Conference proceeding
Hierarchical Classification with Dynamic-Threshold SVM Ensemble for Gene Function Prediction
Advanced Data Mining and Applications (ADMA 2010), PT II, v 6441(2), pp 336-347
01 Jan 2010
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
The paper proposes a novel hierarchical classification approach with dynamic-threshold SVM ensemble. At training phrase, hierarchical structure is explored to select suit positive and negative examples as training set in order to obtain better SVM classifiers. When predicting an unseen example, it is classified for all the label classes in a top-down way in hierarchical structure. Particulary, two strategies are proposed to determine dynamic prediction threshold for different label class, with hierarchical structure being utilized again. In four genomic data sets, experiments show that the selection policies of training set outperform existing two ones and two strategies of dynamic prediction threshold achieve better performance than the fixed thresholds.
Metrics
Details
- Title
- Hierarchical Classification with Dynamic-Threshold SVM Ensemble for Gene Function Prediction
- Creators
- Yiming Chen - Hunan Agricultural UniversityZhoujun Li - National University of Defense TechnologyXiaohua Hu - Drexel UniversityJunwan Liu - National University of Defense Technology
- Contributors
- Longbing Cao (Editor) - University of Technology SydneyYong Feng (Editor) - Chongqing UniversityJiang Zhong (Editor) - Chongqing University
- Publication Details
- Advanced Data Mining and Applications (ADMA 2010), PT II, v 6441(2), pp 336-347
- Conference
- 6th International Conference on Advanced Data Mining and Applications, ADMA 2010, 6th (Chongqing, China, 19 Nov 2010–21 Nov 2010)
- Series
- Lecture Notes in Artificial Intelligence; 6441
- Publisher
- Springer Nature
- Number of pages
- 12
- Grant note
- 60573057 / NSF( national science foundation) in China
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:000319827000032
- Scopus ID
- 2-s2.0-78650199784
- Other Identifier
- 991019170147304721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence