Independent component analysis for multiple access interference noise cancellation

Multiple access interference cancellation system is based on the emerging unsupervised neural network learning technique called Independent Component Analysis (ICA) which can determine both the channel propagation transfer function [A] and independent sources S, provided that the channel is linear and an array of receiver antenna exists. The proposed technique works at various levels in a base band synchronous Direct Sequence Code Division Multiple Access (DS- CDMA) system. Simulation results show that the performance equivalent to single user is achievable in principle. The realistic channel propagation case involving time delay and multiple path effects will be considered for a practical system implementation.

[1]  Harold H. Szu,et al.  Continuous speech segmentation determined by blind source separation , 1998, Defense, Security, and Sensing.

[2]  Pornchai Chanyagorn,et al.  Human visual system singularity map analyses , 2000, SPIE Defense + Commercial Sensing.

[3]  H. Vincent Poor,et al.  Blind equalization and multiuser detection in dispersive CDMA channels , 1998, IEEE Trans. Commun..

[4]  Harold Szu.  Thermodynamics Energy for both Supervised and Unsupervised Learning Neural Nets at a Constant Temperature , 1999, Int. J. Neural Syst..

[5]  Tapani Ristaniemi,et al.  Advanced ICA-based receivers for DS-CDMA systems , 2000, 11th IEEE International Symposium on Personal Indoor and Mobile Radio Communications. PIMRC 2000. Proceedings (Cat. No.00TH8525).

[6]  Harold H. Szu,et al.  Local ICA for the Most Wanted face recognition , 2000, SPIE Defense + Commercial Sensing.

[7]  Aapo Hyvärinen,et al.  Survey on Independent Component Analysis , 1999 .

[8]  Harold H. Szu,et al.  Ranking ICA bases by associative memory recalls of training texture samples , 2000, SPIE Defense + Commercial Sensing.

[9]  Harold H. Szu,et al.  Unsupervised ICA neural networks applied to reticle optical trackers , 2000, SPIE Defense + Commercial Sensing.

[10]  H Szu,et al.  Landsat spectral demixing a la superresolution of blind matrix inversion by constraint MaxEnt neural nets , 1997, Defense, Security, and Sensing.

[11]  Harold H. Szu,et al.  Independent component analysis approach to resolve the multi-source limitation of the nutating rising-sun reticle based optical trackers , 2000 .

[12]  Harold H. Szu,et al.  ICA neural net to refine remote sensing with multiple labels , 2000, SPIE Defense + Commercial Sensing.

[13]  Harold H. Szu,et al.  Statistical mechanics demixing approach to selection of independent wavelet basis , 1998, Defense, Security, and Sensing.

[14]  Harold H. Szu,et al.  Multimedia authenticity with ICA watermarks , 2000, SPIE Defense + Commercial Sensing.

[15]  A. Nandi.  Blind estimation using higher-order statistics , 1999 .

[16]  Harold H. Szu,et al.  Blind de-mixing with unknown sources , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[17]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..