Dinamisasi Parameter pada Fuzzy Model Xu dalam Toolbox Algoritma Fuzzy Evolusi
Fuzzy Evolutionary Algorithm (FEA) is a hybrid model between genetic algorithms and fuzzy logic. Model Xu and Vukovich was one of the FEA model that uses fuzzy logic to determine the probability of crossover and mutation probability with the input of population size and number of generations. This c...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Theses and Dissertations NonPeerReviewed |
| Published: |
[Yogyakarta] : Universitas Gadjah Mada
2013
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/123426/ http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=63537 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universitas Gadjah Mada |
| Summary: | Fuzzy Evolutionary Algorithm (FEA) is a hybrid model between genetic
algorithms and fuzzy logic. Model Xu and Vukovich was one of the FEA model
that uses fuzzy logic to determine the probability of crossover and mutation
probability with the input of population size and number of generations. This
concept has the weakness that if the value of the input fuzzy logic such as
population size is static value then the value of the resulting output will also be a
static value. This allows slow search times because the parameters used in the
FEA is worth staying and the results in a less than optimal solution.
This study was conducted to improve the weakness in the fuzzy logic model
of Xu and Vukovich, is to develop the concept of the Population Resizing on
Fitness Improvement Fuzzy Evolutionary Algorithm (PRoFIFEA) ) who
collaborate on models Population Resizing on Fitness Improvement Genetic
Algorithm (PRoFIGA) for the determination of the size of the population used as
input in the fuzzy logic. In this research, the development is used at PRoFIFEA
toolbox and function of PROFIFEA. For the testing is used the case of
optimization function and Travelling Salesman Problem (TSP). For comparison
will be tested in the same case using FEA models of Xu and Vukovich and using
the genetic algorithm.
Based on the test results show that PRoFIFEA is produce more optimal
solutions than the solutions generated by the fuzzy evlutionary algorithm model of
Xu and Vukovich and genetic algorithms. PRoFIFEA also has a diversity of
individuals in a population level that is higher than the other two algorithms. With
levels greater diversity of individuals expected to prevent trapped in local
optimum. This proves that the concept PRoFIFEA able to improve the
performance of running processes and produce more optimal solutions. |
|---|