Towards music fitness evaluation with the hierarchical SOM

In any evolutionary search system, the fitness raters are most crucial in determining successful evolution. In this paper, we propose a Hierarchical Self Organizing Map based sequence predictor as a fitness evaluator for a music evolution system. The hierarchical organization of information in the H...

Full description

Bibliographic Details
Main Authors: Edwin Hui Hean, Law, Somnuk, Phon-Amnuaisuk
Format: Article
Published: SPRINGER-VERLAG BERLIN 2008
Subjects:
Online Access:http://shdl.mmu.edu.my/2792/
_version_ 1848790151302479872
author Edwin Hui Hean, Law
Somnuk, Phon-Amnuaisuk
author_facet Edwin Hui Hean, Law
Somnuk, Phon-Amnuaisuk
author_sort Edwin Hui Hean, Law
building MMU Institutional Repository
collection Online Access
description In any evolutionary search system, the fitness raters are most crucial in determining successful evolution. In this paper, we propose a Hierarchical Self Organizing Map based sequence predictor as a fitness evaluator for a music evolution system. The hierarchical organization of information in the HSOM allows prediction to be performed with multiple levels of contextual information. Here, we detail the design and implementation of such a HSOM system. From the experimental setup, we show that the HSOM's prediction performance exceeds that of a Markov prediction system when using randomly generated and musical phrases.
first_indexed 2025-11-14T18:08:03Z
format Article
id mmu-2792
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:08:03Z
publishDate 2008
publisher SPRINGER-VERLAG BERLIN
recordtype eprints
repository_type Digital Repository
spelling mmu-27922011-09-19T08:19:23Z http://shdl.mmu.edu.my/2792/ Towards music fitness evaluation with the hierarchical SOM Edwin Hui Hean, Law Somnuk, Phon-Amnuaisuk T Technology (General) QA75.5-76.95 Electronic computers. Computer science In any evolutionary search system, the fitness raters are most crucial in determining successful evolution. In this paper, we propose a Hierarchical Self Organizing Map based sequence predictor as a fitness evaluator for a music evolution system. The hierarchical organization of information in the HSOM allows prediction to be performed with multiple levels of contextual information. Here, we detail the design and implementation of such a HSOM system. From the experimental setup, we show that the HSOM's prediction performance exceeds that of a Markov prediction system when using randomly generated and musical phrases. SPRINGER-VERLAG BERLIN 2008 Article NonPeerReviewed Edwin Hui Hean, Law and Somnuk, Phon-Amnuaisuk (2008) Towards music fitness evaluation with the hierarchical SOM. SPRINGER-VERLAG BERLIN, 4974. pp. 443-452. http://apps.webofknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=1&SID=Q1Mem7jkjbFNK9JeCJh&page=83&doc=829
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
Edwin Hui Hean, Law
Somnuk, Phon-Amnuaisuk
Towards music fitness evaluation with the hierarchical SOM
title Towards music fitness evaluation with the hierarchical SOM
title_full Towards music fitness evaluation with the hierarchical SOM
title_fullStr Towards music fitness evaluation with the hierarchical SOM
title_full_unstemmed Towards music fitness evaluation with the hierarchical SOM
title_short Towards music fitness evaluation with the hierarchical SOM
title_sort towards music fitness evaluation with the hierarchical som
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2792/
http://shdl.mmu.edu.my/2792/