See the RobocodeJGAP page for details.
JGAP has been subject of various publications, applications and research projects. Find a list of currently known uses of JGAP below in loose order. If you know any other to be included here, please tell us (see main page, feedback section for contact information)!
If you want to cite JGAP, please do it as follows: Meffert, Klaus et al.: JGAP - Java Genetic Algorithms and Genetic Programming Package. URL: http://jgap.sf.net
Subject is the evolution of a game playing strategy for Backgammon. To accomplish this, the neural network framework JOONE has been used in conjunction with JGAP. The bridge between the two packages is another Sourceforge project named JOONEGAP.
Author: Michael James Collins
The research involves extending JGAP in order to
model genetic flow within metapopulations. The results are used to
investigate the relationship between population connectivity, population
dynamics and population genetic structure.
Author: Jonathan Kool
This research involves the use of JGAP in developing an Evolutionary Algorithm to assign airport arrival and departure times to flights based on a multi-objective fitness function. The fitness function includes historic flight and taxi times as well as airline and air traffic control preferences. To the abstract.
Author: Florian Hafner
JGAP has been used to help develop database performant queries for a huge number of datasets.
Author: Achim Westermann
Original title in German: Integration Evolutionärer Algorithmen in das MFOS
The thesis considers the following aspects:
Exploration of optimizing Fuzzy Controllers with Evolutionary Algorithms
Development of a Genetic Algorithm (GA) for optimizing the rule-base of Mamadani-type Fuzzy Controllers following the Pittsburgh-Approach
Design and Implementation of the Integration of the developed GA in the existing Java-Implementation of MFOS for Mamadani-type Fuzzy Controllers (MFOS-M)
Experiments with the Implementation of the GA show good performance
Author: Knut Willems
Title of the paper: Impact of Energy End-use and Customer Interruption Cost on Optimal Allocation of Switchgear in Constrained Distribution Networks
Accepted for future publication in IEEE Transactions on Power Delivery, see http://ieeexplore.ieee.org/.
Abstract: The introduction of new energy carriers, such as natural gas and district heating, to energy systems dominated by electrical power will certainly relieve stress on the power system. Some of the end uses initially served by the power system will be gradually decoupled and served by alternative energy carriers. As a result, the specific customer interruption costs and load profiles will change. In this paper, we analyze how the optimal level of switchgear in electric power distribution systems is affected by such changes. The proposed optimization method is based on a genetic algorithm and takes into account the constrained network capacity.
Authors: A. Helseth; A. T. Holen
Comparison of several evolutionary parameters for JGAP, done in the context of a thesis (last update: 17 August 2005). Besides an in-depth analysis, the article contains some nice graphs.
Authors: Rebecca Fiebrink
German book "JUnit Profi-Tipps", describing software testing with JUnit, and referencing JGAP as a prominent project massively utilizing unit tests. Link to Amazon.
Author: Klaus Meffert
Printed article in the German magazine JavaMagazin 08/2004. Original title: "Auf Darwins Spuren". Link to number 08/2004.
Author: Klaus Meffert
Printed article in the German magazine Der Entwickler 02/2005. Original title: "Einführung in die Genetische Programmierung". Link to number 02/2005. Download the article (local version)
Author: Klaus Meffert
Printed article in the German magazine JavaMagazin 05/2005. Original title: "Genetische Programmierung: leistungsfähiges Verfahren zur Problemlösung". Link to number 05/2005.
Author: Klaus Meffert
Weblog entry in the popular SAP Developer Network (SDN): Genetic Algorithms: Introducing JGAP
Author: Klaus Meffert
Weblog entry in the popular SAP Developer Network (SDN): Genetic Algorithms: The Darwinian Way
Author: Klaus Meffert
In Self-Managing Federated Services, Cuenca-Acuna et. al. use JGAP to find mappings of processes to nodes on a distributed system that optimize a Service-Level Agreement (SLA).
Authors: Francisco Matias Cuenca-Acuna, Thu D. Nguyen
Please see http://research.microsoft.com/~livshits/papers/pdf/thesis.pdf.
Author: Benjamin Livshits
|
|
See the RobocodeJGAP page for details. |
JOONEGAP allows for adjusting a Neural Network with help of a Genetic Algorithm. The frameworks involved are JOONE and JGAP.
Attention: developers needed for bringing the project up-to-date! Please contact us in case you are interested.
Result of the above mentioned dissertation is a full-blown Backgammon game with AI opponent, game board and nice-to-use graphical gaming interface. You could find it within JOONEGAP.
unEvo is an Eclipse plug-in designed to be a framework for the implementation of Evolutionary Algorithms focused on the Experimentation and Research process rather than the codification of the algorithm itself. EvoGAP in turn is a bridge between unEvo and JGAP. EvoGAP is currently under initial development.
HiperionCAD is a CAD tool for optical fiber networks design with a genetic algorithm optimization approach. Its a project sponsored by the North Electrical Company of Brazil's Eletronorte, and it was built using Eclipse, its Graphical Modeling Framework and JGAP. In a rough way, JGAP its used to model all the parameters of network components onto genes, so it can be found out find very quickly which combination of values are the less expensive (in terms of wasted signal strength) on the network.
This is a really nice project as you can imagine from the screenshots:
To obtain more information please visit the HiperionCAD website or contact
Ugo Sangiorgi - Chief on development
Diego
Guimarães - Developer
Paulo Augusto Bichara - Developer
and GA Specialist
DOAP contains all general meta information about JGAP, including links to resources.
No need to download something in case you want to get a quick overview from anywhere in the online-world. Just browse the trunk of JGAP files at Koders.
Copyright © 2005-2008 Klaus Meffert, GNU free documentation license