Communication Channel Equalization- Pattern Recognition or Neural Networks?

Satnam Singh, Wayne Blanding, Vishal Ravindra, Krishna Pattipati
2006 2006 International Conference on Communication Technology  
The communication channel equalization is a difficult problem, especially when the channel is nonlinear and complex. Numerous algorithms are presented in the neural networks literature to solve this problem. In this paper, a comparison is made among the latest neural network techniques (Complex Minimal Resource Allocation Networks (CMRAN) [1]), a classical communication technique (Viterbi algorithm), and two pattern recognition techniques (Support Vector Machine (SVM), Learning Vector
more » ... on (LVQ)) to solve this problem. The simulation results show that Viterbi (MLSE decoding technique), and SVM methods outperform the CMRAN method.
doi:10.1109/icct.2006.342046 fatcat:mrjkasw53vet7nado43ogwix54