Towards a brain controller interface for generating simple Berlin School style music with interactive genetic algorithms

James-Reynolds, Carl ORCID logoORCID: https://orcid.org/0000-0002-5892-5415 and Currie, Edward ORCID logoORCID: https://orcid.org/0000-0003-1186-5547 (2021) Towards a brain controller interface for generating simple Berlin School style music with interactive genetic algorithms. Bramer, Max and Ellis, Richard, eds. Artificial Intelligence XXXVIII: 41st SGAI International Conference on Artificial Intelligence, AI 2021, Cambridge, UK, December 14–16, 2021, Proceedings. In: AI 2021: 41st SGAI International Conference on Artificial Intelligence, 14-16 Dec 2021, Cambridge, United Kingdom [Online]. pbk-ISBN 9783030910990, e-ISBN 9783030911003. ISSN 0302-9743 [Conference or Workshop Item] (doi:10.1007/978-3-030-91100-3_31)

[img] PDF (Conference Paper) - Final accepted version (with author's formatting)
Restricted to Repository staff and depositor only until 6 December 2022.

Download (190kB)

Abstract

A novel approach to generating music is presented using two interactive Genetic Algorithms with electroencephalogram inputs from two subjects as their fitness functions. Many interactive Genetic Algorithm approaches for generating music employ constrained solution spaces that only utilise notes from a given scale. Our work incorporates the use of mutation to extend the solution space through the inclusion of accidental notes. A thresholding approach is adopted, that allows riffs to be repeated until fitness drops, together with a ‘killswitch’ to ensure unpleasant sounding riffs are removed from the population.

The development is ongoing, with more testing and calibration required to ensure that there are no timing errors in communication between the microcontroller boards and to identify the most appropriate threshold and mutation ranges, in addition to determining the most appropriate mixes for the users to hear.

Item Type: Conference or Workshop Item (Poster)
Additional Information: Lecture Notes in Computer Science (LNCS, volume 13101)
Research Areas: A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 34078
Notes on copyright: This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/978-3-030-91100-3_31. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms
Useful Links:
Depositing User: Carl James-Reynolds
Date Deposited: 05 Nov 2021 16:21
Last Modified: 06 Jun 2022 18:07
URI: https://eprints.mdx.ac.uk/id/eprint/34078

Actions (login required)

View Item View Item

Statistics

Activity Overview
6 month trend
0Downloads
6 month trend
35Hits

Additional statistics are available via IRStats2.