| Summary: | 博士 === 國立臺灣科技大學 === 營建工程系 === 103 === After the Jiji eqrthquake at Taiwan. Ministry of Education work together with National Center for Research on Earthquake Engineering(NCREE) on a project to improve aseismic ability of every level of schools. During the project process, lots of survey and evaluation data were collected including the geometry design parameters, strength of materials, age and status of buildings, evaluation results, retrofit plans ..etc. The collected data were stored in a database called school aseismic database. The amount of data are huge. It should contain hidden knowledge which is very hard to get just by human brain. Data Mining is a subfield of computer science. The goal of data mining is to discover patterns in an easy to understand form. The data mining technologies are artificial intelligence, machine learning, statistics and database system. The purpose of this research is using data mining technology to discover hidden knowledge from school aseismic database. Nased on four main data mining category: regression, classification, clustering and association rules. We reasearch on the characteristic of these four main category and find knowledge candidates. After the mining and analysis. Three useful and reliable model were discovered: "Model of School Building Geometry Parameter and Aseismic Ability", "Model of School Building Geometry Parameter and Major Crack Component" and "Model of School Building Geometry Parameter and Retrofit Cost".
|
|---|
