The data replication method for the classification with reject option

• Type: Article in International Scientific Journal
• Date: 2013

Authors

Ricardo Sousa (Author) Other; Jaime S Cardoso (Author) FEUP

Journal

Title: AI Communications

Vol. 26

Pages: 281-302

ISSN: 0921-7126

Publisher: IOS PRESS

Indexing

ISI Web of Knowledge - 5 Citations

ISI Web of Science

Scopus - 7 Citations

Scientific classification

FOS: Natural sciences > Computer and information sciences

CORDIS: Technological sciences > Engineering > Knowledge engineering

Other information

Authenticus ID: P-005-727

DOI: 10.3233/aic-130566

Abstract (EN): Classification is one of the most important tasks of machine learning. Although the most well studied model is the two-class problem, in many scenarios there is the opportunity to label critical items for manual revision, instead of trying to automatically classify every item. In this paper we tailor a paradigm initially proposed for the classification of ordinal data to address the classification problem with reject option. The technique reduces the problem of classifying with reject option to the standard two-class problem. The introduced method is then mapped into support vector machines and neural networks. Finally, the framework is extended to multiclass ordinal data with reject option. An experimental study with synthetic and real datasets verifies the usefulness of the proposed approach.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 22