Title :
Modulation classification in fading multipath channel
Author :
Venäläinen, Juha ; Terho, Liisa ; Koivunen, Vasa
Author_Institution :
Signal Process. Lab., Helsinki Univ. of Technol., Espoo, Finland
Abstract :
A system for modulation classification in a dispersive communication channel is developed. The channel equalizer and symbol rate are blindly estimated from data. The features used for recognition include cumulants and moments computed from a polar coordinate representation of the IQ-plane. The actual classification is performed using a neural MLP classifier. Simulation results are presented using the WSSUS (wide sense stationary uniform scattering) channel model in typical urban and hilly terrain scenarios. Highly accurate recognition is achieved even at low signal-to-noise ratios. The importance of the equalization stage is clearly demonstrated.
Keywords :
blind equalisers; channel estimation; dispersive channels; fading channels; feedforward neural nets; higher order statistics; modulation; multilayer perceptrons; multipath channels; signal classification; telecommunication computing; SNR; blind estimation; channel equalizer; cumulants; dispersive channel; fading channel; fading multipath channel; feedforward neural classifier; hilly terrain scenario; modulation classification; multilayer perceptrons; neural MLP classifier; polar coordinate representation; signal-to-noise ratio; typical urban scenario; Communication channels; Computational modeling; Equalizers; Fading; Feedforward systems; Laboratories; Multipath channels; Radio spectrum management; Surveillance; Transceivers;
Conference_Titel :
Signals, Systems and Computers, 2002. Conference Record of the Thirty-Sixth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-7803-7576-9
DOI :
10.1109/ACSSC.2002.1197103
