Analysis of anti-interference detection ability of wave net network signal based on convolution neural. Issue 4 (March 2021)

• Record Type: Journal Article
• Authors: Chen, Tao; Sun, Yaxuan; Ding, Yulin
• Is Part Of: IOP conference series. Volume 714:Issue 4(2021)
• Publication Date: 2021-03
• Subjects: Convolutional neural network -- wave net network -- signal -- anti-interference; Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/714/4/042054
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: Deep learning has been widely used in image, speech, natural language, and robot and so on. However, how to use these technologies in radar detection is still very few. There are a lot of artificial design elements in the traditional radar processing, its application range must be considered practically, while the intelligent radar relies more on the self-learning and improvement ability of the algorithm itself. In this paper, a method of target detection based on convolution neural network is proposed. By matching the received signal with the transmitted waveform, the matching feature of the sliding window is extracted. Moreover, the feature information processed by convolution network is connected into a network, and the anti-jamming target detection under any transmitted waveform and given form of interference is completed. As a creative way, this paper compares the signal anti-interference detection and processing ability of convolution network and full connection network on independent distance unit, and finds that convolution network has the best effect.