Title :
Nearest Mean Classification via One-Class SVM
Author :
Shin, Donghyuk ; Kim, Saejoon
Author_Institution :
Dept. of Comput. Sci. & Eng., Sogang Univ., Seoul, South Korea
Abstract :
We propose a new multi-class classification algorithm based on one-class SVM and nearest mean classifier methods. A wrapper-style feature selection scheme designed specifically for our algorithm is also provided for increased classification accuracy. It will be demonstrated that the proposed classification algorithm provide excellent performance, and in particular, performs strictly better than some of the currently known best classification algorithms on five biological datasets.
Keywords :
feature extraction; pattern classification; support vector machines; biological dataset; multiclass classification algorithm; nearest mean classification method; one-class SVM; wrapper-style feature selection scheme; Algorithm design and analysis; Classification algorithms; Computer science; Image retrieval; Intrusion detection; Kernel; Optimization methods; Support vector machine classification; Support vector machines; Testing; Nearest Mean Classification; One-class SVM;
Conference_Titel :
Computational Sciences and Optimization, 2009. CSO 2009. International Joint Conference on
Print_ISBN :
978-0-7695-3605-7
DOI :
10.1109/CSO.2009.388
