Emitter signals modulation recognition based on discriminative projection and collaborative representation

Li, Dongjin; Yang, Ruijuan; Dong, Ruijie; Zuo, Jiajun

doi:10.1049/iet-rsn.2019.0550

Cited by 5 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the existing methods are not suitable for the same frequency or spectrum mixed signals, or only for the overlapping signals whose signal components are periodic signals with different periods, so they have certain limitations. With the development of big data and the improvement of computing power, deep learning has achieved great success in temporal signal processing, such as speech recognition, speech separation [13][14][15][16][17][18][19][20][21][22], communication and radar signal modulation recognition [23][24][25][26][27][28][29], demonstrating its powerful feature extraction and temporal signal processing capabilities. However, the application of deep learning in communication and radar signal processing is more common in conventional modulation recognition and classification tasks, but not in complex sequential regression tasks such as SCBSS.…”

Section: Introductionmentioning

confidence: 99%

Single channel blind source separation of complex signals based on spatial‐temporal fusion deep learning

Luo¹,

Yang²,

Jin³

et al. 2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Blind Source Separation (BSS) of complex signals composed of radar, communication and jamming signals is the first step in an integrated electronic system, which requires higher accuracy of separation. However, the traditional Single‐Channel Blind Source Separation (SCBSS) method has low separation accuracy and poor robustness. Aiming at this problem, this paper proposes a SCBSS method based on spatial‐temporal fusion deep learning model. This is a deep neural network model, which realizes spatial‐temporal of mixed signals by integrating Convolutional Neural Network (CNN) and Bidirectional Long Short‐Term Memory Network (BiLSTM). Convolutional Neural Network is used to extract spatial features from input sequences, and BiLSTM is used to mine timing rules of signals. A batch normalisation layer and a dropout layer are added to improve stability and prevent overfitting. The experiments show that the average similarity coefficient of the separated signals is above 0.99 and the Signal‐Distortion Ratio (SDR) is up to 27 dB without noise. When the Signal‐Noise Ratio is 0–20 dB and Jamming‐Signal Ratio is 15 dB, the SDR is 5–30 dB higher than the traditional methods and the single network structure deep learning methods.

show abstract