ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 A New Support Vector Compression Method Based on Singular Value Decomposition
Cited 3 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
윤상훈, 여준기, 천익재, 석정희, 노태문
발행일
201108
출처
ETRI Journal, v.33 no.4, pp.652-655
ISSN
1225-6463
출판사
한국전자통신연구원 (ETRI)
DOI
https://dx.doi.org/10.4218/etrij.11.0210.0349
협약과제
10MB2900, SoC플랫폼용 고속 영상인식 핵심엔진(본과제:다중카메라 기반 고속 영상인식 SoC플랫폼), 노태문
초록
In this letter, we propose a new compression method for a high dimensional support vector machine (SVM). We used singular value decomposition (SVD) to compress the norm part of a radial basis function SVM. By deleting the least significant vectors that are extracted from the decomposition, we can compress each vector with minimized energy loss. We select the compressed vector dimension according to the predefined threshold which can limit the energy loss to design criteria. We verified the proposed vector compressed SVM (VCSVM) for conventional datasets. Experimental results show that VCSVM can reduce computational complexity and memory by more than 40% without reduction in accuracy when classifying a 20,958 dimension dataset. © 2011 ETRI.
키워드
RBF SVM, SVD, Vector compression
KSP 제안 키워드
Compression method, Computational complexity, Design Criteria, High-dimensional, Radial Basis function, Support VectorMachine(SVM), Vector compression, energy loss, singular value decomposition(SVD)