多项式核函数

多项式核函数SVM快速分类算法

Fast Classification Algorithm for Polynomial Kernel Support Vector Machines

最后，将组合核函数与多项式核函数、RBF核函数进行了对比。

Finally , we compared the combined kernel with Polynomial kernel and RBF kernel .

本研究小组早期提出了对支持向量机（SVM）的多项式核函数及支持向量回归机（SVR）的Bn-splines核函数的几何修正方法。

Our research group have proposed an information-geometrical method to modify the polynomial kernel function and the Bn - splines kernel function .

首先，利用启发式搜索算法，得到优化的基于RBF核函数和多项式核函数支持向量机子模型。

Firstly , a heuristic searching algorithm is presented , which is valuable for getting the support vector machines submodels based on RBF and polynomial kernel functions .

该方法主要分为两个阶段，第一阶段应用统计学方法建模，第二阶段为带有多项式核函数的支持向量机（SVM）。

The method consists of two stages : models based on statistical method were built in the first stage and a support vector machine ( SVM ) with polynomial kernel is used in the second stage .

并给出了基于二次网格搜索方法的核参数选取方法，找出了多项式核函数，RBF核函数以及Sigmoid核函数的最佳参数，从中确定了SVM的最优核函数及其参数。

Then we propose the method of second gridding searching to get best kernel parameters . Using this method , we get best parameters of poly kernel function , RBF kernel function and Sigmoid kernel function .

本文的主要贡献：1.针对非线性多输入多输出（MIMO）系统，提出基于二次多项式核函数SVM的提前一步非线性模型预测控制（NMPC）的结构和算法。

For nonlinear multi-input / multi-output ( MIMO ) systems , the structure and algorithm of SVM with quadratic polynomial kernel function based one-step-ahead nonlinear model predictive control ( NMPC ) is proposed .

通过仿真实验证明了采用混合核函数在低信噪比的情况下进行边缘检测的性能要优于单独使用多项式核函数和高斯核函数的LS-SVM算法。

The result of experiment shows that the LS-SVM performance by using mixtures of kernels is much better than that using polynomial and Gaussian kernel function when the SNR is lower .

选择了高斯核函数和多项式核函数，应用交叉验证的方法对SVM进行训练识别，得到了最优的参数模型，取得了有一定意义的实验结果，为进一步的研究奠定了较好的基础。

Training and identifying SVM by selecting Gaussian kernel function and polynomial kernel function and using cross-validation method , the optimal parameter model is obtained and the significant experimental results are achieved , which lay a good foundation for further studies .

针对多项式核函数的WVD分布图较为复杂，提出了基于Viterbi算法的时频分布图最优路径搜索算法。

For the polynomial kernel function of the signal frequency distribution map is more complicated , a frequency map optimal path search algorithm based on the Viterbi algorithm is proposed .

实验中比较了采用不同核函数构造的SVM的分类效果，结果表明SVM具有较高的识别率，其中三项多项式核函数构造的SVM的识别率最高，可达到93.2%。

In experiments , the classification effects were based on SVM with different kernel functions were compared . The results showed the high efficiency of recognition and classification by SVM . Especially , SVM with three-polynomial kernel function has the highest classification effect by 93.2 % .

针对非线性MIMO系统，提出基于二次多项式核函数并行SVMs的提前多步NMPC的结构和算法，给出关于提前多步的各个最优控制分量与已知输入、输出量间的解析方程组。

For nonlinear MIMO systems , the structure and algorithm of parallel SVMs with quadratic polynomial kernel function based multi-step-ahead NMPC is proposed and the analytical equations with respect to the optimal multi-step-ahead input components and known inputs / outputs are derived .

传统高斯核函数属于局部性核函数，学习能力强但泛化推广能力弱；属于全局性核函数的多项式核函数，学习能力弱但泛化推广能力强。

The traditional Gaussian kernel function is localized kernel function , learning ability is strong but generalization ability is weak .

文章将一种新的核函数用于虹膜识别，并与传统的多项式核函数、高斯核函数进行了比较。

This paper applies a new kind of kernel function to iris identification , and compares with traditional polynomial kernel function and Gauss kernel function .

利用多项式核函数和高斯径向基核函数将原始的人脸图像空间隐式地映射到高维非线性空间；提出了基于核纯类间列空间算法和基于公共列空间的人脸识别算法。

Polynomial kernel function and Gaussian RBF kernel with different parameters are used to map the original face image space to high dimensional feature space .

研究出一种正交多项式核函数，具有有限支撑而在全实轴连续。

This paper proposes a kind of kernel function constructed by orthogonal polynomials . It is continuous on the total real axis and its support set is finite .

由于再生核核函数兼具多项式核函数和高斯核函数的优点，所以它不仅具有良好的全局性质，而且还具有很强的内推能力。

The kernel functions with the advantages of both polynomial kernel and Gauss kernel , not only have a good global property , but also have a strong ability to interpolate .

通过特征样本选择能够降低核费舍尔判别分析的计算复杂度，引入余弦核函数可以改进原始多项式核函数的性能，引入最近邻特征线分类器能够提高模型的分类准确率。

Feature Sample Selection works well in reducing computation of FDA . Cosine Kernel Function is applied to enhance the performance of original Polynomial Kernel Function and Nearest Feature Line Classifier is used to improve the classifying accuracy of model . 4 .

Legendre矩是以Legendre多项式为核函数的矩，在单位圆内Legendre多项式构成了一个完备正交集。

Moments with the Legendre polynomials as kernel function are called Legendre mo-ments , which forma complete orthogonal set inside the unit circle .

在第二章中，我们采用截断多项式函数为核函数，解析的给出点、直线段、圆弧、二次曲线和三角面片等骨架的势函数。

In chapter two , using piecewise quartic polynomial as kernel function , we give analytical convolution solutions for points , line segments , arcs , quadratic Bezier curves and triangle segments .