加权支持向量回归算法在船舶智能建模中的应用

A new weighted support vector regression and its application in ship′s intelligent modeling

在分析现有基于高斯核的支持向量回归方法优缺点的基础上,将高斯核参数加权与支持向量回归算法相结合,实现了一种"基于高斯核参数加权的支持向量回归算法".在该新算法中引入一种带权重因子的核函数,其中权重因子由输入向量来确定,同时将该算法应用在散货船舶主尺度要素智能化建模中并与常规算法进行了比较.试验结果表明了这种改进的支持向量回归算法在船舶主尺度要素智能化建模中的有效性和实用性.

With the analysis of both advantages and disadvantages of current support vector regression,a new weighted support vector regression algorithm is proposed by combining the weighted Gaussian kernel function with support vector regression.In the algorithm,a new kernel function is brought forward with weight vectors that are decided by the input vectors.At the same time,the new algorithm is adopted to model the principal particulars of bulk carriers and compared with ordinary methods.The results show the practicability and effectiveness of the algorithm in the field of ship′s principal particulars intelligent modeling.