R package emoa
emoa package has been released on CRAN as a public preview. The
included functionality is sufficient to implement state of the art
EMOA. As an example, an SMS-EMOA implementation is included in the git
repository. The development is currently focused on defining an
abstract function signature and emoa result object that is flexible
enough to accommodate future developments.
If you are interested in bleeding-edge development versions read the following sections on how to obtain the source code of the package.
This package would not have been possible without the contribution of the following people (in alphabetical order). Most of them have graceously placed their source code under a liberal license so that I could include it in the package instead of reimplementing their work.
- Michael H. Buselli
- Wessel Dankers
- Carlos Fonseca
- Joshua Knowles
- Huang Ling
- Wudong Liu
- Manuel Lopez-Ibanez
- Luis Paquete
- Ponnuthurai Nagaratnam Suganthany
- Santosh Tiwar
- Qingfu Zhang
- Aimin Zhou
- Shizheng Zhaoy
In particular this package uses version 1.3 of the hypervolume code available from here. For a description of the algorithm see
Carlos M. Fonseca, Luís Paquete, and Manuel López-Ibáñez. An improved dimension-sweep algorithm for the hypervolume indicator. In IEEE Congress on Evolutionary Computation, pages 1157-1163, Vancouver, Canada, July 2006.
Beta package version
To install a beta version of
emoa run the
following in the
Contributing to emoa
If you want to contribute to the package, please clone my git repository using
git clone git://git.datensplitter.net/emoa
and send me a patch using
git format-am origin
You can find detailed instructions on using git as a contributor here. If you do not want to use git, which I can wholeheartedly recommend, feel free to send me plain patches or a tarball / zip archive with your modified source code.