臺灣博碩士論文加值系統

隨著科技快速的發展， GPS (Global Positioning System，全球衛星定位系統)的免費開放使用，使用者可以使用GPS記錄各種不同的路徑與軌跡，因此GPS相關的研究與應用服務日益興盛，使GPS相關的應用與議題逐漸被重視，其中從GPS原始軌跡資料中分析與預測使用者行為也成為一個值得研究的議題。GPS的紀錄有許多的誤差與干擾影響軌跡的合理性，這些不合理的紀錄點在分析交通模式時會破壞軌跡的連續性、速度、加速度等等，故GPS軌跡資料在提取交通模式特徵與分析前需做資料的前處理，來加強分辨不同交通模式特徵的品質。接著本論文提出提取GPS原始軌跡資料中多種不同交通模式之特徵的方法來分析使用者交通模式，推論交通模式的演算法以決策樹(Decision tree)與邏輯回歸模型(Logistic Regression Model)兩種方式來做分析與比較，最後討論兩者推論出來的結果。

With the rapid development of Information Technology, the Global Positioning System (GPS) is widely and freely used to record the various kinds of path and trajectory for people. Therefore, the GPS-related applications have become much popular in our daily lives. However, it is an important issue to analyze and predict the user behaviors among the trajectory analysis from the original GPS data. Besides, there are many erroneous records of GPS data affecting the precision of GPS trajectories which may destroy the continuity of the trajectory, velocity, acceleration of the GPS trajectory when we identify the transportation mode from GPS trajectory. It should be fixed the unreasonable information before using the of GPS trajectory and then the feature extraction of GPS trajectory will be enhance the quality of features to classify different transportation modes based on user behaviors. By the way, this thesis try to find a way for extracting the mobility features from GPS trajectory and adopts the inference algorithms, decision tree and logistic regression model, for precisely identify the transport modes.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 x
第1章 緒論 1
1.1 研究背景 1
1.1.1 GPS 1
1.1.2 GPS分析 2
1.1.3 GPS用途 3
1.1.4 GPS交通模式 3
1.2 研究動機與目的 4
1.3 論文架構 5
第2章 文獻探討 6
2.1 GPS軌跡 6
2.2 GPS分析與應用 7
2.3 GPS軌跡交通模式預測 9
2.4 變速點(Change point)偵測路段 10
2.5 推論演算法 11
2.6 問題討論 12
第3章 GPS軌跡上的移動特徵擷取方法 13
3.1 R-Tree空間索引結構 13
3.2 交通模式特徵擷取方法 15
3.2.1 速度、加速度 15
3.2.2 改變方向角度 17
3.2.3 停留點與停留次數 20
3.2.4 路口 21
3.2.5 公車路線相似度 25
3.3 GPS軌跡交通模式分析 30
3.3.1 決策樹(Decision tree) 30
3.3.2 邏輯迴歸(Logistic Regression Model) 33
第4章 實驗分析 35
4.1 實驗資料 35
4.2 實驗流程 38
4.3 資料前處理 38
4.3.1 同一時間點多點軌跡之情況 39
4.3.2 排除不合理的紀錄點 43
4.4 參數設置 50
4.5 分析結果 52
4.5.1 決策樹 52
4.5.2 邏輯回歸 54
第5章 結論與未來展望 60
第6章 參考文獻 62

[1] X. Chen , “A Comparison of Decision Tree and Logistic Regression Model,” North Dakota State University

[2] M. Ester, H. Kriegel, J. Sander and X. Xu, “A density-based algorithm for discovering clusters in large spatial databases with noise,” in Proceedings of the 2th Internatioanl Conference on Knowledge Discovery and Data Mining, pp. 226–231, 1996.

[3] T. C. Hsieh, “An Analysis of User Behavior Similarity Based on GPS Trajectory Information,” Master Thesis, Department of Computer Science and Information Engineering, National Chiayi University, 2012.

[4] C. Gang, C. Baoquan, and Y. Yizhou, “Mining Frequent Trajectory Patterns from GPS Tracks,” in Proceedings of International Conference on Computational Intelligence and Software Engineering (CiSE), pp. 1 - 6, 10-12 Dec. 2010.

