Conference paper
Adaptive complex modified probabilistic neural network in digital channel equalization
IEEE
The Seventh Australian and New Zealand Intelligent Information Systems Conference (Perth, Western Australia, 18/11/2001–21/11/2001)
2001
Abstract
A novel adaptive technique is proposed for the complex-valued modified probabilistic neural network (MPNN). The adaptive feature is desirable when using the MPNN in channel equalization to track time-varying channels. The MPNN is initially trained using the clustering technique. When training is completed, the network is switched to decision-directed mode and the network parameters are adapted using stochastic gradient-based algorithms in an unsupervised manner. Simulations show that the equalizer was able to efficiently equalize 4-QAM symbol sequences transmitted through nonlinear, slowly time-varying channels.
Details
- Title
- Adaptive complex modified probabilistic neural network in digital channel equalization
- Authors/Creators
- J.P. Young (Author/Creator)T. Hanselmann (Author/Creator)A. Zaknich (Author/Creator)Y. Attikiouzel (Author/Creator)
- Conference
- The Seventh Australian and New Zealand Intelligent Information Systems Conference (Perth, Western Australia, 18/11/2001–21/11/2001)
- Publisher
- IEEE
- Identifiers
- 991005543722807891
- Copyright
- © 2001 IEEE
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
154 File views/ downloads
86 Record Views