Hierarchical multi-label classification incorporating prior information for gene function prediction

Benhui Chen, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an improved Hierarchical Multi-label Classification (HMC) method for solving the gene function prediction. The HMC task is transferred into a series of binary SVM classification tasks. By introducing the hierarchy constraint into learning procedures, two measures with incorporating prior information are implemented to improve the HMC performance. Firstly, for imbalanced functional classes, a hierarchical SMOTE is proposed as over-sampling preprocessing to improve the SVM learning performance. Secondly, an improved True Path Rule consistency approach is introduced to ensemble the results of binary probabilistic SVM classifications. It can improve the classification results and guarantee the hierarchy constraint of classes.

Original languageEnglish
Title of host publicationProceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
Pages231-236
Number of pages6
DOIs
Publication statusPublished - 2010
Event2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10 - Cairo
Duration: 2010 Nov 292010 Dec 1

Other

Other2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10
CityCairo
Period10/11/2910/12/1

Fingerprint

Labels
Genes
Sampling

Keywords

  • Consistency ensemble
  • Gene function prediction
  • Hierarchical multi-label classification
  • Hierarchical SMOTE

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Hardware and Architecture

Cite this

Chen, B., & Furuzuki, T. (2010). Hierarchical multi-label classification incorporating prior information for gene function prediction. In Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10 (pp. 231-236). [5687261] https://doi.org/10.1109/ISDA.2010.5687261

Hierarchical multi-label classification incorporating prior information for gene function prediction. / Chen, Benhui; Furuzuki, Takayuki.

Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. p. 231-236 5687261.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, B & Furuzuki, T 2010, Hierarchical multi-label classification incorporating prior information for gene function prediction. in Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10., 5687261, pp. 231-236, 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10, Cairo, 10/11/29. https://doi.org/10.1109/ISDA.2010.5687261
Chen B, Furuzuki T. Hierarchical multi-label classification incorporating prior information for gene function prediction. In Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. p. 231-236. 5687261 https://doi.org/10.1109/ISDA.2010.5687261
Chen, Benhui ; Furuzuki, Takayuki. / Hierarchical multi-label classification incorporating prior information for gene function prediction. Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10. 2010. pp. 231-236
@inproceedings{9ceff9cd75b64fd7a0ab2bab37c77035,
title = "Hierarchical multi-label classification incorporating prior information for gene function prediction",
abstract = "This paper proposes an improved Hierarchical Multi-label Classification (HMC) method for solving the gene function prediction. The HMC task is transferred into a series of binary SVM classification tasks. By introducing the hierarchy constraint into learning procedures, two measures with incorporating prior information are implemented to improve the HMC performance. Firstly, for imbalanced functional classes, a hierarchical SMOTE is proposed as over-sampling preprocessing to improve the SVM learning performance. Secondly, an improved True Path Rule consistency approach is introduced to ensemble the results of binary probabilistic SVM classifications. It can improve the classification results and guarantee the hierarchy constraint of classes.",
keywords = "Consistency ensemble, Gene function prediction, Hierarchical multi-label classification, Hierarchical SMOTE",
author = "Benhui Chen and Takayuki Furuzuki",
year = "2010",
doi = "10.1109/ISDA.2010.5687261",
language = "English",
isbn = "9781424481354",
pages = "231--236",
booktitle = "Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10",

}

TY - GEN

T1 - Hierarchical multi-label classification incorporating prior information for gene function prediction

AU - Chen, Benhui

AU - Furuzuki, Takayuki

PY - 2010

Y1 - 2010

N2 - This paper proposes an improved Hierarchical Multi-label Classification (HMC) method for solving the gene function prediction. The HMC task is transferred into a series of binary SVM classification tasks. By introducing the hierarchy constraint into learning procedures, two measures with incorporating prior information are implemented to improve the HMC performance. Firstly, for imbalanced functional classes, a hierarchical SMOTE is proposed as over-sampling preprocessing to improve the SVM learning performance. Secondly, an improved True Path Rule consistency approach is introduced to ensemble the results of binary probabilistic SVM classifications. It can improve the classification results and guarantee the hierarchy constraint of classes.

AB - This paper proposes an improved Hierarchical Multi-label Classification (HMC) method for solving the gene function prediction. The HMC task is transferred into a series of binary SVM classification tasks. By introducing the hierarchy constraint into learning procedures, two measures with incorporating prior information are implemented to improve the HMC performance. Firstly, for imbalanced functional classes, a hierarchical SMOTE is proposed as over-sampling preprocessing to improve the SVM learning performance. Secondly, an improved True Path Rule consistency approach is introduced to ensemble the results of binary probabilistic SVM classifications. It can improve the classification results and guarantee the hierarchy constraint of classes.

KW - Consistency ensemble

KW - Gene function prediction

KW - Hierarchical multi-label classification

KW - Hierarchical SMOTE

UR - http://www.scopus.com/inward/record.url?scp=79851469358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851469358&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2010.5687261

DO - 10.1109/ISDA.2010.5687261

M3 - Conference contribution

SN - 9781424481354

SP - 231

EP - 236

BT - Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA'10

ER -