Hierarchical Approach to the Classification of Digital Modulation Types in Multipath Environments

摘要

This study presents a hierarchical classification approach to the classification of digital modulation schemes of types 2,4,8-PSK, 2,4,8-FSK and 16,64,256-QAM in low SNR levels and multipath propagation channel conditions. A hierarchical tree-based classification approach is selected as it leads to a relatively simple overall scheme with few parameters needed to differentiate between the various modulation types. Back-propagation neural network units are adopted at each tree node because they offer the flexibility needed to cope with varying propagation environments, as is the case in real-world communications. The selection of robust and well-defined higher-order statistics-based class features is considered and a small number of cumulates and moments chosen to differentiate between all various types of modulation types, except for specific M-QAM types. Simulations show that M-QAM types may be so affected by multipath and fading that higher-order statistic parameters become of very limited use. While being part of the hierarchical procedure, the identification of specific M-QAM types is conducted via equalization algorithms. Extensive simulations show overall classification performances to be strongly affected by the amount of multipath distortion and noise in the transmission channels. Results also show a much higher sensitivity of high-order M-QAM types to fading and multipath propagation distortions than other modulation types.