Automatic modulation classification using stacked sparse auto-encoders
Ao Dai, Haijian Zhang, Hong Sun · 2016
Automatic modulation classification (AMC) plays a key role in cognitive radar, cognitive radio and some other civilian and military fields to identify the type of modulation. In this paper, a deep learning based modulation classification method is developed for discriminating digital modulated signals. This proposed method uses a stacked sparse auto-encoders to extract features from ambiguity function (AF) images of signals. The obtained features are fed into a softmax regression classifier in order to output reliable classification. The scheme has the capability to recognize 7 popular modulations including ASK, PSK, QAM, FSK, MSK, LFM, and OFDM. Experimental results show that, compared to some existing methods, the proposed method has a relatively higher accuracy and greatly improves the classification performance in low SNR situations.