RTU Research Information System
Latviešu English

Publikācija: Antigen Reduction Applied to Support Vector Machine Classification for Melanoma-Related Diagnostics

Publication Type Scientific article indexed in ERIH database, in INT1 or INT2 category journals
Funding for basic activity Unknown
Defending: ,
Publication language English (en)
Title in original language Antigen Reduction Applied to Support Vector Machine Classification for Melanoma-Related Diagnostics
Field of research 1. Natural sciences
Sub-field of research 1.2 Computer and information sciences
Authors Vilens Jumutcs
Pawel Zayakin
Aija Linē
Keywords SVM, feature selection, clustering, K-Means, SD
Abstract This paper discusses the application of Support Vector Machines (SVM) to classification of autoantibody profiles with a large number of antigens (attributes) and effectiveness gain produced by the proposed antigen reduction methods. As a result of research effort, a new biologically robust and meaningful method on selecting antigens with high expression level in cancer patients is introduced. The proposed antigen reduction method improves initial full-range SVM model and clearly proves the necessity for more careful attribute selection in classification tasks performed by SVM. The proposed method can also be used for novel biomarker discovery and can give a necessary insight into uncovered connections between already known and newly discovered CT (cancer testis) biomarkers.
Hyperlink: http://www.pjoes.com 
Reference Jumutcs, V., Zayakin, P., Linē, A. Antigen Reduction Applied to Support Vector Machine Classification for Melanoma-Related Diagnostics. Polish Journal of Environmental Studies, 2009, Vol.18, No.4a, pp.3-8. ISSN 1230-1485.
ID 9606