数据加载中.....
|
请使用永久网址来引用或连结此文件:
https://nccur.lib.nccu.edu.tw/handle/140.119/126592
|
| 题名: | 以基因演算法優化最小二乘支持向量機提升大地起伏估計精度
Using genetic algorithm based least squares support vector machine to improve the undulation estimation accuracy |
| 作者: | 陳佳欣
Chen, Chia-Hsin |
| 贡献者: | 林老生
Lin, Lao-Sheng
陳佳欣
Chen, Chia-Hsin |
| 关键词: | 大地起伏
最小二乘支持向量機
基因演算法
正高
橢球高
Global Undulation
Least Squares Support Vector Machine (LSSVM)
Genetic Algorithm (GA)
Orthometric height
Ellipsoidal height |
| 日期: | 2019 |
| 上传时间: | 2019-10-03 17:20:08 (UTC+8) |
| 摘要: | 工程應用上常使用之正高常以逐差水準測量獲得，然其所需成本較高;而由GPS水準測量獲得之正高具有所需成本低之特性。為提升GPS水準測量精度，求得滿足一定精度的大地起伏模型為當前主要研究課題。
本研究使用最小二乘支持向量機(Least Squares Support Vector Machine)擬合區域的大地起伏，並使用基因演算法(Genetic Algorithm)，藉著其能快速求得全局最優(global optimization)之特性，對最小二乘支持向量機之參數進行搜索並優化，以提升大地起伏估計之精度。
本研究分別以台南市、台灣中部以及台灣為實驗區，利用區域內同時擁有正高、橢球高及點位平面坐標之一等水準點資料，以基因演算法優化之最小二乘支持向量機擬合大地起伏值。實驗成果顯示: (1)台南市、台灣中部以及台灣實驗區經基因演算法優化後之最小二乘支持向量機(LSSVM(GA))於大地起伏擬合精度較未優化前，分別提升19.13%(由0.0298m降至0.0241m)、42.83%(由0.0523m降至0.0299m)以及1.86%(由0.0431m降至0.0423m); (2)與相關研究比較後，成果顯示LSSVM(GA)於建立三實驗區之大地起伏模型上，精度均優於倒傳遞神經網路(Back Propagation Artificial Neural Network, BPANN)方法。
The orthometric height often used in engineering application can be derived by leveling, which costs a lot. Whereas the orthometric height derived by GPS leveling has the advantage of lower cost. And within the process of improving the accuracy of GPS levelling, obtaining the undulation model that satisfies the required accuracy is the main study goal.
In this paper, Least Square Support Vector Machine(LSSVM) will be used to estimate the undulation model. And the Genetic Algorithm (GA), which has the capability of global optimization, will be used to search and optimize the parameters of LSSVM to improve the accuracy of the undulation model.
Tainan, central part of Taiwan and Taiwan are chosen as the test area in this paper. For the test data, 2,067 benchmark points distributed throughout the Taiwan region with the orthometric height, the ellipsoidal height and plane coordinates of the points at the same time, were used. According to the test results, the conclusions are obtained as follows: (1) undulation are improved after using genetic algorithm based least squares support machine (LSSVM(GA)) with 19.13 % improvement in Tainan (reduced from 0.0298m to 0.0241m), 42.83 % improvement at central part of Taiwan (reduced from 0.0523m to 0.0299m) and 1.86% improvement in Taiwan (reduced from 0.0431m to 0.0423m). (2) after comparing with other studies, the results show that LSSVM(GA) is superior to Back Propagation Artificial Neural Network (BPANN) in establishing the undulation model of the three test area. |
| 參考文獻: | 一、中文參考文獻
王繼剛、胡永輝、孔令杰，2009。基於最小二乘支持向量機的區域GPS高程轉換組合，大地測量與地球動力學，第29卷，第5期，99-102頁。
任東風、徐愛功，2012。基於遺傳算法優化的徑向基神經網絡在礦區 GPS 高程轉換中的應用，大地測量與地球動力學，第32卷，第4期， 103-105頁。
任超、李和旺，2012。最小二乘支持向量機在 GPS 高程擬合中的應用，工程勘察，55-57頁。
何晨光、賀思德、董志民，2008。最小二乘支持向量機在人臉辨識中的應用，南大學學報，第30卷，第3期，239-245頁。
沈昱廷.，2011。以最小二乘支持向量機擬合區域性大地起伏值之研究-以台中地區為例，中興大學土木工程學系所學位論文，1-56頁。
