OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

We propose a genetic algorithm (GA), OPTISIA, for efficiently finding optimal parameter combinations when running OMNISIA, a program that implements a family of analysis and compression algorithms based on the SIA point-set pattern discovery algorithm. The GA, when given a point-set representation of a piece of music as input, runs OMNISIA multiple times, attempting to evolve a combination of parameter values that achieves the highest compression factor on the input piece. When evaluated on two musicological tasks, the system consistently selected well-performing parameters for Forth’s algorithm compared to combinations found in published evaluations on the same musicological tasks.
Original languageEnglish
Title of host publication12th International Workshop on Machine Learning and Music
Number of pages6
PublisherSpringer
Publication statusAccepted/In press - 2019
EventInternational Workshop on Machine Learning and Music - Würzburg, Germany
Duration: 16 Sep 201916 Sep 2019
Conference number: 12
https://musml2019.weebly.com/

Conference

ConferenceInternational Workshop on Machine Learning and Music
Number12
CountryGermany
CityWürzburg
Period16/09/201916/09/2019
Internet address

Fingerprint

Set theory
Genetic algorithms

Cite this

Schmuck, V., & Meredith, D. (Accepted/In press). OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms. In 12th International Workshop on Machine Learning and Music Springer.
@inproceedings{417409630a3b471d901795efe3b62e87,
title = "OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms",
abstract = "We propose a genetic algorithm (GA), OPTISIA, for efficiently finding optimal parameter combinations when running OMNISIA, a program that implements a family of analysis and compression algorithms based on the SIA point-set pattern discovery algorithm. The GA, when given a point-set representation of a piece of music as input, runs OMNISIA multiple times, attempting to evolve a combination of parameter values that achieves the highest compression factor on the input piece. When evaluated on two musicological tasks, the system consistently selected well-performing parameters for Forth’s algorithm compared to combinations found in published evaluations on the same musicological tasks.",
author = "Viktor Schmuck and David Meredith",
year = "2019",
language = "English",
booktitle = "12th International Workshop on Machine Learning and Music",
publisher = "Springer",
address = "Germany",

}

Schmuck, V & Meredith, D 2019, OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms. in 12th International Workshop on Machine Learning and Music. Springer, International Workshop on Machine Learning and Music, Würzburg, Germany, 16/09/2019.

OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms. / Schmuck, Viktor; Meredith, David.

12th International Workshop on Machine Learning and Music. Springer, 2019.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - OPTISIA: An Evolutionary Approach to Parameter Optimisation in a Family of Point-Set Pattern-Discovery Algorithms

AU - Schmuck, Viktor

AU - Meredith, David

PY - 2019

Y1 - 2019

N2 - We propose a genetic algorithm (GA), OPTISIA, for efficiently finding optimal parameter combinations when running OMNISIA, a program that implements a family of analysis and compression algorithms based on the SIA point-set pattern discovery algorithm. The GA, when given a point-set representation of a piece of music as input, runs OMNISIA multiple times, attempting to evolve a combination of parameter values that achieves the highest compression factor on the input piece. When evaluated on two musicological tasks, the system consistently selected well-performing parameters for Forth’s algorithm compared to combinations found in published evaluations on the same musicological tasks.

AB - We propose a genetic algorithm (GA), OPTISIA, for efficiently finding optimal parameter combinations when running OMNISIA, a program that implements a family of analysis and compression algorithms based on the SIA point-set pattern discovery algorithm. The GA, when given a point-set representation of a piece of music as input, runs OMNISIA multiple times, attempting to evolve a combination of parameter values that achieves the highest compression factor on the input piece. When evaluated on two musicological tasks, the system consistently selected well-performing parameters for Forth’s algorithm compared to combinations found in published evaluations on the same musicological tasks.

M3 - Article in proceeding

BT - 12th International Workshop on Machine Learning and Music

PB - Springer

ER -