Radar signal recognition based on triplet convolutional neural network

Liu, Lutao; Li, Xinyu

doi:10.1186/s13634-021-00821-8

Cited by 13 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al studied the modulation recognition algorithm when the channel state information is unknown in the multicarrier scenario. First, the energy detector is used to confirm the working subcarriers, then the expectation maximization algorithm is used to estimate the channel state information, and finally, the HLRT function is constructed according to the estimated parameters to realize signal recognition [6]. Although the above modulation recognition algorithms can achieve high recognition rate, compared with the pattern recognition methods based on feature extraction, these algorithms have high computational complexity and are difficult to be applied in practical engineering projects.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Modulation and Recognition of Robot Communication Signal Based on Deep Learning Neural Network

Zou

2022

Journal of Sensors

View full text Add to dashboard Cite

In order to solve the problem that the traditional method of manually extracting expert features for communication signal recognition has large limitations and low accuracy under low signal-to-noise ratio, this paper proposes an automatic modulation and recognition method of robot communication signal based on deep learning neural network. In this method, the received signal is preprocessed to obtain the complex baseband signal including in-phase component and quadrature component. The signal is used as the data set of the input convolution neural network model. The model structure and the super parameters such as convolution kernel, step size, characteristic graph, and activation function are adjusted through multiple training, and the trained model is used to extract and recognize the features of the communication signal. It realizes the identification and classification of seven types of digital communication signals: 2FSK, 4FSK, BPSK, 8PSK, QPSK, QAM16, and QAM64. The experimental results show that the average recognition accuracy of the seven signals has reached 94.61% when the signal-to-noise ratio is 0 dB. Conclusion. The algorithm is proved to be effective and has high accuracy under the condition of low signal-to-noise ratio.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Automatic Modulation and Recognition of Robot Communication Signal Based on Deep Learning Neural Network

Zou

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…By expanding Equation (10), the following can be obtained: (11) Expanding Equation ( 11) into real and imaginary parts: (13) Expanding ( 11) and ( 12):…”

Section: Cyclic Mean Analysis Of the Fm Signalmentioning

confidence: 99%

“…Among these, σ(σ ＞0) is known as the scaling factor, which substitutes (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11) into the unified expression of the Cohen class time-frequency distribution. If the continuous signal is…”

Section: Cwd Time-frequency Analysis Image Generationmentioning

confidence: 99%

“…The authors of [ 10 ] propose RRSARNet, a new artificial neural network based on meta-transfer learning, which can recognize STFT images and adaptively recognize signals. In [ 11 ], to solve the problem of LPI radar waveform recognition at low SNR, a triple convolutional neural network was designed to recognize PWVD time-frequency images, and the recognition accuracy reached 94% at −10 dB. In [ 12 ], the CMWT time-frequency graph was input into the ResNet (SEP-ResNet) network, which could classify the enhanced T-F images and complete the high-precision intelligent recognition of radar-modulated signals in a low SNR environment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Low SNR Multi-Emitter Signal Sorting and Recognition Method Based on Low-Order Cyclic Statistics CWD Time-Frequency Images and the YOLOv5 Deep Learning Model

Huang

Yan

Hao

et al. 2022

Sensors

View full text Add to dashboard Cite

It is difficult for traditional signal-recognition methods to effectively classify and identify multiple emitter signals in a low SNR environment. This paper proposes a multi-emitter signal-feature-sorting and recognition method based on low-order cyclic statistics CWD time-frequency images and the YOLOv5 deep network model, which can quickly dissociate, label, and sort the multi-emitter signal features in the time-frequency domain under a low SNR environment. First, the denoised signal is extracted based on the low-order cyclic statistics of the typical modulation types of radiation source signals. Second, the time-frequency graph of multisource signals was obtained through CWD time-frequency analysis. The cyclic frequency was controlled to balance the noise suppression effect and operation time to achieve noise suppression of multisource signals at a low SNR. Finally, the YOLOv5s deep network model is used as a classifier to sort and identify the received signals from multiple radiation sources. The method proposed in this paper has high real-time performance. It can identify the radiation source signals of different modulation types with high accuracy under the condition of a low SNR.

show abstract

“…The network is composed of a shallow CNN, an attention-based bidirectional long shortterm memory (LSTM) network, and a dense neural network. Liu and Li [29] put forward an automatic recognition approach for modulating different low probability of intercept (LPI) radar signals. Firstly, the time-domain signals were converted into TFIs, using a smooth pseudo-Wigner-Ville distribution.…”

Section: Introductionmentioning

confidence: 99%

Marine Distributed Radar Signal Identification and Classification Based on Deep Learning

Liu¹,

Antypenko²,

Sushko³

et al. 2021

View full text Add to dashboard Cite

Distributed radar is applied extensively in marine environment monitoring. In the early days, the radar signals are identified inefficiently by operators. It is promising to replace manual radar signal identification with machine learning technique. However, the existing deep learning neural networks for radar signal identification consume a long time, owing to autonomous learning. Besides, the training of such networks requires lots of reliable time-frequency features of radar signals. This paper mainly analyzes the identification and classification of marine distributed radar signals with an improved deep neural network. Firstly, the time frequency features were extracted from signals based on short-time Fourier transform (STFT) theory. Then, a target detection algorithm was proposed, which weighs and fuses the heterogenous marine distributed radar signals, and four methods were provided for weight calculation. After that, the frequency-domain priori model feature assistive training was introduced to train the traditional deep convolutional neural network (DCNN), producing a CNN with feature splicing operation. The features of time- and frequency-domain signals were combined, laying the basis for radar signal classification. Our model was proved effective through experiments.

show abstract

Radar signal recognition based on triplet convolutional neural network

Cited by 13 publications

References 44 publications

Automatic Modulation and Recognition of Robot Communication Signal Based on Deep Learning Neural Network

Automatic Modulation and Recognition of Robot Communication Signal Based on Deep Learning Neural Network

Low SNR Multi-Emitter Signal Sorting and Recognition Method Based on Low-Order Cyclic Statistics CWD Time-Frequency Images and the YOLOv5 Deep Learning Model

Marine Distributed Radar Signal Identification and Classification Based on Deep Learning

Contact Info

Product

Resources

About