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

Huynh‐The, Thien; Doan, Van‐Sang; Hua, Cam-Hao; Pham, Quoc-Viet; Nguyen, Toan-Van; Kim, Dong-Seong

doi:10.1109/lwc.2021.3075880

Cited by 73 publications

(41 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Choi-Williams distribution (CWD) describes the timefrequency characteristics, which belongs to the Cohenlike time-frequency distribution. CWD is obtained by twodimensional convolution of the Wigner-Ville distribution with a kernel function, which is an improved method for the defects of the Wigner-Ville distribution as [12]…”

Section: A Choi-williams Distributionmentioning

confidence: 99%

“…where w * is the optimal weight. Due to the inherent complexity of most machine learning models, it is usually impossible to find a closed-form solution to (12). Therefore, the gradient descent method is usually used to solve (12).…”

Section: Distributed Federated Learningmentioning

confidence: 99%

“…Due to the inherent complexity of most machine learning models, it is usually impossible to find a closed-form solution to (12). Therefore, the gradient descent method is usually used to solve (12). Here, a typical distributed gradient descent algorithm is used to solve (12).…”

Section: Distributed Federated Learningmentioning

confidence: 99%

“…Therefore, the gradient descent method is usually used to solve (12). Here, a typical distributed gradient descent algorithm is used to solve (12). At present, this algorithm is widely used in federated learning.…”

Section: Distributed Federated Learningmentioning

confidence: 99%

See 3 more Smart Citations

Radio Frequency Fingerprint Collaborative Intelligent Blind Identification for Green Radios

Liu

Chen

et al. 2023

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

show abstract

Section: A Choi-williams Distributionmentioning

confidence: 99%

Section: Distributed Federated Learningmentioning

confidence: 99%

Section: Distributed Federated Learningmentioning

confidence: 99%

Section: Distributed Federated Learningmentioning

confidence: 99%

See 2 more Smart Citations

Radio Frequency Fingerprint Collaborative Intelligent Blind Identification for Green Radios

Liu

Chen

et al. 2023

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…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%

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

A method for LPI radar signals recognition based on complex convolutional neural network

Liu

Wang²,

et al. 2023

Int J Numerical Modelling

View full text Add to dashboard Cite

For the low probability of intercept (LPI) radar signal recognition problem, recognition algorithms based on deep learning usually use time‐frequency analysis to convert the signal into a two‐dimensional feature image for classification and recognition. However, these methods often have problems with large network size, high computational complexity, and huge memory consumption, making them difficult to apply on small devices with limited computational power and storage space. This paper proposes an LPI radar signal recognition method based on a lightweight complex convolutional neural network, named CV‐LPINet. It uses a complex convolutional module to complete data fusion of IQ sampled signals, uses a deep separable convolutional module to extract features and reduce dimensions, and introduces residual structures to improve network training. Experiments show that the average recognition accuracy of this method is 91.76% with a signal to noise ratio in the range of −6 to 10 dB, and its recognition accuracy is similar to that of typical algorithms. However, the network size is significantly reduced and the computational complexity is low, making it suitable for small intelligent devices.

show abstract

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

Cited by 73 publications

References 14 publications

Radio Frequency Fingerprint Collaborative Intelligent Blind Identification for Green Radios

Radio Frequency Fingerprint Collaborative Intelligent Blind Identification for Green Radios

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

A method for LPI radar signals recognition based on complex convolutional neural network

Contact Info

Product

Resources

About