Support vector machine for classification based on fuzzy training data
Expert Systems with Applications: An International Journal
Distribution-free performance bounds with the resubstitution error estimate (Corresp.)
IEEE Transactions on Information Theory
Hi-index | 12.05 |
This paper comments on the recently published work dealing with support vector machine for classification based on fuzzy data [Ji, A.-B., Pang, J.-H., & Qiu, H.-J. (2010). Support vector machine for classification based on fuzzy training data. Expert Systems with Applications 37(4), 3495-3498]. The authors have claimed that their proposed program is a classical convex quadratic program. But, we show that their proposed program is neither convex nor classical quadratic. Then, we propose a convex program by using the similar strategy proposed by Ji et al. (2010).