Eugene: a generic interactive genetic algorithm controller

James-Reynolds, Carl and Currie, Edward (2015) Eugene: a generic interactive genetic algorithm controller. In: AI-2015: Thirty-fifth SGAI International Conference on Artificial Intelligence, 15-17 Dec 2015, Cambridge, UK.

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (339kB) | Preview

Abstract

This paper outlines the development of an open source generic hardware-based interactive Genetic Algorithm controller (Eugene) and explores contexts in which it may be deployed. The system was first applied to the generation of synthetic sound using MIDI and a simple analogue synthesiser with 27 continuous controller values. It was then applied in the area of image evaluation using an image enhancer program with 7 continuous controller values. The system was evaluated by experimental observation of users attempting various tasks with different success criteria. This led to the identification of issues, some of which were specific to, and others divorced from the application domain. These are discussed together with areas for improvement.

Item Type: Conference or Workshop Item (Poster)
Research Areas: A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 17579
Notes on copyright: This is a post-peer-review, pre-copyedit version of an conference paper published in Research and Development in Intelligent Systems XXXII: Incorporating Applications and Innovations in Intelligent Systems XXIII, Part X. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-25032-8_27
Useful Links:
Depositing User: Carl James-Reynolds
Date Deposited: 21 Sep 2015 09:41
Last Modified: 01 Jun 2019 17:21
ISBN: 9783319250304
URI: https://eprints.mdx.ac.uk/id/eprint/17579

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year