基于Multi-kernel和KRR的数据还原算法  

Data reconstruction algorithm based on Multi-kernel and KRR

作　　者：刘剑[1,2] 龚志恒[1] 吴成东[2] 

机构地区：[1]沈阳建筑大学信息与控制工程学院,沈阳110168 [2]东北大学信息科学与工程学院,沈阳110004

出　　处：《控制与决策》2014年第5期821-826,共6页Control and Decision

基　　金：国家自然科学基金项目(61272253);国家住建部科技计划项目(2010-K9-22)

摘　　要：由于数据被核化后不能还原,使核方法的应用受到局限.对此,提出一种基于Multi-kernel和KRR的数据还原算法.首先,通过同类数据中已知数据进行多次核化迭代,使已知数据在超高维欧氏空间中呈线性;然后,利用已知数据对同类未知数据进行线性表示,并以Kernel ridge regression(KRR)算法进行未知数据的回归;最后实现数据还原.选取Iris flower和JAFFE两类数据集进行还原实验,实验结果表明,所提出的算法可以有效地还原未知数据,而且在其他领域的应用也有较好的效果.The kernel methods are limited because the data of transformation can not be restored. For its characteristics of problem, a method based on Multi-kernel and Kernel ridge regression（KRR） is proposed. Firstly, the given data of homogeneous data is iterated by the kernel, and given data will express linearly in the ultra high-dimensional Euclidean space. Then, the unknown data can be linearly denoted by the given data. Thereafter, the unknown data can be regressed according to the KRR algorithm. Finally, the data reduction can be achieved. The two classes of data sets are selected as the experimental data. The results show that the proposed method has a great effect to restore unknown data, and it can be applied to other fields.

关 键 词：多核 数据还原 核岭回归 迭代 超高维欧氏空间 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]