[5] H. Jiawe and M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann, New York, 2007.

[6] Y. Koyama, L. Tan Kok, T. Tanaka, “High-Precision GPS Measurement for Motorcycle Trajectory Using Kalman Filter,” in Proceedings of the 6th International Conference on Networked Sensing Systems (INSS), June 17-19, 2009.

[7] Q. Li, Y. Zheng, X. Xie, Y. Chen, W. Liu and W. Y. Ma, “Mining User Similarity Based on Location History,” in Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2008.

[8] A. H. Mohamed, K. P. Schwarz, “Adaptive Kalman Filtering for INS/GPS,” Journal of Geodesy vol. 73, pp. 193-203, 1999.

[9] M. Ester, H. P. Kriegel, J. Sander, X. Xu, “A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise,” in Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), pp. 226-231, 1996.

[10] M. S. SMITH, “Processing of Prefiltered CPS Data,” IEEE Transactions on Aerospace and Electronic systems vol. 25, NO. 5, pp. 711-728, September, 1989.

[11] C. Xu, M. Ji*, W. Chen, and Z. Zhang “Identifying Travel Mode from GPS Trajectories through Fuzzy Pattern Recognition,” in Proceedings of IEEE 10th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 889 - 893, 2010.

[12] J. J. C. Ying , E. H. C. Lu, W. C. Lee, T. C. Weng, V. S. Tseng, “Mining User Similarity from Semantic Trajectories,” in Proceedings of the 2nd International Workshop on Location Based Social Networks, pp. 19-26, November 2, 2010.

[13] W. Zheng, Y. Zheng, X. Xie and Q. Yang, “Collaborative Location and Activity Recommendations with GPS History Data,” in Proceedings of the 9th international conference on World wide web, pp. 1029-1038, 2010.

[14] Y. Zheng, L. Liu, L. Wang and X. Xie, “Learning Transportation Mode from Raw GPS Data for Geographic Applications on the Web,” in Proceedings of the 17th International World Wide Web Conference, pp. 247-256, 2008.

[15] Y. Zheng, Q. Li, Y. Chen, X. Xie and W. Y. Ma, “Understanding Mobility Based on GPS Data,” in Proceedings of the 10th International Conference on Ubiquitous Computing, pp. 312-321, 2008.

[16] Y. Zheng, L. Zhang, X. Xie, W. Y. Ma “Mining Interesting Locations and Travel Sequences from GPS Trajectories,” in Proceedings of the International World Wide Web Conference Committee (IW3C2), pp. 791-800, April 20-24, 2009.

[17] Y. Zheng, X. Xie “Learning Location Correlation from GPS Trajectories”, in Proceedings of the 11th International Conference on Mobile Data Management (MDM), pp. 27-32, May 23-26, 2010.

[18] GeoLife GPS Trajectories [Online]. Available:
http://research.microsoft.com/en-us/downloads/b16d359d-d164-469e-9fd4-daa38f2b2e13/

[19] GPS軌跡資訊檔案格式參考[Online]. Available :
http://www.rus-roads.ru/gps/help_ozi/fileformats.html

[20] 市區道路人行道設計手冊 [Online]. Available :http://w3.cpami.gov.tw/district6/i4.htm

[21] 吳佳展（2005），台灣地區交通路網電子地圖之建置，義守大學資訊管理研究所碩士論文。

[22] 邱秋婷（2007），屬性導向方法應用於證券交易相對關係規則之挖掘，國立中央大學資訊管理研究所碩士論文。

[23] 許政穆, 謝德瑾, 葉擎宏，以文史內容為主的行動導覽端服務建置，全國計算機會議2011

[24] 陳士杰，機器學習課程，國立聯合大學資訊管理學系。

[25] 劉育穎（2006），結合決策樹與遺傳演算法建構不同鋒線程度之基金投資組合-以國內發行之股票基金為例，中原大學資訊管理學系碩士班碩士論文.。

[26] 鄭昆霖（2002），在PDA上整合GPS與GIS之導航系統，逢甲大學資訊工程學系碩士班碩士論文。