Improving Classification Accuracy on Uncertain Data by Considering Multiple Subclasses

摘要

We study the problem of classification on uncertain objects whose locations are uncertain and described by probability density functions (pdf). Though there exist some classification algorithms proposed to handle uncertain objects, all existing algorithms are complex and time consuming. Thus, a novel supervised UK-means algorithm is proposed to classify uncertain objects more efficiently. Supervised UK-means assumes the classes are well separated. However, in real data, subsets of objects of the same class are usually interspersed among (disconnected by) other classes. Thus, we proposed a new algorithm Supervised UK-means with Multiple Subclasses (SUMS) which considers the objects in the same class can be further divided into several groups (subclasses) within the class and tries to learn the subclass representatives to classify objects more accurately.