Modulation recognition for radar emitter signals based on convolutional neural network and fusion features

Gao, Jingpeng; Shen, Liangxi; Gao, Lipeng

doi:10.1002/ett.3612

Cited by 23 publications

(15 citation statements)

References 33 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scholars have proposed multi-component signal separation methods based on parameterized timefrequency analysis [5], [13], time-frequency image processing [14] and blind source separation [15], [16]. Recently, some researchers have proposed radar signal intra-pulse modulation recognition methods based on multi-component signal separation [17], [18]. Reference [17] decompose received signals into multiple components based on fractional Fourier transform and then identifies each signal component separately based on CNN and fusion features.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, some researchers have proposed radar signal intra-pulse modulation recognition methods based on multi-component signal separation [17], [18]. Reference [17] decompose received signals into multiple components based on fractional Fourier transform and then identifies each signal component separately based on CNN and fusion features. The method can separate and recognize 9 kinds of overlapping radar signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Hou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Intra-pulse modulation recognition of radar signals is an important part of modern electronic intelligence reconnaissance and electronic support systems. With the increasing density of radar signals, the analysis and processing of multi-component radar signals have become an urgent problem in the current radar reconnaissance system. In this paper, an intra-pulse modulation recognition approach for singlecomponent and dual-component radar signals is proposed. First, in order to adapt to the time-frequency energy distribution characteristics of various radar signals, we propose to extract the time-frequency images (TFIs) of received signals by Cohen class time-frequency distribution (CTFD) with multiple kernel functions. Besides, the image processing methods are used to suppress noise and adjust the size and amplitude of the TFIs. Second, we design and pre-train a TFI feature extraction network for radar signals based on a convolutional neural network (CNN). Finally, to improve the probability of successful recognition (PSR) of the recognition system in the pulse overlapping environment, a multi-label classification network based on a deep Q-learning network (DQN) is explored. Besides, two sub-networks take TFIs based on special kernel functions as input and re-judge the recognition results of some specific signals to further enhance the recognition effect of the recognition system. The proposed approach can identify 8 kinds of random overlapping radar signals. The simulation results show that the overall PSR of dual-component radar signals and single-component radar signals can reach 94.83% and 94.43%, respectively, when the signal-to-noise ratio (SNR) is −6 dB. INDEX TERMS Radar signal recognition, Cohen class time-frequency distribution, convolutional neural network, deep Q-learning network.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Hou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It is also a kind of T‐F signal analysis tool which is excellent in the processing of nonlinear and nonstationary signals. It is being used widely in many areas like image processing, 30 fault detection, 31‐33 forecasting, 34 speech processing, 35 and signal denoising 36,37 . Earlier, various decomposition methods like Empirical Mode Decomposition (EMD), Local Mean Decomposition (LMD) were used extensively in various fields but the problem of mode mixing has restricted their application.…”

Section: Introductionmentioning

confidence: 99%

An efficient interference mitigation approach for NavIC receivers using improved variational mode decomposition and wavelet packet decomposition

Lorraine

Madhu

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Reliable positioning, timing, and navigation services have become vitally important in safety and security applications. Hence, the need for Global Navigation Satellite Systems (GNSS) is growing continually. However, Continuous Wave Interference (CWI) was found to be one of the major potential threats of GNSS systems which degrades the receiver's performance. So, in this paper, a new approach using Improved Variational Mode Decomposition and Wavelet Packet Decomposition (IVMD‐WPD) has been proposed to mitigate CWI in NAVigation with Indian Constellation (NavIC) receivers. Although VMD is considered as an excellent signal analysis tool in decomposing non‐stationary and complex signals, the accuracy of the decomposition results depends upon the parameter setting. To address this, firstly, Normalized Kurtosis Energy Ratio (nKER) evaluation index is constructed. Then, the principle of nKER maximum is implemented to find the optimal parameters of VMD. Using the optimized parameters, the received signal is decomposed by IVMD into sub‐signals. Secondly, the mutual information index is introduced to extract the information dominant modes. The extracted modes are then processed by wavelet packet filter and finally, the desired signal is reconstructed. The proposed IVMD‐WPD method not only reduces the jamming efficiently but also overcomes the limitations of VMD. Moreover, by integrating IVMD with wavelet packet filter, the remaining effects of jamming and noise present in desired modes can be filtered thereby enhancing the performance. Simulation results reveal that the proposed method performs better in comparison with the conventional techniques in case of a single tone, multi‐tone, and chirp jamming environments.

show abstract

“…On the other hand, deep learning approaches based on multi-layer networks such as the convolutional neural network (CNN) are promising for overcoming such feature selection problems without advance need for feature sets. GoogleNet, AlexNet, VGGNet, ResNet, and DenseNet are good examples of deep learning models [ 34 , 35 , 36 , 37 , 38 , 39 , 40 ].…”

Section: Introductionmentioning

confidence: 99%

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Song

Kim

et al. 2021

Sensors

View full text Add to dashboard Cite

Recently, Doppler radar-based foot gesture recognition has attracted attention as a hands-free tool. Doppler radar-based recognition for various foot gestures is still very challenging. So far, no studies have yet dealt deeply with recognition of various foot gestures based on Doppler radar and a deep learning model. In this paper, we propose a method of foot gesture recognition using a new high-compression radar signature image and deep learning. By means of a deep learning AlexNet model, a new high-compression radar signature is created by extracting dominant features via Singular Value Decomposition (SVD) processing; four different foot gestures including kicking, swinging, sliding, and tapping are recognized. Instead of using an original radar signature, the proposed method improves the memory efficiency required for deep learning training by using a high-compression radar signature. Original and reconstructed radar images with high compression values of 90%, 95%, and 99% were applied for the deep learning AlexNet model. As experimental results, movements of all four different foot gestures and of a rolling baseball were recognized with an accuracy of approximately 98.64%. In the future, due to the radar’s inherent robustness to the surrounding environment, this foot gesture recognition sensor using Doppler radar and deep learning will be widely useful in future automotive and smart home industry fields.

show abstract

Modulation recognition for radar emitter signals based on convolutional neural network and fusion features

Cited by 23 publications

References 33 publications

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network

An efficient interference mitigation approach for NavIC receivers using improved variational mode decomposition and wavelet packet decomposition

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Contact Info

Product

Resources

About