Line spectrum target recognition algorithm based on time‐delay autoencoder

• Published in: IET radar, sonar & navigation sonar & navigation, 2024-10, Vol.18 (10), p.1681-1690
• Main Authors: Ju, Donghao, Chi, Cheng, Li, Yu, Huang, Haining
• Format: Article
• Language: English
• Subjects: adaptive filters; feature extraction; sonar target recognition
• ISSN: 1751-8784; 1751-8792
• DOI: 10.1049/rsn2.12601

Effective extraction of target features has always been a key issue in target recognition technology in the field of signal processing. Traditional deep learning algorithms often require extensive data for pre‐training models to ensure the accuracy of feature extraction. Moreover, it is challenging to completely remove noise due to the complexity of the underwater environment. A Time‐Delay Autoencoder (TDAE) is employed to extract ship‐radiated noise characteristics by leveraging the strong coherent properties of line spectrum. This approach eliminates the need for previous data to adaptively develop a nonlinear model for line spectrum extraction. The test data was processed using three distinct approaches, and plots of recognition accuracy curves at various signal‐to‐noise ratios were made. On the dataset utilised in the research, experimental results show that the proposed approach achieves over 75% recognition accuracy, even at a signal‐to‐noise ratio of −15 dB. The strong coherent properties of line spectral features are utilised to extract ship radiation noise features using Time‐delay Autoencoder (TDAE) without relying on prior data for adaptively constructing a nonlinear model for line spectral feature extraction. Experimental results demonstrate that the proposed algorithm achieves over 75% recognition accuracy on the dataset used even at a signal‐to‐noise ratio of −15 dB.