dc.contributor.advisor | 林老生 | zh_TW |
dc.contributor.author (Authors) | 王奕鈞 | zh_TW |
dc.creator (作者) | 王奕鈞 | zh_TW |
dc.date (日期) | 2005 | en_US |
dc.date.accessioned | 18-Sep-2009 16:16:23 (UTC+8) | - |
dc.date.available | 18-Sep-2009 16:16:23 (UTC+8) | - |
dc.date.issued (上傳時間) | 18-Sep-2009 16:16:23 (UTC+8) | - |
dc.identifier (Other Identifiers) | G0093257006 | en_US |
dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/35873 | - |
dc.description (描述) | 碩士 | zh_TW |
dc.description (描述) | 國立政治大學 | zh_TW |
dc.description (描述) | 地政研究所 | zh_TW |
dc.description (描述) | 93257006 | zh_TW |
dc.description (描述) | 94 | zh_TW |
dc.description.abstract (摘要) | 現今台灣地區使用的地籍坐標系統有相當多種,在這當中最廣泛使用的為TWD67與TWD97坐標系統。由於不同時期建置的資料具有不同的地籍坐標系統,因此常需要在兩地籍坐標系統間進行坐標轉換。目前,國內正積極將地籍資料由TWD67坐標系統轉換為TWD97坐標系統。而如何在TWD67與TWD97之間進行坐標轉換,整合不同地籍坐標系統間資料之聯繫與共享,一直是國內學者致力於研究的問題。在廣泛的討論當中,最常使用的方式為利用最小二乘法求解轉換參數。 近幾年來由於神經網路技術快速的發展,提供了我們在進行地籍坐標轉換研究時新的選擇。本研究目的在於嘗試利用神經網路方式進行TWD67與TWD97地籍坐標系統;同時為了提升神經網路的效用,及解決神經網路的黑盒子問題,本研究提出利用神經網路建構網格式地籍坐標轉換模式的方法。為了驗証本研究所提出之坐標轉換方法,利用三個大小不同的實驗區之共同點資料,由不同方式轉換所得的結果顯示,以純粹利用神經網路方式所得轉換結果為佳,而網格式地籍坐標轉換模式所得結果與利用最小二乘法求解結果不相上下。 | zh_TW |
dc.description.abstract (摘要) | Currently, there are two cadastral coordinate systems used in Taiwan. They are TWD67 (Taiwan Datum 1967) and TWD97 (Taiwan Datum 1997) cadastral coordinate systems respectively. Frequently it is necessary to transform from one coordinate system to another. One of the most widely used method is Least-Squares with affine transformations.The artificial neural network (ANN) provides a new technology for cadastral coordinate transformation. The popularity of this methodology is rapidly growing. The greatest advantage of ANN is that it can be used very successfully with a huge quantity of data and free-model estimation that traditional transformation methods cannot be applied.In this research coordinate transformation between TWD67 and TWD97 with artificial neural network (ANN) and Least-Squares with affine transformations were examined. Besides, in order to overcome the so called ‘‘Black Box Problem’’ of ANN, algorithm of applying artificial neural network to develop regional grid-based cadastral coordinate transformation model was proposed. Three data sets with varied sizes from the Taiwan region are used to test the proposed algorithms. The test results show that the coordinate transformation accuracies using the ANN models are better than those of using other methods, such as, Least-Squares with affine transformations. The proposed algorithms and the detailed test results are presented in this paper. | en_US |
dc.description.tableofcontents | 中文摘要.........................................Ⅰ英文摘要..........................................Ⅱ目錄.............................................Ⅲ圖目錄...........................................Ⅴ表目錄...........................................Ⅶ第一章、緒論......................................1第一節、前言......................................1第二節、研究動機與目的..............................3第三節、論文之架構.................................5第四節、研究流程...................................6第二章、文獻回顧...................................7第一節、地籍坐標轉換相關文獻回顧.....................7第二節、神經網路相關文獻回顧.........................9第三節、小結.......................................10第三章、神經網路...................................11第一節、神經網路簡介................................11第二節、神經網路的工作原理...........................12 一、學習過程....................................14 二、測試過程....................................15 三、影響神經網路效能的因素........................15第三節、倒傳遞神經網路...............................18 一、倒傳遞神經網路演算法..........................18 二、倒傳遞神經網路參數的決定.......................23 