By Topic

A neural network for constrained optimization with application to CDMA communication systems

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Fantacci, R. ; Dipt. di Elettronica e Telecomunicazioni, Univ. di Firenze, Italy ; Forti, M. ; Marini, M. ; Tarchi, D.
more authors

This brief proposes a neural network for the solution in real time of a class of quadratic optimization problems with equality and inequality constraints arising in code-division multiple access (CDMA) communication systems. The network, which is derived via a nonobvious modification of the circuit for nonlinear programming introduced by Kennedy and Chua, is shown to be globally asymptotically stable, and as such is able to compute the global optimal solution in real time, without the risk of spurious responses. Computer simulations are presented to verify the neural network optimization capabilities and speed, and the performance in the application to CDMA communication systems.

Published in:

Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on  (Volume:50 ,  Issue: 8 )