Quantity Distribution Search using Sparse Representation Generated with Kernel-based Regression

The number of records representing a quantity distribution (e.g. temperature and rainfall) requires an extreme amount of overhead to manage the data. We propose a method using a subset of records against the problem. The proposed method involves an approximation derived with kernel ridge regression in advance to determine the minimal dataset to be input into database systems. As an advantage of the proposed method, processes to reconstruct the original dataset can be completely implemented with Structured Query Language, which is used for relational database systems. Thus users can analyze easily the quantity distribution. From the results of experiments using digitized elevation map data, we confirmed that the proposed method can reduce the number of data to less than 1/10 of the original number if the acceptable error was set to 125 m.