Title :
Fusion of one-class classifiers in the belief function framework
Author :
Aregui, Astride ; Denoeux, Thierry
Author_Institution :
Univ. de Technol. de Compiegne, Compiegne
Abstract :
A method is proposed for converting a novelty measure such as produced by one-class SVMs or Kernel principal component analysis (KPCA) into a belief function on a well- defined frame of discernment. This makes it possible to combine one-class classification or novelty detection methods with other information expressed in the same framework such as expert opinions or multi-class classifiers.
Keywords :
belief networks; pattern classification; principal component analysis; support vector machines; KPCA; SVM; belief function framework; kernel principal component analysis; novelty detection; one-class classifiers; Kernel; Monitoring; Pattern classification; Principal component analysis; Support vector machine classification; Support vector machines; Demspter-Shafer theory; Novelty detection; Transferable Belief Model; evidence theory; one-class classification;
Conference_Titel :
Information Fusion, 2007 10th International Conference on
Conference_Location :
Quebec, Que.
Print_ISBN :
978-0-662-45804-3
Electronic_ISBN :
978-0-662-45804-3
DOI :
10.1109/ICIF.2007.4408102
