A Highly Functional Decision Paradigm Based on Nonlinear Adaptive Genetic Algorithm
Abstract
In Phase 2, the genetic algorithm (GA) developed in Phase 1 was refined and integrated with a neural network for network topology optimization. In addition, a Mathlink GA was developed as a Mathematica module. POC wrote the Mathematica plug-in module as a function optimizer using Mathlink. The GA route optimizer was written, tested, and demonstrated. On the hardware side, a TMS320C80 based parallel DSP board was used as a testbed for parallel GA. The GA programs running on the parallel computing hardware exhibited a significant speedup.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 07, 1997
- Accession Number
- ADA344278
Entities
People
- Andrew Kostrzewski
- Jeongdal Kim