English  |  正體中文  |  简体中文  |  Items with full text/Total items : 73032/73032 (100%)
Visitors : 23358159      Online Users : 561
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/64832

    Title: 以知識本體技術與探勘方法探討台北都會區道路工程與管理系統之研究;The Study of Road Engineering and Management System Using Ontology Technology and Data Mining in Taipei Metropolitan Area
    Authors: 洪嘉澤;Hung,Chia-Tse
    Contributors: 土木工程學系
    Keywords: 路平專案;再利用材料;道路管理系統;資料探勘;知識本體;Road-smoothing project;reclaimed asphalt pavement (RAP);Road management system;Data Mining (DM);Ontology
    Date: 2014-07-29
    Issue Date: 2014-10-15 14:29:07 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 近年來路面工程的內涵由於用路人需求標準提高,相關的養護管理作業必須從過去較單純的技術層次提昇至複雜之管理層次;而路面工程則必須藉由系統管理的技術方法將工程中所包含之各項工作如:規劃、設計、施工和養護等全工程生命週期納入一套層次分明的管理系統架構中,迫使工程單位各階層人員,可透過此管理系統來執行路面養護之相關決策,並且尋求路面問題中最佳解決方案。
    為了提升現有管理系統架構與環境,透過資料探勘(Data Mining)中的分類與關聯規則找出資料庫中潛藏的樣式和預測未知的數據資訊,所萃取的資料透過正規概念點陣的方式作呈現,主要目的是用來將資料作正規性的比較後以知識本體技術(Ontology)來建構路面破壞分類知識庫,因為Ontology中具有概念化(Conceptualization)、共享(Shared)、正式的(Formal)及明確的(Explicit)特性,能將管理系統做資訊及語意上的整合,本研究最終設計出一互動式查詢介面,並包含空間屬性供未來養護工程師、專家學者進行操作,另外本研究的雛形系統知識庫藉由案例展示之過程,提出軟硬體上的效益比較分析,使未來台北市道路管理系統資料庫導入成為以知識為導向的知識庫管理系統。
    ;As a result of increased road occupancy demands, the need for improved standards of pavement engineering has become apparent in recent years. However, the upgrading of road maintenance and management methods involves complex management. The use of a management system for the execution of road maintenance and to make strategic decisions is the current trend for maintenance engineers. This study uses information obtained from the system database for the New Construction Offices of the Taipei City Government. Analysis of road sections must be performed in accordance with the road-smoothing project. First, we base our analysis on information from the International Roughness Index (IRI), known the situation in Taipei city, followed by discussion of road deterioration trends and determination of the conservation threshold using regression analysis and the Artificial Neural Network (ANN) method. After addition, the urban traffic flow value are used in a discussion of the density of traffic and its relationship with the IRI index. A strategy for road maintenance is then proposed based on the survey results. For example, recycled materials from Taipei’s roads could be used for future road-smoothing projects as part of engineering lifecycle management.
    Analysis of this engineering management system (EMS) is carried out using data mining methods for classification and association in order to find the hidden samples and unknown information. The extracted information is presented as a formal concept lattice, followed by a formal concept analysis (FCA). Through concept lattices we can know which knowledge is more important and what the road damage ratio for Taipei’s roads is. The goal of this study is to create a knowledge database using Ontology′s Conceptualization, Shared, Formal and Explicit properties to create a Semantic Web to integrate the current engineering systems and upgrade the usability of these system. Finally we design an interactive interface for spatial property investigation and later carry out a case study with the proposed system and knowledge database which should benefit engineers, domain experts and lead to a multiple web-based GI service in the future.
    Appears in Collections:[土木工程研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明