三、神經網路使用上之限制..........................27第四章、神經網路應用於地籍坐標轉換.....................29第一節、地籍坐標轉換原理..............................29第二節、最小二乘法應用於地籍坐標轉換....................30第三節、神經網路應用於地籍坐標轉換......................32 一、訓練神經網路...................................32 二、網格式地籍坐標轉換模式的建立與應用................34第五章、實驗成果與分析.................................37第一節、實驗區資料....................................37 一、台灣本島實驗區資料..............................37 二、台北市南區實驗區資料............................39 三、台中市實驗區資料................................40第二節、資料處理與實驗方法..............................41 一、資料預處理.....................................41 二、實驗方法.......................................41 三、資料驗證.......................................43第三節、實驗結果與分析.................................47 一、神經網路應用於地籍坐標轉換有關參數值設定之實驗.....47 二、網格式地籍坐標轉換模式實驗.......................62 三、網格式地籍坐標轉換模式於數值法地籍測量中的應用情形..66第六章、結論與建議.....................................73第一節、結論….........................................73第二節、建議..........................................75參考文獻.............................................77 | zh_TW |
dc.format.extent | 62847 bytes | - |
dc.format.extent | 72343 bytes | - |
dc.format.extent | 104061 bytes | - |
dc.format.extent | 154375 bytes | - |
dc.format.extent | 123597 bytes | - |
dc.format.extent | 477264 bytes | - |
dc.format.extent | 220003 bytes | - |
dc.format.extent | 954273 bytes | - |
dc.format.extent | 96362 bytes | - |
dc.format.extent | 163247 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | en_US | - |
dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0093257006 | en_US |
dc.subject (關鍵詞) | TWD67坐標系統 | zh_TW |
dc.subject (關鍵詞) | TWD97坐標系統 | zh_TW |
dc.subject (關鍵詞) | 神經網路 | zh_TW |
dc.subject (關鍵詞) | TWD67 | en_US |
dc.subject (關鍵詞) | TWD97 | en_US |
dc.subject (關鍵詞) | artificial neural network | en_US |
dc.title (題名) | 神經網路應用於地籍坐標轉換之研究 | zh_TW |
dc.title (題名) | Cadastral Coordinate Transformation Using Artificial Neural Network | en_US |
dc.type (資料類型) | thesis | en |
dc.relation.reference (參考文獻) | 中文部分: | zh_TW |
dc.relation.reference (參考文獻) | 1.王文安,2005,「應用不同幾何方法推求區域性大地起伏值之研究-以臺中市為例」,國立中興大學土木工程學系碩士論文:台中。 | zh_TW |
dc.relation.reference (參考文獻) | 2.尤瑞哲,1998,「三度空間GPS 坐標和台灣地區二度TM 坐標轉換可行性分析之研究」,NSC 87-2211-E006-036。 | zh_TW |
dc.relation.reference (參考文獻) | 3.伍志宗,2003,「製圖區地控點資訊不足之基準轉換研究」,國防大學中正理工學院軍事工程研究所碩士論文:桃園。 | zh_TW |
dc.relation.reference (參考文獻) | 4.何維信,2005,「數值地形模型、上課講義第四章」,國立政治大學地政系。 | zh_TW |
dc.relation.reference (參考文獻) | 5.林老生,2005,「利用神經網路建立台灣區大地起伏模式之研究」,『中國測量工程學會論文研討會論文集』,第1-16頁。 | zh_TW |
dc.relation.reference (參考文獻) | 6.洪慧齡,1999,「土地測量成果坐標整合之研究」,國立成功大學測量工程研究所碩士論文:台南。 | zh_TW |
dc.relation.reference (參考文獻) | 7.許皓寧,2003,「臺北市地籍資料TWD67與TWD97坐標轉換之比較研究」,國立中興大學土木工程學系碩士論文:台中。 | zh_TW |
dc.relation.reference (參考文獻) | 8.陳立夫,2005,「土地法規」,新學林出版股份有限公司:台北。 | zh_TW |
dc.relation.reference (參考文獻) | 9.黃華尉,2001,「TWD97 與TWD67 二度TM 坐標轉換之研究」,國立成功大學測量工程研究所碩士論文:台南。 | zh_TW |
dc.relation.reference (參考文獻) | 10.溫豐文,2003,『土地法』,二○○三年九月修訂版。 | zh_TW |
dc.relation.reference (參考文獻) | 11.董倩琪,2005,「以最小二乘配置法整合臺北市地籍圖資料至TWD97坐標系統作業方法之研究」,『中華民國地籍測量學會會刊論文集』,第78-100頁。 | zh_TW |
dc.relation.reference (參考文獻) | 12.劉正倫、鄭彩堂、董荔偉,2004,「以約制條件實施坐標轉換整合圖解數化成果之研究」,內政部土地測量局93年度自行研究報告:台中。 | zh_TW |
dc.relation.reference (參考文獻) | 13.蔡慶賢,2002,「類神經網路在風浪推測上的研究」,國立中興大學土木工程學系碩士論文:台中。 | zh_TW |
dc.relation.reference (參考文獻) | 14.鄭彩堂,2002,「以限制條件及附加參數法輔助圖解區土地複丈之研究」,國立中興大學土木工程學系碩士論文:台中。 | zh_TW |
dc.relation.reference (參考文獻) | 15.戴翰國、余致義、曾清涼,2002,「利用六參數平面轉換與最小二乘配置進行小區域TWD67 與TWD97 之地籍資料坐標轉換-以臺北市大安通化段為例」,『第五屆GPS 衛星科技研討會』,第66-71頁。 | zh_TW |
dc.relation.reference (參考文獻) | 16.蕭榮錦,2003,「土地複丈作業系統改進之研究─以台北市為例」,國立台北大學地政學系研究所碩士論文:台北。 | zh_TW |
