Machine Learning
Automatic identification of digital modulation types
Signal Processing
Digital modulation classification using constellation shape
Signal Processing
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Combined likelihood power estimation and multiple hypothesis modulation classification
ASILOMAR '95 Proceedings of the 29th Asilomar Conference on Signals, Systems and Computers (2-Volume Set)
Hi-index | 0.00 |
Automatic modulation type identification (AMTI) has seen increasing demand for both military and civilian, nowadays. Most of previous methods have been proposed on classification of modulations in additive white Gaussian noise (AWGN) channels. However in real world scenarios, communication channels suffer from dispersion (fading). This paper proposes a novel automatic digital modulation types identifier (ADMTI) in dispersive environment. In the ADMTI's structure, undesired effects of channel are mitigated by an equalizer. Higher order cumulants and moments (up to eighth) are used as features and classification is performed by a multiclass SVM-based classifier. Simulation results show that ADMTI is able to identify different types of modulations (e.g. QAM64, V.29, and ASK8) with high accuracy even at low SNRs.