TY - GEN
T1 - An improved support vector machine with soft decision-making boundary
AU - Li, Boyang
AU - Hu, Jinglu
AU - Hirasawa, Kotaro
PY - 2008/12/1
Y1 - 2008/12/1
N2 - This paper proposes an improved support vector machine (SVM) classifier by introducing a soft decision-making boundary for solving real-world classification problem. The soft decision-making boundary contains two parameters describing the offset and the shape, which are estimated automatically from the distribution of training samples around the boundary via a distribution of belief degree in the decision value domain. The SVMwith soft decisionmaking boundary increases classification accuracy by reducing the effects of data unbalance and noises in the realworld data. Simulation results show the effectiveness of the proposed approach.
AB - This paper proposes an improved support vector machine (SVM) classifier by introducing a soft decision-making boundary for solving real-world classification problem. The soft decision-making boundary contains two parameters describing the offset and the shape, which are estimated automatically from the distribution of training samples around the boundary via a distribution of belief degree in the decision value domain. The SVMwith soft decisionmaking boundary increases classification accuracy by reducing the effects of data unbalance and noises in the realworld data. Simulation results show the effectiveness of the proposed approach.
KW - Real-world data classification
KW - SVM
KW - Soft decision-making boundary
KW - Unbalanced data
UR - http://www.scopus.com/inward/record.url?scp=62849112519&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=62849112519&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:62849112519
SN - 9780889867093
T3 - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2008
SP - 40
EP - 45
BT - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, AIA 2008
T2 - IASTED International Conference on Artificial Intelligence and Applications, AIA 2008
Y2 - 13 February 2008 through 15 February 2008
ER -