Automatic Radar Waveform Recognition Based on Deep Convolutional Denoising Auto-encoders
- 195 Downloads
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 framework is trained by greedy layer-wise algorithm. The optimized network parameters are employed to initialize convolutional neural networks. By layers of mapping and pooling, 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 collaborative representation, the proposed algorithm is more applicable to the small-sample-size case.
KeywordsRadar waveform recognition Feature extraction Deep learning Convolutional neural network Collaborative representation
The authors would like to thank all the reviews and the editors for their precious suggestions. This work is supported by the National High Technology Research and Development Program of China (No.2014AA7014061) and the National Natural Science Foundation of China (No. 61501484).
- 6.X.B. Han, Y.F. Zhong, B. Zhao et al., Unsupervised hierarchical convolutional sparse auto-encoder for high spatial resolutional imagery scene classification, in International Conference on Natural Computation 15–17 Aug (2015), pp 42–46Google Scholar
- 9.J. Lunden, L. Terho, V. Koivunen, Waveform recognition in pulse compression radar systems, in IEEE Workshop on Mach. Learn. for, Signal Process (2005), pp. 271–276Google Scholar
- 11.J. Masci, U. Meier, C. Dan et al., Stacked convolutional auto-encoders for hierarchical feature extraction, in Interantional Conference on Artificial Neural Network Espoo, Finland, June 14–17 (2011), pp. 52–59Google Scholar
- 15.P. Vincent, H. Larochelle, Y. Bengio et al., Extracting and composing robust features with denoising autoencoders, in ICML Interantional Conference on Machine Learn, New York, USA (2008), pp. 1096–1103Google Scholar
- 18.Z.W. Zhou, G.M. Huang, J. Gao, An emitter fusion recognition algorithm based on multi-collaborative representations, in International Congress on Image Signal Process, Liaoning, China (2015), pp. 1231–1235Google Scholar