周輝仁、任仙玲及鄭丕諤，2009。最小二乘支持向量基的參數優選方法及應用，系統工程學報，第24卷，第2期，248-252頁。
周理含，2010。最小二乘支持向量機在 GPS 高程轉換中的應用，工程地球物理學報，第7卷，第2期，243-247頁。
林老生，2012。e-GPS水準測量精度研究，台灣土地研究，第15卷，第2期，35-58頁。
林老生、黃鈞義，2015。基因演算法優化最小二乘支持向量在地籍坐標轉換之研究，國土測繪與空間資訊，第3卷，第2期，67-85頁。
姜華、曹紅妍，2010。基於最小二乘支持向量機的鐵路客運量預測研究，河南科學，第28卷，第8期，989-991頁。
陳帥、朱建寧。2008，區域似大地水準面確定的最小二乘支持向量機方法，華東理工大學學報，第34卷，第2期，278-282頁。
黃鈞義，2014。以基因演算法優化最小二乘支持向量機於坐標轉換之研究，國立政治大學地政研究所碩士論文。
劉鯖潔、陳桂明、劉小方、楊慶。2012，基於遺傳算法的 SVM 參數組合優化，計算機應用與軟件，第29卷，第4期，94-96頁。
盧敏，張展羽、馮寶平，2005。支持向量機在徑流預報中的應用探討，人民長江，第36卷，第8期，38-39頁。
蘇高利、柳欽火、鄧芳萍、辛曉洲，2007。基於 LSSVM 方法的晴空逐時太陽輻射模型，Journal of Beijing Normal University (Natural Science)，第43卷，第3期。
二、 英文參考文獻
Avci E., 2009. Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm support vector machines: HGASVM. Expert Systems with Applications, Vol. 36, No.2, pp. 1391-1402..
Cakir, L., and N. Yilmaz, 2014.Polynomials, radial basis functions and multilayer perceptron neural network methods in local geoid determination with GPS/levelling. Measurement , pp. 148-153.
Cai, Z., W. Xu, Y. Meng, C. Shi, and R. Wang, 2016. Prediction of landslide displacement based on GA-LSSVM with multiple factors. Bulletin of engineering geology and the environment, Vol. 75, No. 2, pp. 637-646.
Deng, X., X. Hua and Y. You, 2013. Transfer of height datum across seas using GPS leveling, gravimetric geoid and corrections based on a polynomial surface, Computers & Geosciences, Vol. 51, pp. 135-142.
Das, R. K., S. Samanta, S. K. Jana, and R. Rosa, 2017. Polynomial interpolation methods in development of local geoid model. The Egyptian Journal of Remote Sensing and Space Science.
Doganalp, S. and H. Z. Selvi, 2015, Local geoid determination in strip area projects by using polynomials, least-squares collocation and radial basis functions.Measurement, 73, pp. 429-438.
Featherstone, W., 2000. Refinement of gravimetric geoid using GPS and leveling data, J. Surv. Eng., Vol. 126, No. 2, pp. 27-56.
Grefenstette, J. J., 1986. Optimization of control parameters for genetic algorithms. IEEE Transactions on systems, man, and cybernetics, Vol, 16, No. 1, pp. 122-128.
Gunn, S. R., 1998, Support vector machines for classification and regression. ISIS technical report, Vol.14, No. 1, pp. 5-16.
Ghilani, C. D., 2010. Adjustment Computations: Spatial Data Analysis, 5th Edition, Wiley, John Wiley & Sons, Inc.
Gullu, M., Yilmaz, M., and Yilmaz, I., 2011. Application of back propagation artificial neural network for modelling local GPS/levelling geoid undulations: A comparative study. In FIG Working Week, pp. 18-22.
Heiskanen, W. A., and H. Moritz, 1967. Physical geodesy, Bulletin Géodésique (1946-1975), Vol. 86, No. 1, pp. 491-492.
Huang, C. L., and Wang, C. J., 2006. A GA-based feature selection and parameters optimizationfor support vector machines. Expert Systems with applications, Vol. 31, No. 2, pp. 231-240.
Jung, H. C., J. S. Kim, and H. Heo, 2015. Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach, Energy and Buildings, Vol. 90, pp. 76-84.
