公开(公告)号：KR1020040049721A

公开(公告)日：2004-06-12

申请号：KR1020020077571

申请日：2002-12-07

Applicant: 한국전자통신연구원

Inventor： 신미영 ,  박선희 ,  박상규 ,  임기욱 ,  고엘암릿엘 ,  임호정

IPC: G06N3/12

CPC classification number: G06N99/005

Abstract: 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.

Abstract translation: 目的：提供一种使用径向基函数生成微阵列数据分类模型的系统和方法，以系统地设置通过使用径向基函数生成分类模型所需的各种变量值。 构成：数据发生器（10）生成表示微阵列上每个样本的基因启示模式和功能分类组的标准化数据。 输入变量设定工具（20）设定学习数据反映的输入值和数据表示精度。 学习控制变量/基础功能宽度设定工具（30）根据输入的学习数据反射和数据表示精度，自动设定用于决定分类模型的基础功能的学习控制变量和宽度。 候选分类模型生成器（40）通过自动确定多个功能，中心位置和权重来生成候选分类模型。 分类模型决策者（60）将具有最小验证误差率的分类模型确定为最终分类模型。

公开(公告)号：KR100445427B1

公开(公告)日：2004-08-25

申请号：KR1020020077571

申请日：2002-12-07

Applicant: 한국전자통신연구원

Inventor： 신미영 ,  박선희 ,  박상규 ,  임기욱 ,  고엘암릿엘 ,  임호정

IPC: G06N3/12

CPC classification number: G06N99/005

Abstract: The present invention relates to a radial basis function classifier generating system and method to classify gene expression pattern appearing on micro-array for functional property. In the present invention, the 'representation coverage' to be represented by classifier and the 'representation precision', instead of various variables, are set to be input variables and other variables required to generate classifier are automatically determined based on the given values of the input variables. Developer's selection of the values of variables is minimized and the unnecessary trial-and-errors are reduced. Developers understand easily meaning of such input variables and can predict the result of the selection of variables. Accordingly, the trial-and-errors due to meaningless selection of the values of the variables are reduced, so the classifier generation process can be optimized.

Abstract translation: 本发明涉及一种径向基函数分类器生成系统和方法，用于对出现在微阵列上的基因表达模式进行分类以获得功能特性。 在本发明中，代替各种变量，将要由分类器表示的'表示覆盖率'和'表示精度'被设置为输入变量，并且基于给定值的值来自动确定生成分类器所需的其他变量 输入变量。 开发人员对变量值的选择被最小化，并减少了不必要的试错。 开发人员很容易理解这些输入变量的含义，并可以预测变量选择的结果。 因此，由于无意义地选择变量的值而导致的试错被减少，所以分类器生成过程可以被优化。