English  |  正體中文  |  简体中文  |  Items with full text/Total items : 65317/65317 (100%)
Visitors : 21286754      Online Users : 231
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/987654321/1065


    Title: 資料挖掘技術應用於外來入侵植物研究;(以恆春地區銀合歡為例)
    Authors: 陳俊賓;jiun-bin chen
    Contributors: 土木工程研究所
    Keywords: 決策樹;CART;資料挖掘;銀合歡;decision tree;CART;data mining;Leucaena leucocephala
    Date: 2005-06-13
    Issue Date: 2009-09-18 17:19:20 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 台灣屬於海島型國家,海洋是天然屏障,種子除了經由海漂及藉由鳥類及人類攜帶之外,外來植物不容易入侵。台灣在經濟活動因素下,於1976年引進原產於中南美洲的銀合歡,後來因經濟效益不佳,加上墾丁國家公園於1984年1月成立後成立後,相關法令規定下,不得任意砍伐植物。造成南台灣的恆春地區銀合歡大量的繁殖,嚴重影響到當地的生態。故需要對銀合歡進行監測,避免生態再度遭受破壞。 本研究採用資料挖掘技術中CART決策樹演算法,利用其由上而下,一層層的往下將資料分類的特性,在土地利用圖、道路環域圖、DTM、坡度圖、土壤pH值分佈圖、坡向圖、土地利用類別環域圖、衛星影像與NDVI等空間資料中,挖掘出隱藏在空間資料與光譜資料中銀合歡分佈規則,進而可以預測恆春地區銀合歡分佈的區域。 本研究利用三種不同的實驗測試,分別為不同銀合歡密度等級與不同訓練區數量、並測試雜訊之影響及加入SPOT多光譜影像,探討不同因素對於預測結果的影響。實驗測試結果精確度都有80%左右,顯示資料挖掘技術結合空間資料,可以有效與快速的找出恆春地區銀合歡的分佈範圍。 The Ocean is natural barrier in Taiwan Island, so external plants invade uneasily except drift, bird and carriage by human. Because of economical activities, Taiwan import in 1976 Leucaena leucocephala yielded in South American Afterwards, low economical benefits as well as related lows which forbid cutting down plants randomly after establishing Kenting National park make Leucaena leucocephala in Heng-Chung area of southern Taiwan proliferate and then affect seriously the local ecology so that Leucaena leucocephala need monitor in order not to be damaged again. In the research, the concept of Data Mining can explore information and knowledge in data which includes ground truth in 1996, buffer map of land use, buffer map of road, aspect, buffer map of land use, satellite image and NDVI. With CART, the research attempt to explore the distributions of Leucaena leucocephala and the rules of data, so as to forecast the range of distribution of Leucaena leucocephala of Heng-Chung area. Three experimental tests include different Leucaena leucocephala dense level and amount of training set, noise reductions and SPOT images in order to explore the effects of prediction. The accuracy of experimental tests is about 80 percent. Therefore, CART can detect effectively the range of Leucaena leucocephala.
    Appears in Collections:[土木工程研究所] 博碩士論文

    Files in This Item:

    File SizeFormat
    0KbUnknown621View/Open


    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