A method for LPI radar signals recognition based on complex convolutional neural network.
In: International Journal of Numerical Modelling, Jg. 37 (2024), Heft 1, S. 1-13
Online
academicJournal
Zugriff:
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. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Numerical Modelling is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
A method for LPI radar signals recognition based on complex convolutional neural network.
|
---|---|
Autor/in / Beteiligte Person: | Liu, Zhilin ; Wang, Jindong ; Wu, Tong ; He, Tianzhang ; Yang, Bo ; Feng, Yuntian |
Link: | |
Zeitschrift: | International Journal of Numerical Modelling, Jg. 37 (2024), Heft 1, S. 1-13 |
Veröffentlichung: | 2024 |
Medientyp: | academicJournal |
ISSN: | 0894-3370 (print) |
DOI: | 10.1002/jnm.3155 |
Schlagwort: |
|
Sonstiges: |
|