Low Probability Of Intercept Radar Waveforms Research Articles

LPI radar waveform recognition based on semi-supervised model all mean teacher

Low probability of intercept (LPI) radar signal identification plays an important role in electronic warfare, but most existing algorithms are proposed under the condition of sufficient samples, ignoring the problem of a small amount of labeled data in the actual electromagnetic environment. To solve the problem, in this paper, a semi-supervised learning model All Mean Teacher (AMT) based on Mean Teacher (MT) is proposed. First, the LPI radar signal is transformed into Time-frequency images (TFIs) by using the Choi-Williams distribution, and Random Erasing is used for TFIs which improves the generalization ability of the model. Then the Multi-headed Self-Attention Network (MSA-Net) is aimed to extract features, combined with AMT to realize the automatic waveform recognition of radar signals. MSA-Net facilitates feature information propagation by computing contrast costs on TFIs between the student and teacher networks. It solves the problem that TFIs are not easy to train for small amounts of labeled data, improving the accuracy of signal recognition in semi-supervised learning scenarios. Experimental results show that the average recognition accuracy of the proposed method is up to 85.7% at a signal-to-noise ratio of -8 dB.

LPI Radar Signals Modulation Recognition Based on ACDCA-ResNeXt

For low probability of intercept (LPI) radar waveform identification accuracy (ACC) problem at low Signal-to-Noise Ratios (SNRs), an approach based on time-frequency analysis (TFA) and Asymmetric Dilated Convolution Coordinate Attention Residual networks (ACDCA-ResNeXt) is proposed to recognize twelve kinds of LPI radar signals automatically. First, we apply Choi-Williams distribution (CWD), which shows superior performance at low SNRs, to transforming radar signals into time-frequency images (TFI). Then, in order to obtain the high-quality TFIs, a series of image processing techniques, including 2DWiener filtering, image cutting, and image resize, are used to remove the background noise and redundant frequency bands of the TFI and obtain a fixed-size gray scale image containing main morphological features of the TFI. Finally, the TFIs are input into ACDCA-ResNeXt network that can extract and learn deep features to recognize radar waveforms. Furthermore, a fusion loss function, which is composed of a soft-label smoothed cross entropy loss function and a center loss function, improves the generalization capability performance of network and achieves a better clustering effect. Experimental results demonstrate that, for twelve kinds of LPI radar waveforms, the overall recognition ACC of the proposed approach achieves 97.94% when SNR is -8 dB.

Efficient TFI-Based Depth-Tunable LPI Radar Waveform Recognition Network

Low probability of intercept (LPI) radar waveform recognition (LWR) based on deep learning can significantly enhance the recognition accuracy. However, most existing LWR networks overlook the algorithmic complexity and disparities between visual images and time-frequency images (TFIs). In practical applications, it is critical to enhance the recognition accuracy while minimizing the computational complexity to satisfy the reliability and timeliness requirements of an LWR network. To address this issue, we propose an efficient depth-tunable network (EDTN) for LWR. The EDTN reduces the computational complexity and enhances the recognition accuracy by adopting a flexible network structure, using convolution methods appropriate for TFIs, and combining several beneficial designs. Our experiments with a classical LPI radar waveform dataset demonstrate that the EDTN reduces the computational complexity by more than 95% over that of the state-of-the-art networks while maintaining the recognition accuracy.

LPI Radar Signal Recognition Based on Dual-Channel CNN and Feature Fusion

The accuracy of low probability of intercept (LPI) radar waveform recognition is an important and challenging problem in electronic warfare. Aiming at the problem of the difficulty in feature extraction and the low recognition rates of the LPI radar signal under a low signal-to-noise ratio, and inspired by the symmetry theory, we propose a new approach for the LPI radar signal recognition method based on a dual-channel convolutional neural network (CNN) and feature fusion. Our new approach contains three main modules: the preprocessing module that converts the LPI radar waveforms into two-dimensional time-frequency images using the Choi–Williams distribution (CWD) transformation and performs image binarization, the feature extraction module that extracts different features obtained from the images, and the recognition module that utilizes a multi-layer perceptron (MLP) network to fuse these features and distinguish the type of LPI radar signals. In the feature extraction module, a two-channel CNN model is proposed that extracts Histogram of Oriented Gradients (HOG) features and deep features from time-frequency images, respectively. Finally, the recognition module recognizes the radar signals using a Softmax classifier based on the fused features from two channels. The experimental results from 12 types of LPI radar signals prove the superiority and robustness of the proposed model. Its overall recognition rate reaches 97% when the signal-to-noise ratio is −6 dB.

