Title :
Neural network implementation for reliability evaluation
Author :
Hachem, Nabil ; Bedi, Jatinder
Author_Institution :
Lawrence Technol. Univ., Southfield, MI, USA
Abstract :
A new method for computing the terminal reliability of communication systems using artificial neural networks is presented. The algorithm utilizes an improved method for minimizing Boolean functions to obtain the reliability expression, and a multilayer neural network to implement the system. It is assumed that reliable nodes and the probability of link existence of each link is known. Examples illustrate the new method
Keywords :
Boolean functions; backpropagation; multilayer perceptrons; probability; telecommunication computing; telecommunication links; telecommunication network reliability; Boolean functions minimisation; algorithm; artificial neural networks; back propagation; communication system; link existence probability; multilayer neural network; neural network implementation; reliability evaluation; reliable node; terminal reliability; Artificial neural networks; Boolean algebra; Boolean functions; Communication networks; Computer network reliability; Computer networks; Minimization methods; Multi-layer neural network; Neural networks; Telecommunication network reliability;
Conference_Titel :
Southeastcon '96. Bringing Together Education, Science and Technology., Proceedings of the IEEE
Conference_Location :
Tampa, FL
Print_ISBN :
0-7803-3088-9
DOI :
10.1109/SECON.1996.510090
