Radar Waveform Recognition Based on Time-Frequency Analysis and Artificial Bee Colony-Support Vector Machine

Abstract

In this paper, a system for identifying eight kinds of radar waveforms is explored. The waveforms are the binary phase shift keying (BPSK), Costas codes, linear frequency modulation (LFM) and polyphase codes (including P1, P2, P3, P4 and Frank codes). The features of power spectral density (PSD), moments and cumulants, instantaneous properties and time-frequency analysis are extracted from the waveforms and three new features are proposed. The classifier is support vector machine (SVM), which is optimized by artificial bee colony (ABC) algorithm. The system shows well robustness, excellent computational complexity and high recognition rate under low signal-to-noise ratio (SNR) situation. The simulation results indicate that the overall recognition rate is 92% when SNR is −4 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.…”

“…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.…”

“…For the second method, literature [6,12,13], and [16] reduce the TFI noise through image processing, but the processing methods of image morphology and threshold filtering will easily lose the signal components. In addition, [6,13] and [16] only studied the classification of 8 types of LPI radar signals, the polytime codes (T1, T2, T3, and T4) are not mentioned in [6,16], the polyphase codes (P1, P2, P3 and P4) are not mentioned in [13]. Furthermore, the recognition rate under the SNR of −4 dB has not been studied in [6,13,16].…”

“…In addition, [6,13] and [16] only studied the classification of 8 types of LPI radar signals, the polytime codes (T1, T2, T3, and T4) are not mentioned in [6,16], the polyphase codes (P1, P2, P3 and P4) are not mentioned in [13]. Furthermore, the recognition rate under the SNR of −4 dB has not been studied in [6,13,16]. Obviously, in order to obtain better classification results, it is necessary to design a receiver capable of classifying more types of radar signals at a lower SNR.In this paper, we propose a new signal preprocessing technique by using short-time autocorrelation and combine TFA to solve the problem of the low recognition rate of multiple types of LPI radar signal for classification.…”