An Improved LPI Radar Waveform Recognition Framework With LDC-Unet and SSR-Loss

Low probability of intercept (LPI) radar signals have been widely used in modern radars due to the advantages of being hardly intercepted by non-cooperative receivers. Therefore, the waveform recognition of LPI radar signals has recently gained increasing attention. In this letter, an improved LPI radar waveform recognition framework with local dense connection U-net and novel loss function is proposed. Specifically, radar signals are transformed into time-frequency images (TFIs) through time-frequency analysis techniques. Then, the local dense connection U-net is proposed to reduce interference of noise and enhance TFIs features. Finally, the recognition task is implemented through a deep convolutional neural network, which is trained with a noise-robust loss function called SSR-loss. Compared with other existing LPI radar waveform recognition frameworks, our method can obtain a significant improvement in recognition accuracy under noise conditions. When signal-to-noise ratio (SNR) is as low as −10 dB, the overall probability of successful recognition on twelve kinds of typical modulated signals can reach up to 91.17%.

Accurate LPI Radar Waveform Recognition With CWD-TFA for Deep Convolutional Network

Automotive radars, with a widespread emergence in the last decade, have faced various jamming attacks. Utilizing low probability of intercept (LPI) radar waveforms, as one of the essential solutions, demands an accurate waveform recognizer at the intercept receiver. Numerous conventional approaches have been studied for LPI radar waveform recognition, but their performance is inadequate under channel condition deterioration. In this letter, by exploiting deep learning (DL) to capture intrinsic radio characteristics, we propose a convolutional neural network (CNN), namely LPI-Net, for automatic radar waveform recognition. In particular, radar signals are first analyzed by a time-frequency analysis using the Choi-Williams distribution. Subsequently, LPI-Net, primarily consisting of three sophisticated modules, is built to learn the representational features of time-frequency images, in which each module is constructed with a preceding maps collection to gain feature diversity and a skip-connection to maintain informative identity. Simulation results show that LPI-Net achieves the 13-waveform recognition accuracy of over 98% at 0 dB SNR and further performs better than other deep models.

Research on LPI radar signal detection and parameter estimation technology

Modern radar signals mostly use low probability of intercept (LPI) waveforms, which have short pulses in the time domain, multicomponent properties, frequency hopping, combined modulation waveforms and other characteristics, making the detection and estimation of LPI radar signals extremely difficult, and leading to highly required significant research on perception technology in the battlefield environment. This paper proposes a visibility graphs (VG)-based multicomponent signals detection method and a modulation waveforms parameter estimation algorithm based on the time-frequency representation (TFR). On the one hand, the frequency domain VG is used to set the dynamic threshold for detecting the multicomponent LPI radar waveforms. On the other hand, the signal is projected into the time and frequency domains by the TFR method for estimating its symbol width and instantaneous frequency (IF). Simulation performance shows that, compared with the most advanced methods, the algorithm proposed in this paper has a valuable advantage. Meanwhile, the calculation cost of the algorithm is quite low, and it is achievable in the future battlefield.

LPI Radar Waveform Recognition Based on Multi-Resolution Deep Feature Fusion

Deep neural networks are used as effective methods for the Low Probability of Intercept (LPI) radar waveform recognition. However, existing models’ performance degrades seriously at low Signal-to-Noise Ratios (SNRs) because the effective features extracted by the networks are insufficient under noise jamming. In this paper, we propose a multi-resolution deep feature fusion method for LPI radar waveform recognition. First, we apply the enhanced Fourier-based Synchrosqueezing Transform (FSST), which shows good performance at low SNRs, to convert radar signals into time-frequency images. Then, we construct a multi-resolution deep convolutional network to extract more deep features from each resolution channel. Next, we explore an interactive feature fusion strategy for deep feature fusion. By some down-sampling or up-sampling blocks, different resolution features are fused to generate new features. Finally, we apply a fusion algorithm to the fully connected layer to achieve classification fusion for better performance. Simulation experiments on twelve kinds of LPI radar waveforms show that the overall recognition accuracy of our method can reach 95.2% at the SNR of −8 dB. It is proved that our approach does indeed improve the recognition accuracy effectively at low SNRs.

LPI RADAR WAVEFORM CLASSIFICATION USING BINARY SVM AND MULTI-CLASS SVM BASED ON PRINCIPAL COMPONENTS OF TFI

Since cognition has become an important topic in Electronic Warfare (EW) systems, Electronic Support Measures (ESM) are used to monitor, intercept and analyse radar signals. Low Probability of Intercept (LPI) radars is preferred to be able to detect targets without being detected by ES systems. Because of their properties as low power, variable frequency, wide bandwidth, LPI Radar waveforms are difficult to intercept with ESM systems. In addition to intercepting, the determination of the waveform types used by the LPI Radars is also very important for applying counter-measures against these radars. In this study, a solution for the LPI Radar waveform recognition is proposed. The solution is based on the training of Support Vector Machine (SVM) after applying Principal Component Analysis (PCA) to the data obtained by Time-Frequency Images (TFI). TFIs are generated using Choi-Williams Distribution. High energy regions on these images are cropped automatically and then resized to obtain uniform data set. To obtain the best result in SVM, the SVM Hyper-Parameters are also optimized. Results are obtained by using one-against-all and one-against-one methods. Better classification performance than those given in the literature have been obtained especially for lower Signal to Noise Ratio (SNR) values. The cross-validated results obtained are compared with the best results in the literature.

