Data Mining from Hybrid Data with Numerical Attributes and Graph Structures

具有数值属性和图结构的混合数据的数据挖掘

• 批准号: 16500084
• 负责人: MIYAHARA Tetsuhiro
• 金额: $ 2.05万
• 依托单位: Hiroshima City University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2004
• 资助国家: 日本
• 起止时间: 2004 至 2006
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-16500084/
• 关键词: numerical data; graph structured data; data mining; recursive real-valued function

The purpose of this research project is to give theoretical foundations of data mining from hybrid data with numerical attributes and graph structures. Since HTML/XML files are considered to be tree structured data, methods for discovering characteristic patterns from tree structured data are useful. Based on Genetic Programming, we have implemented a discovery system for characteristic tree structured patterns from given positive and negative examples of tree structured data. Our tree structured patterns are tag tree patterns. Although variables in a tag tree pattern are structured variables which can be substituted by arbitrary trees, these variables are considered to be special edges in a tree. Then we have naturally applied Genetic Programming, which is a genetic method for tree structured objects, to implementing our discovery system. Inferring real-valued functions from numerical data obtained from experiments or observations is a basic learning method for data mining from numerical data. A recursive real is a real number which we can deal with on a computer. So we have investigated learnabilities of recursive real-valued functions such as prediction and finite prediction of recursive real-valued functions. Also we have given various learning algorithms for tree or graph structured data, including an algorithm for extracting structural features among words and polynomial time inductive inference algorithms from positive data for newly introduced classes of graph languages.

本课题旨在为具有数值属性和图结构的混合数据的数据挖掘提供理论基础。由于HTML/XML文件被认为是树状结构数据，因此从树状结构数据中发现特征模式的方法非常有用。基于遗传规划，我们实现了一个从给定的树状结构数据正反例中发现特征树状结构模式的系统。我们的树结构模式是标签树模式。虽然标签树模式中的变量是可以被任意树替换的结构化变量，但这些变量被认为是树中的特殊边。然后我们自然地应用了遗传规划，这是一种树状结构对象的遗传方法，来实现我们的发现系统。从实验或观测得到的数值数据中推断实值函数是数值数据挖掘的一种基本学习方法。递归实数是我们可以在计算机上处理的实数。因此，我们研究了递归实值函数的可学习性，如递归实值函数的预测和有限预测。此外，我们还给出了树或图结构数据的各种学习算法，包括从单词中提取结构特征的算法和从新引入的图语言类的正数据中提取多项式时间归纳推理算法。

项目成果

Prediction of recursive real-valued functions from finite examples. Joint JSAI 2005 Workshop-Post-Proceedings, Springer-Verlag

从有限示例预测递归实值函数。

• 发表时间: 2006
• 期刊: Lecture Notes in Artificial Intelligence Vol. 4012
• 作者: E.Hirowatari;K.Hirata;T.Miyahara
• 通讯作者: T.Miyahara

Finite prediction of recursive real-valued functions. Proceedings of Computability in Europe 2006 (CIE-2006), University of Wales Swansea

递归实值函数的有限预测。

• 发表时间: 2006
• 期刊: Computer Science Report Series. CSR 7-2006
• 作者: E.Hirowatari;K.Hirata;T.Miyahara
• 通讯作者: T.Miyahara

Learning of Elementary Formal Systems with Two Clauses using queries

使用查询学习具有两个子句的基本形式系统

• 发表时间: 2005
• 期刊: Proc. ALT 2005, Lecture Notes in Artificial Intelligence(Springer-Verlag) 3374
• 作者: H.Kato;S.Matsumoto;T.Miyahara
• 通讯作者: T.Miyahara

Evolution of Characteristic Tree Structured Patterns from Semistructured Documents

半结构化文档特征树结构模式的演变

• 发表时间: 2006
• 期刊: Proc.AI-2006, Springer, Lecture Notes in Artificial Intelligence 4304
• 作者: K.Inata;T.Miyahara;H.Ueda;and K.Takahashi
• 通讯作者: and K.Takahashi

Polynomial Time Inductive Inference of TTSP Graph Languages from Positive Data

TTSP图语言从正数据的多项式时间归纳推理

• 发表时间: 2005
• 期刊: Proc.ILP-2005, Springer, Lecture Notes in Artificial Intelligence 3625
• 作者: R.Takami;Y.Suzuki;T.Uchida;T.Shoudai;and Y.Nakamura
• 通讯作者: and Y.Nakamura