Neural network techniques for multi-user demodulation

U. Mitra, H. Vincent Poor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations


Adaptive methods for demodulating multi-user communication in a Direct-Sequence Spread-Spectrum Multiple-Access (DS/SSMA) environment are investigated. In this setting the noise is characterized as being the sum of the interfering user's signals and additive Gaussian noise. The optimal receiver for DS/SSMA systems has a complexity that is exponential in the number of users. Adaptive Radial Basis Function (RBF) networks that operate with knowledge of only a subset of the system parameters are studied. This approach is further bolstered by the fact that the optimal detector in the synchronous case can be implemented by a RBF network when all of the system parameters are known. The RBF network's performance is compared with other multi-user detectors. The centers of the RBF neurons, when the system parameters are not fully known, are determined using clustering techniques. This work shows that the adaptive RBF network obtains near optimal performance and is robust in realistic communication environments.

Original languageEnglish (US)
Title of host publication1993 IEEE International Conference on Neural Networks
PublisherPubl by IEEE
Number of pages6
ISBN (Print)0780312007
StatePublished - 1993
Event1993 IEEE International Conference on Neural Networks - San Francisco, California, USA
Duration: Mar 28 1993Apr 1 1993

Publication series

Name1993 IEEE International Conference on Neural Networks


Other1993 IEEE International Conference on Neural Networks
CitySan Francisco, California, USA

All Science Journal Classification (ASJC) codes

  • General Engineering
  • Control and Systems Engineering
  • Software
  • Artificial Intelligence


Dive into the research topics of 'Neural network techniques for multi-user demodulation'. Together they form a unique fingerprint.

Cite this