Multi-Resolution Fusion Convolutional Neural Networks for Intrapulse Modulation LPI Radar Waveforms Recognition

Low Probability of Intercept (LPI) radar waveform has complex and diverse modulation schemes, which cannot be easily identified by the traditional methods. The research on intrapulse modulation LPI radar waveform recognition has received increasing attention. In this paper, we propose an automatic LPI radar waveform recognition algorithm that uses a multi-resolution fusion convolutional neural network. First, signals embedded within the noise are processed using Choi-William Distribution (CWD) to obtain time-frequency feature images. Then, the images are resized by interpolation and sent to the proposed network for training and identification. The network takes a dual-channel CNN structure to obtain features at different resolutions and makes features fusion by using the concatenation and Inception module. Extensive simulations are carried out on twelve types of LPI radar waveforms, including BPSK, Costas, Frank, LFM, P1~P4, and T1~T4, corrupted with additive white Gaussian noise of SNR from 10dB to -8dB. The results show that the overall recognition rate of the proposed algorithm reaches 95.1% when the SNR is -6dB. We also try various sample selection methods related to the recognition task of the system. The conclusion is that reducing the samples with SNR above 2dB or below -8dB can effectively improve the training speed of the network while maintaining recognition accuracy.

LPI Radar Waveform Recognition Based on Features from Multiple Images.

Detecting and classifying the modulation type of the intercepted noisy LPI (low probability of intercept) radar signals in real-time is a necessary survival technique in the electronic intelligence systems. Most radar signals have been designed to have LPI properties; therefore, the LPI radar waveform recognition technique (LWRT) has recently gained increasing attention. In this paper, we propose a multiple feature images joint decision (MFIJD) model with two different feature extraction structures that fully extract the pixel feature to obtain the pre-classification results of each feature image for the non-stationary characteristics of most LPI radar signals. The core technology of this model is combining the short-time autocorrelation feature image, double short-time autocorrelation feature image and the original signal time-frequency image (TFI) simultaneously input into the hybrid model classifier, which is suitable for non-stationary signals, and it has higher universality. We demonstrate the performance of MFIJD by simulating 11 types of the signals defined in this paper and generating training sets and test sets. The comparison with the literature shows that the proposed methods not only has a high universality for LPI radar signals, but also better adapts to LPI radar waveform recognition at low SNR (signal to noise ratio) environment. The overall recognition rate of the method reaches 87.7% when the SNR is −6 dB.

Automatic Recognition of General LPI Radar Waveform Using SSD and Supplementary Classifier

For low probability of intercept (LPI) radars, frequency-modulated and phase-modulated continuous waveforms are widely used because of their low peak power compared to that of pulse waves (PW). However, there has been a limited number of studies on recognizing continuous wave (CW) LPI radar, in spite of its importance and popularity. In this paper, in order to recognize both PW and CW LPI radar waveforms, we propose an LPI radar waveform recognition technique (LWRT) based on a single-shot multi-box detector (SSD) and a supplementary classifier. It is demonstrated with Monte Carlo simulations that the proposed LWRT achieves classification performance similar to that of the current LWRT with the highest classification performance for PW LPI radar waveforms, even without the prior condition used in existing LWRTs. For CW LPI radar waveforms, on the other hand, with the combination of the SSD and the supplementary classifier, the proposed LWRT achieves extraordinary recognition performance for all 12 LPI radar modulation schemes (i.e., BPSK, Costas, LFM, Frank, P1, P2, P3, P4, T1, T2, T3, and T4) considered in the literature.

LPI Radar Waveform Recognition Based on Deep Convolutional Neural Network Transfer Learning

Low Probability of Intercept (LPI) radar waveform recognition is not only an important branch of the electronic reconnaissance field, but also an important means to obtain non-cooperative radar information. To solve the problems of LPI radar waveform recognition rate, difficult feature extraction and large number of samples needed, an automatic classification and recognition system based on Choi-Williams distribution (CWD) and depth convolution neural network migration learning is proposed in this paper. First, the system performs CWD time-frequency transform on the LPI radar waveform to obtain a 2-D time-frequency image. Then the system preprocesses the original time-frequency image. In addition, then the system sends the pre-processed image to the pre-training model (Inception-v3 or ResNet-152) of the deep convolution network for feature extraction. Finally, the extracted features are sent to a Support Vector Machine (SVM) classifier to realize offline training and online recognition of radar waveforms. The simulation results show that the overall recognition rate of the eight LPI radar signals (LFM, BPSK, Costas, Frank, and T1–T4) of the ResNet-152-SVM system reaches 97.8%, and the overall recognition rate of the Inception-v3-SVM system reaches 96.2% when the SNR is −2 dB.

