Research Article
Continuous IFF Response Signal Recognition Technology Based on Capsule Network
@INPROCEEDINGS{10.1007/978-3-030-90196-7_39, author={Yifan Jiang and Zhutian Yang and Chao Bo and Dongjia Zhang}, title={Continuous IFF Response Signal Recognition Technology Based on Capsule Network}, proceedings={Artificial Intelligence for Communications and Networks. Third EAI International Conference, AICON 2021, Xining, China, October 23--24, 2021, Proceedings, Part I}, proceedings_a={AICON}, year={2021}, month={11}, keywords={Identification of friend or foe (IFF) DM-CapsNet Attention mechanism Co-frequency interference}, doi={10.1007/978-3-030-90196-7_39} }- Yifan Jiang
Zhutian Yang
Chao Bo
Dongjia Zhang
Year: 2021
Continuous IFF Response Signal Recognition Technology Based on Capsule Network
AICON
Springer
DOI: 10.1007/978-3-030-90196-7_39
Abstract
Identification of friend or foe (IFF) system has become an indispensable part in modern war. In order to meet the needs of air target situation control in rapid response operations, it is urgent to find an intelligent IFF signal recognition method. Aiming at the problems of low recognition accuracy and high false alarm rate of continuous IFF signal of single channel multiple air maneuvering targets in low SNR environment, a signal pattern recognition method of continuous IFF signal based on capsule network and attention mechanism in complex environment is proposed by improving signal data set and capsule network model structure. Using the good generalization ability and strong feature interpretation ability of attention mechanism provided by capsule network, the improved method has a certain degree of improvement in the pattern recognition ability of simulated complex signals compared with traditional frame detection method and multilayer convolutional neural network. At the same time, the false alarm rate and the missed alarm rate are significantly improved, which can meet the actual detection requirements.
