A New Feature Selection Method to Extract Functional Structures from Multidimensional Symbolic Data

摘要

In this paper, we propose a feature selection method to extract functional structures embedded in multidimensional data. In our approach, we do not approximate functional structures directly. Instead, we focus on the seemingly trivial property that functional struc- tures are geometrically thin in an informative subspace. Using this prop- erty, we can exclude irrelevant features to describe functional stuc- tures. As a result, we can use conventional identification methods, which use only informative features, to accurately identify functional struc- tures. In this paper, we define Geometrical Thickness (GT) in the Car- tesian System Model (CSM), a mathematical model that can manipu- late symbolic data.