By Topic

A genetic algorithm tracking model for product deployment in telecom services

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

3 Author(s)
Murphy, L. ; Electr. & Syst. Eng., Oakland Univ., Rochester, MI ; Abdel-Aty-Zohdy, H.S. ; Hashem-Sherif, M.

Genetic algorithms (GA) are designed to search for, discover and emphasize good solutions by applying selection and crossover techniques, inspired by nature, to supply solutions to engineering systems. Genetic algorithms operate on pieces of information like nature does on genes in the course of evolution. All individuals of one generation are evaluated by a fitness function. This paper presents an approach to implement a genetic algorithm to depict a recently developed "Integrated Model" for defect tracking for product deployment in telecommunication systems by means of a solution space representing target variables. The genetic algorithm inputs these target values as dynamic input measurements. From these measurements, the best possible fused values are found for the target variables. The goal of the genetic algorithm is dynamically to update the parameters applied to the input measurements to find the optimum solution for the defect tracking model system. Focus will be given to one dimension of sensor input measurements consisting of three four-bit binary sensor inputs varying within a given range of data points. The genetic algorithm is applied to these inputs by means of a 64 6-bit random member binary population using the "half-sibling and a clone" (HSAC) technique of crossover and mutation. The population members are evaluated using a fitness function where the fittest individuals are retained to survive and produce offspring for the next generation and the remainder is discarded. Genetic diversity is maintained through using a roulette wheel technique. The simulation tool MATLAB will be used to simulate the genetic algorithm. The genetic algorithm will be completed in VLSI using Verilog and the Mentor Graphics tools. The first stage components have been designed and completed using the Mentor Graphics toolset

Published in:

Circuits and Systems, 2005. 48th Midwest Symposium on

Date of Conference:

7-10 Aug. 2005