基本思想是通过非线性变换，使样本变换之后的特征空间中变得线性可分。
Basic idea is to adoption of non-linear transform, so that after changing the characteristics of the sample space become linearly separable.
使用仿射变换内点回代技术的信赖域子空间算法解线性不等式约束的非线性优化问题。
We present an affine scaling trust region algorithm with interior back - tracking and subspace techniques for nonlinear optimizations subject to linear inequality constraints.
算法采用核函数变换的方式，将重叠严重和非线性的光谱数据进行高维空间变换后再计算各组分气体浓度。
The transformation of kernel function is used to solve the overlapped mixed gas feature absorption spectrum in high dimension space.
应用推荐