Automatic RadarWaveform Recognition Based on Deep Convolutional Denoising Auto-encoders 基于深卷积去噪自动编码器的雷达波形自动识别.pdfVIP

Circuits Syst Signal Process /10.1007/s00034-018-0757-0 Automatic Radar Waveform Recognition Based on Deep Convolutional Denoising Auto-encoders Zhiwen Zhou1 · Gaoming Huang1 · Haiyang Chen1 · Jun Gao1 Received: 30 November 2016 / Revised: 8 January 2018 / Accepted: 10 January 2018 © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Aimed at the deficiency of traditional feature extraction techniques in radar emitter recognition, a novel deep feature extraction and recognition architecture is proposed. To fit into the model, the time-domain emitters are transformed into unique time-frequency images correspondingly. Since auto-encoders restrict the input data to be vector-form and convolutional model is hard to optimize, denoising auto-coders are stacked in a convolutional manner in the pre-training stage and the proposed frame- work is trained by greedy layer-wise algorithm. The optimized network parameters are employed to initialize convolutional neural networks. By layers of mapping and pool- ing, deep time-frequency features are extracted, which are fed into the collaborative representation-based classifier to implement classification task. Experimental results on simulated data validate the feasibility of the proposed architecture. Furthermore, compared with conventional shallow algorithms, the proposed one can obtain higher recognition accuracy and more robust performance. Taking advantage of collabora- tive representation, the proposed algorithm is more applicable to the small-sample-size case. B Zhiwen Zhou mini_paper@ Gaoming Huang hgaom@163.com Haiyang Chen hychen@ Jun Gao gaojun@163.com 1 Electronic Engineering College, Naval University of Engineering, Wuhan 430033, People’s Republic of China Circuits Syst Signal Process Keywords Radar waveform recognition · Fe