System and Method for generating micro-array data class model using radial basis functions

摘要

PURPOSE: A system and a method for generating a micro array data classification model using a radial basis function are provided to systematically set various variable values needed for generating the classification model by using the radial basis function. CONSTITUTION: A data generator(10) generates the normalized data representing a gene revelation pattern and a functional classification group of each sample on a micro array. An input variable setting tool(20) sets an input value for the learning data reflection and the data representation accuracy. A learning control variable/basis function width setting tool(30) automatically sets a learning control variable and a width of the basis function for deciding the classification model from the inputted learning data reflection and the data representation accuracy. A candidate classification model generator(40) generates a candidate classification model by automatically deciding a number of functions, a central position, and a weight. A classification model decider(60) decides the classification model having the minimum verification error ratio as the final classification model.