Kao, S. P., C. N. Chen, H. C. Huang, and Y. T. Shen, 2014. Using a least squares support vector machine to estimate a local geometric geoid model, Boletim de Ciências Geodésicas, Vol. 20, No. 2, pp. 427-443.
Kao, S. P., F. S. Ning, C. N. Chen, and C. L. Chen, 2017. USING PARTICLE SWARM OPTIMIZATION TO ESTABLISH A LOCAL GEOMETRIC GEOID MODEL, Boletim de Ciências Geodésicas, Vol. 23, No. 2, pp. 327-337.
Lin, L.S., 2007. Application of a Back-Propagation Artificial Neural Network to Regional Grid-Based Geoid Model Generation Using GPS and Leveling Data, Journal of Surveying Engineering, Vol. 133, No. 2, pp. 81-89.
Lin, L.S., 2014. Orthometric Height Improvement in Tainan City using RTK GPS and Local Geoid Corrector Surface Models, Journal of Surveying Engineering, Vol. 140, No. 1, pp. 35-43.
Liu, L. L., T. X. Zhang, M. Zhou, W. Wang, and L. K. Huang, 2014. Research of GPS elevation conversion based on least square support vector machine and BP neural network, Applied Mechanics and Materials, Vol. 501, pp. 2166-2171.
Mårtensson, S. G. , 2002. Height determination by GPS: Accuracy with respect to different geoid models in Sweden. In XXII FIG International Congress, April 19-26 2002, Washington, DC, USA , pp. 106-113.
Ning, F. S., 2015. Using surface fitting and buffer analysis to estimate regional geoidal undulation, Boletim de ciências geodésicas, Vol. 21, No. 3, pp. 624-636.
Suykens, J.A.K. and J. Vandewalle,1999. Least Squares Support Vector Machine Classifiers, Neural Processing Letters, Vol. 9, No.3, pp. 293-3
Smola, Alex J., and B. Schölkopf, 2004, A tutorial on support vector regression. Statistics and computing, Vol.14, No. 3, pp. 199-222.
Samanta, B., 2004. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms. Mechanical systems and signal processing, Vol. 18, No. 3, pp. 625-644.
Stopar, B., T. Ambrožič, M. Kuhar and G. Turk, 2006. GPS-derived geoid using artificial neural network and least squares collocation, Survey Review, Vol. 38, No. 300, pp. 513-524.
Vapnik, V., 1999, The nature of statistical learning theory, New York: Springer-Verlag, New York, Inc.
Veronez, M. R., Thum, A. B, and C. G., Souza, 2006. A new method for obtaining geoidal undulations through Artificial Neural Networks. In: Proceedings of 7 th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Lisbon, Portugal.
Xue, X., and M. Xiao, 2017. Deformation evaluation on surrounding rocks of underground caverns based on PSO-LSSVM. Tunnelling and Underground Space Technology, 69, pp. 171-181
Yang, J., and Honavar, V., 1998, Feature subset selection using a genetic algorithm. In Feature extraction, construction and selection. pp. 117-136.
Yang, Z., X. S. Gu, X. Y. Liang, and L. C. Ling, 2010, Genetic algorithm-least squares support vector regression based predicting and optimizing model on carbon fiber composite integrated conductivity. Materials & Design, Vol. 31, No. 3, pp. 1042-1049.
Zhang, W., Li, C., and Zhong, B., 2009, LSSVM parameters optimizing and non-linear system prediction based on cross validation. In 2009 Fifth International Conference on Natural Computation. Vol. 1, pp. 531-535
三、網頁參考
LSSVMlab v1.8，Math Works，取用日期2019年7月，https://www.esat.kuleuven.be/sista/lssvmlab/ |
| 描述: | 碩士
國立政治大學
地政學系
106257032 |
| 資料來源: | http://thesis.lib.nccu.edu.tw/record/#G0106257032 |
| 数据类型: | thesis |
| DOI: | 10.6814/NCCU201901190 |
| 显示于类别: | [地政學系] 學位論文
|
文件中的档案:
| 档案 |
大小 | 格式 | 浏览次数 |
|---|
| 703201.pdf | 4626Kb | Adobe PDF2 | 0 | 检视/开启 |
|
在政大典藏中所有的数据项都受到原著作权保护.
|