Reduced complexity and near optimum detector for linear‐frequency‐modulated and phase‐modulated LPI radar signals

Dealing with low probability of intercept (LPI) radar signals in very low signal-to-noise ratio (SNR) stages requires reconnaissance systems to employ an effectively practical method for detecting and fully characterising the received signals. Following the aim of LPI signal detection, in this study, a novel method based on concentrating the energy of the signal in one particular row of the time–frequency domain matrix is proposed. It is shown that the proposed method enables to detect and estimate the parameters of multiple low-power linear-frequency-modulated signals. A comparison has been made between the performance of the matched filter and the proposed method, and it is shown the proposed method has approximately the same performance and low computational complexity as matched filters. This method is also able to detect the poly-phase signals such as Frank-coded signals and also non-linear-frequency-modulated signals, as well. To show the effectiveness of the method, extensive simulations are carried out with different LPI radar waveforms corrupted with additive white Gaussian noise of SNR down to −25 dB.

An Investigation of LPI Radar Waveforms Classification in RoF Channels

Intensive research has been developed to either design or classify low probability of intercept (LPI) radar signals. These types of signals are used in different sensitive electronic warfare applications such as electronic support, electronic attack, and radar emitter identification. Linear frequency modulation, nonlinear frequency modulation, frequency shift keying, polyphase Barker, polyphase P1, P2, P3, P4 and Frank codes are examples of LPI waveforms. In this paper, we consider the modulation classification problem under the effect of transporting the captured radar signals through radio over fiber channels. Distortions and noise introduced by such channels are likely to affect the performance of LPI classification algorithms. Here, we investigate the accuracy of a recently proposed hierarchical decision-tree automatic modulation classification algorithm for additive white Gaussian noise channels and provide the necessary adjustments when the intercepted radar signals are transmitted over fiber optic channels. The investigation is conducted by simulations and experimental demonstration. The obtained results show that for an 80 km fiber link and noisy intercepted LPI signals, the average identification accuracy reaches more than 98%, at 16 dB optical signal-to-noise ratio.

LPI Radar Waveform Recognition Based on Multi-Branch MWC Compressed Sampling Receiver

In this paper, a new wideband digital receiver based on the modulated wideband converter compressed sampling (CS) system is proposed to replace a conventional wideband digital receiver, solve the cross-channel signal problem, and achieve intra-pulse modulation recognition for the low probability of intercept (LPI) radar signals. The proposed receiver uses cyclic-shifted pseudo-random sequences to mix the received signals to baseband. The mixed signals are low-pass filtered and down-sampled to obtain compressed sampling data containing the full information of the received signals. Since the phases of the multi-branch CS data are designed to change regularly, we propose a phase correction factor to correct the phases of the multi-branch CS data, which can be superposed to increase the output signal-to-noise ratio (SNR). Then, a recognition method based on the short-time Fourier transform (STFT) and spectrum energy focusing rate tests are proposed. First, the spectrum modulation bandwidth based on the STFT spectrum of the superposed CS data is tested to distinguish phase modulation signals and frequency modulation signals approximately. Then, the spectrum energy focusing rate of the superposed CS data is tested to determine the intra-pulse modulation type specifically. Finally, the superiority of the proposed recognition system for LPI radar signals and cross-channel signals is demonstrated by simulations and analysis. Simulation results show that the overall ratio of the successful recognition (RSR) is 100% when the SNR is greater than 0 dB.

Automatic LPI Radar Waveform Recognition Using CNN

Detecting and classifying the modulation scheme of the intercepted noisy low probability of intercept (LPI) radar signals in real time is a necessary survival technique required in the electronic warfare systems. Therefore, LPI radar waveform recognition technique (LWRT) has gained an increasing attention recently. In this paper, we propose a convolutional neural network (CNN)-based LWRT, where the input and hyperparameters of the CNN, such as the input size, number of filters, filter size, and number of neurons are designed based on various signal conditions to guarantee the maximum classification performance. In addition, we propose a sample averaging technique to efficiently reduce the large computational cost required when the intercept receiver needs to process a large amount of signal samples to improve the detection sensitivity. We demonstrate the performance of the proposed LWRT with numerous Monte Carlo simulations based on the simulation conditions used in the recent LWRTs introduced in the literature. It is testified that the proposed LWRT offers significant improvement, such as robustness to noise and recognition accuracy, over the recent LWRTs.