Abstract
Multi-label classification (MLC) is the technique to solve conditional problem where decisions is a set of labels. Classification is the learning task by using historical examples to make model of conditions to make decision of unseen example. To improve decision in MLC. We can use advantage of domination analysis or dependency relations between the classes by using enhanced Bayesian Chain Classifier (BCC). We introduce an approach for chaining classifier primary order by its individual label accuracy priority (LPC-CC). Our method considers the dependencies among label based on label accuracy priority ordering. Thus, Binary Relevance (BR) theoretical is used for label sequencing priority, and cycle classifiers chain using nave Bayes is for finding domination. The model have been tested on 2 well-known benchmark datasets named Yeast and Emotions and a collection of car sell records from a Thailand Automotive Company.
Original language | English |
---|---|
Title of host publication | Proceedings - 2016 5th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 1048-1053 |
Number of pages | 6 |
ISBN (Electronic) | 9781467389853 |
DOIs | |
Publication status | Published - 2016 Aug 31 |
Event | 5th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2016 - Kumamoto, Japan Duration: 2016 Jul 10 → 2016 Jul 14 |
Other
Other | 5th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2016 |
---|---|
Country | Japan |
City | Kumamoto |
Period | 16/7/10 → 16/7/14 |
Keywords
- Chain Classifier
- Domination Analysis
- Label Dependency
- Label Ordering
- Problem Transformation
ASJC Scopus subject areas
- Information Systems
- Computer Networks and Communications
- Computer Science Applications
- Computer Vision and Pattern Recognition