Research on the Effectiveness of Deep Convolutional Neural Network for Electromagnetic Interference Identification Based on I/Q Data

With the development of wireless communication technology, electromagnetic interference (EMI) artificial radio to weather radar increases significantly, which has a serious impact on quality data. Most research detecting and suppressing was based primary product radar. This paper researches effectiveness deep convolutional neural networks (DCNN) identify suppress I/Q data output from front end receiver. Firstly, this selected UNet, ResNet with UNet structure, DeepLab V3+ for semantic segmentation other signals. After segmentation, used linear interpolation method EMI. Finally, prediction precision model compared products before after EMI suppression evaluate DCNN. The results showed that all three models could effectively were improved suppression. It suggests use DCNN receiver can play certain effect identification interference.