论文部分内容阅读
为了使数据集的内在分布更好地影响训练模型,提出一种密度加权孪生支持向量回归机算法.该算法通过k近邻算法计算获得每个数据点基于数据密度分布的密度加权值,并将密度加权值引入到标准孪生支持向量回归机算法中.算法能够很好地反映训练数据集的内在分布,使数据点准确影响训练模型.通过6个UCI数据集上的实验结果分析验证了所提出算法的有效性.
In order to make the inner distribution of datasets better affect the training model, a density-weighted twin support vector regression algorithm is proposed, which calculates the density weighted value of each data point based on data density distribution by k-nearest neighbor algorithm, The weighted values are introduced into the standard twin support vector regression algorithm.The algorithm can well reflect the inherent distribution of the training data set and make the data points accurately affect the training model.The experimental results on six UCI data sets validate the proposed algorithm Effectiveness.