Project scheduling using a genetic algorithm with adaptable changing genetic operators
β Scribed by Tomoya Ikeuchi; Yoshitomo Ikkai; Dai Araki; Takenao Ohkawa; Norihisa Komoda
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 252 KB
- Volume
- 124
- Category
- Article
- ISSN
- 0424-7760
No coin nor oath required. For personal study only.
β¦ Synopsis
Genetic algorithms (GA) have been widely used to solve planning problems. However, they require one to determine the optimal values of many genetic parameters, such as population sizes, crossover probability, mutation probability, and so on. To make matters worse, the most suitable combination of parameters for one problem is not always optimal for others. Therefore, these parameters should be tuned whenever the problem changes.
In this paper, we propose an adaptable GA mechanism that has autonomic parameter tuning for the composition of generic operators. This mechanism raises questions concerning the probability of genetic operators that acted effectively, that is, the probability that one operator created better individuals than the other operators. It also successively adjusts the combinations of genetic parameters suitable for the target problem. We applied the adaptable GA mechanism to a project scheduling model (PSM) and evaluated it with manual tuning methods.
π SIMILAR VOLUMES
A genetic algorithm with an adapti¨e chromosome structure is proposed to reconstruct the electrical parameters of a multilayered radome of finite size. In order to a¨oid the complicated scattering from the edges of the radome, a Gaussian beam is used to illuminate the central area of the radome surf
Precision and accuracy in determining rates of Down syndrome at livebirth are indispensible to algorithms which determine eligibility for prenatal cytogenetic diagnostic services. W e derived Down syndrome rates by single year of maternal age which we propose as a revised rate schedule for backgroun