Skip to main content

Meta-Learning for Hierarchical Classification and Applications in Bioinformatics

Fabris, Fabio (2018) Meta-Learning for Hierarchical Classification and Applications in Bioinformatics. International Journal of Computer and Information Engineering, 12 (7). ISSN 2010-3921. (KAR id:69105)

PDF Publisher pdf
Language: English
Download (237kB) Preview
[img]
Preview
PDF Author's Accepted Manuscript
Language: English
Download (251kB) Preview
[img]
Preview

Abstract

Hierarchical classification is a special type of

hierarchy, with more generic class labels being ancestors of more

recommendation consists of recommending to the user a classification

the past performance of the candidate algorithms in other datasets.

classification. By contrast, this paper proposes a meta-learning

evaluates it in a large number of bioinformatics datasets. Hierarchical

protein and gene functions tend to be organised into a hierarchy of

This work proposes meta-learning approach for

hierarchical classification dataset. This work’s contributions are: 1)

new datasets to increase the number of meta-instances, 2) proposing

decision-tree meta-models for hierarchical classification algorithm

recommendation.

Item Type: Article
Uncontrolled keywords: Algorithm recommendation, meta-learning, bioinformatics, hierarchical classification
Subjects: Q Science
Q Science > QA Mathematics (inc Computing science)
Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Faculties > Sciences > School of Computing
Depositing User: Alex Freitas
Date Deposited: 14 Sep 2018 14:38 UTC
Last Modified: 29 May 2019 21:09 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/69105 (The current URI for this page, for reference purposes)
Fabris, Fabio: https://orcid.org/0000-0001-7159-4668
  • Depositors only (login required):

Downloads

Downloads per month over past year