybrid classifiers designed that combine a few different multiple classifiers.…”

“…In addition, there have been hybrid classifiers designed that combine a few different multiple classifiers. For instance, in [15,19,20], all of them combine two deep learning models. In [15], the classifier consists of CNN and ENN.…”

“…For instance, in [15,19,20], all of them combine two deep learning models. In [15], the classifier consists of CNN and ENN. In [20], the classifier consists of CNN and SAE.However, the feature of TFI will be overwhelmed by a large amount of noise due to the interference of noise.…”

“…Researchers have dedicated their attention to image pre-processing, generally in two ways, in order to solve this problem. First, before time-frequency conversion, algorithm filtering is used to reduce noise [21][22][23][24]; second, some image processing technology is used to process TFI to achieve accurate classification [6,13,15,16]. For the first method, most of the current noise reduction algorithms are difficult to apply in a low SNR environment.…”