QENNI:一种缺失值填充的新方法

QENNI:A New Imputation Method for Missing Data

针对k最近邻填充算法(kNNI)在缺失数据的k个最近邻的选择上可能存在偏好,提出一种新的缺失填充算法:象限近邻填充算法QENNI(quadrant-encapsidated-nearest-neighbor-based imputation),它仅仅使用缺失数据象限方向的最近邻数据填充该缺失值,避免了kNNI中选取的k个最近邻点有偏好这一情况。另外,此算法对于低维数据集可以是无参的,即消除了对参数的依赖。实验结果表明,QENNI算法的填充准确性要优于kNNI算法。

As the k-nearest neighbor imputation （kNNI） algorithm is often biased in choosing the k nearest neighbors of missing data,a new imputation method is put forward ,Quadrant-Encapsidated-Nearest- Neighbor based Imputation method （QENNI） ,for missing values. The algorithm uses the quadrant nearst neighbors （points of the encapsulant） around a missing datum to impute the missing datum. It is not biased in selecting nearest neighbors. Experiments demonstrate that QENNI is much better than the kNNI method in imputed accuracy.