Study for classification and recognition of radar emitter intra-pulse signals based on the energy cumulant of CWD

Pengyu, Dong; Wang, Hongwei; Xiao, Baihua; Chen, You; Sheng, Tao; Zhang, Hubiao; Zhou, Yipeng

doi:10.1007/s12652-020-02722-4

Cited by 3 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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 [ 5 ] study generalized Hankel matrix factorization and propose a new cyclic mean kernel function, which can improve the accuracy of parameter estimation in a low SNR electromagnetic environment. The method proposed in [ 6 ] accumulates signal energy and suppresses noise, and uses a deep confidence network to automatically sort and identify radiation source signals. The accuracy of this method is 90% at −5 dB.…”

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

Section: Cwd Time-frequency Analysis Image Generationmentioning

confidence: 99%

Section: Introductionmentioning

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

show abstract

“…It is also necessary to extract deeper and more adaptable signal features. The time-frequency analysis method, which is suitable for nonstationary signal processing such as the radar emitter, has been widely used in the extraction of intra-pulse features, including Choi-Williams distribution (CWD) [8,9], Wigner-Ville distribution (WVD) [10,11], smooth pseudo Wigner-Ville distribution (SPWVD) [12,13] and so on. As deep learning has made great progress in the field of image recognition, deeper intra-pulse signal features are automatically excavated by time-frequency transform and deep learning, which have better generalization.…”

Section: Introductionmentioning

confidence: 99%

Radar waveform recognition based on a two‐stream convolutional network and software defined radio

Xia

Huang

2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

As one of the key technologies of electromagnetic spectrum operations, radar waveform recognition is an important basis for judging the threat degree of enemy’s weapons. At present, it is difficult to recognize the waveform at low signal‐to‐noise ratio (SNR), and the theoretical simulation is used in most research studies, which leads to the problem that the engineering practicality of the algorithm is poor. In this paper, a two‐stream convolutional network radar waveform recognition (TCNRWR) algorithm that fuses the original time–frequency image and the continuous frames autocorrelation time–frequency image is proposed, and an experimental platform is built by using software defined radio technology. Compared with traditional theoretical simulations, this paper focusses on the influence of spatial background interference and signal incompleteness on the recognition of intra‐pulse signals, and proposes an automatic removal method of invalid signal in the time–frequency domain. In order to further improve the recognition rate at low SNR, a deeper feature of short‐time autocorrelation flow is excavated, and a two‐stream time–frequency images fusion convolutional network (TTIFCNet) is constructed. The network effectively fuses the pre‐classification results of the two streams through Softmax layer and different weights. Finally, the hardware platform HackRF is used to realize the communication and processing of signals in real space, which proves the effectiveness of the TCNRWR algorithm.

show abstract

Multi-component signal separation based on ALSAE

Chen,

Lei,

Guo

et al. 2024

Wireless Netw

View full text Add to dashboard Cite

Study for classification and recognition of radar emitter intra-pulse signals based on the energy cumulant of CWD

Cited by 3 publications

References 35 publications

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

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

Radar waveform recognition based on a two‐stream convolutional network and software defined radio

Multi-component signal separation based on ALSAE

Contact Info

Product

Resources

About