dc.relation.reference (參考文獻) | 17.蘭雪梅、朱健、黃承明、董德存,2003,『BP網絡的MATLAB實現,微型電腦應用』,19(1):第6-8頁。 | zh_TW |
dc.relation.reference (參考文獻) | 18.蘇昭安,2003,『應用倒傳遞類神經網路在颱風波浪預報之研究』,國立臺灣大學工程科學與海洋工程學系碩士論文:台北。 | zh_TW |
dc.relation.reference (參考文獻) | 英文部分: | zh_TW |
dc.relation.reference (參考文獻) | 1.Demuth, Howard. and Beale, Mark, 2002, User’s Guide of Neural Network Toolbox For Use with MATLAB, Version 4, The MathWorks. | zh_TW |
dc.relation.reference (參考文獻) | 2.Federal Geographic Data Committee(FGDC),1998, Part 3. National Standard for Spatial Data Accuracy, Geospatial Positioning Accuracy Standards, GDC-STD-007.3-1998, Washington, D.C., Federal Geographic Data Committee, Pp.1~28. | zh_TW |
dc.relation.reference (參考文獻) | 3.Jacek M. Zurada, 1992, Introduction to Artificial Neural Systems, West Publishing | zh_TW |
dc.relation.reference (參考文獻) | Company. | zh_TW |
dc.relation.reference (參考文獻) | 4.Junkins, J.L., Miller, G.W. & Jancaitis, J.R., 1973, A weighting function approach to modeling of irregular surfaces. Jurnal of Geophysical Research, Vol. 78, No. 11,April, 1794-1803. | zh_TW |
dc.relation.reference (參考文獻) | 5.Lin, L.S., 1998, Real-time estimation of ionospheric delay using GPS measurements,UNISURV S-51, Reports from School of Geomatic Engineering, The University of New South Wales, Sydney, NSW, Australia. | zh_TW |
dc.relation.reference (參考文獻) | 6.Naser El-Sheimy, 1999, Digital Terrian Modelling, Department of Geomatics Engineering The University of Calgary, Canada. | zh_TW |
dc.relation.reference (參考文獻) | 7.Paláncz B., Völgyesi L., 2003, High accuracy data representation via sequence of neural networks, Acta Geod.Geoph. Hung., Vol. 38 (3), Pp. 337-343. | zh_TW |
dc.relation.reference (參考文獻) | 8.Paul R.Wolf, Charles D.Ghilani, 1997, Adjustment computations: statics and least squares in suryeying and gis 3rd, John Wiley & Sons, Inc. | zh_TW |
dc.relation.reference (參考文獻) | 9.Pen-Shan Hung , 2005, Coordinate Transformation of the Digitized Graphical Cadastral Maps to TWD97, 2005年國際空間資訊理論與應用研討會論文集, 逢甲大學主辦. | zh_TW |
dc.relation.reference (參考文獻) | 10.Piroska Zaletnyik, 1999, Coordinate Transformation with Neural networks and with Polynominals in Hungary. Geodézia és Kartográfia, Budapest, LI, No. 10. Pp.12-18. (in Hungarian) | zh_TW |
dc.relation.reference (參考文獻) | 11.Rumelhart, D.E., McClelland, J.L., and the PDP Research Group,1986. PARALLEL DISTRIBUTED PROCESSING, Vol. 1, MIT Press, Cambridge, MA. | zh_TW |
dc.relation.reference (參考文獻) | 12.Villiers J., Barnard E., 1992. Back-Propagation Neural Netswith One and Two Hidden Layers. IEEE Transaction On Neural Network, Vol. 4, No. 1, Pp.136-141. | zh_TW |
dc.relation.reference (參考文獻) | 13.Zaletnyik P., Völgyesi L., Paláncz B., 2004, Approach of the Hungarian Geoid | zh_TW |
dc.relation.reference (參考文獻) | Surface with Sequence of Neural Networks, ISPRS2004. | zh_TW |
dc.relation.reference (參考文獻) | 網址部分: | zh_TW |
dc.relation.reference (參考文獻) | 類神經網路簡介 | zh_TW |
dc.relation.reference (參考文獻) | http://www.gct.ntou.edu.tw/Lab/aiwww/neural.html | zh_TW |
dc.relation.reference (參考文獻) | The Mathworks | zh_TW |
dc.relation.reference (參考文獻) | http://www.mathworks.com | zh_TW |
dc.relation.reference (參考文獻) | 沃爾夫勒姆研究公司 | zh_TW |
dc.relation.reference (參考文獻) | http://www.wolfram.com/index.html | zh_TW |
dc.relation.reference (參考文獻) | How many hidden layers should I use? | zh_TW |
dc.relation.reference (參考文獻) | http://www.faqs.org/faqs/ai-faq/neural-nets/part3/section-9.html | zh_TW |
dc.relation.reference (參考文獻) | Preconditioning the Network | zh_TW |
dc.relation.reference (參考文獻) | http://www.willamette.edu/~gorr/classes/cs449/precond.html | zh_TW |