Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation (ISCCCA 2013)

Optimal Boundary SVM Incremental Learning Algorithm

Authors
Jian Cao, Shiyu Sun, Xiusheng Duan
Corresponding Author
Jian Cao
Available Online February 2013.
DOI
https://doi.org/10.2991/isccca.2013.33How to use a DOI?
Keywords
supportt vector mechine, increamental learning, KKT condition
Abstract
Support vectors(SVs) can’t be selected completely in support vector machine(SVM) incremental, resulting incremental learning process can’t be sustained. In order to solve this problem, the article proposes optimal boundary SVM incremental learning algorithm. Based on in-depth analysis of the trend of the classification surface and make use of the KKT conditions, selecting the border of the vectors include the support vectors to participate SVM incremental learning. The experiment shows that the algorithm can be completely covered the support vectors and have the identical result with the classic support vector machine, it also saves lots of time. Therefore it can provide the conditions for future large sample classification and incremental learning sustainability.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation (ISCCCA 2013)
Series
Advances in Intelligent Systems Research
Publication Date
February 2013
ISBN
978-90-78677-63-5
ISSN
1951-6851
DOI
https://doi.org/10.2991/isccca.2013.33How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Jian Cao
AU  - Shiyu Sun
AU  - Xiusheng Duan
PY  - 2013/02
DA  - 2013/02
TI  - Optimal Boundary SVM Incremental Learning Algorithm
BT  - Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation (ISCCCA 2013)
PB  - Atlantis Press
SP  - 132
EP  - 135
SN  - 1951-6851
UR  - https://doi.org/10.2991/isccca.2013.33
DO  - https://doi.org/10.2991/isccca.2013.33
ID  - Cao2013/02
ER  -