A Robust Hierarchical Digital Modulation Classification Technique: using Linear Approximations

Automatic modulation recognition has become an essential tool for COMINT. In this paper we use a feature-based method introducing new intuitive features for real-time classification of digitally modulated signals without any prior knowledge of signal parameters. The incoming signal's basic modulation type is detected i.e. FSK, PSK, ASK, QAM, & GMSK and then its order is identified. This hierarchical classification can be considered a step towards a general modulation classifier in AWGN channel. Linear approximations are introduced in instantaneous amplitude and non-linear component of instantaneous phase which result in improved performance of the system at lower SNR values. Simulations show that with the new feature set classification success rate is 99.9% at very low SNR i.e. 5 dB