Specializing for predicting obesity and its co-morbidities

Creative Commons License

Goldstein I., Uzuner O.

JOURNAL OF BIOMEDICAL INFORMATICS, vol.42, no.5, pp.873-886, 2009 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 42 Issue: 5
  • Publication Date: 2009
  • Doi Number: 10.1016/j.jbi.2008.11.001
  • Journal Name: JOURNAL OF BIOMEDICAL INFORMATICS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.873-886
  • Keywords: Classification, Combination of classifiers, Natural language processing, Machine learning, CLASSIFIER, ALGORITHM, SYSTEM, COMBINATION
  • Middle East Technical University Affiliated: No

Abstract

We present specializing, a method for combining classifiers for multi-class classification. Specializing trains one specialist classifier per class and utilizes each specialist to distinguish that class from all others in a one-versus-all manner. It then supplements the specialist classifiers with a catch-all classifier that performs multi-class classification across all classes. We refer to the resulting combined classifier as a specializing classifier.