透過您的圖書館登入
IP:18.222.119.148
  • 學位論文

地理視覺化輔助的空間知識探索-台北市交通流量的個案分析

Applying Geovisualization Techniques in Enhancing Knowledge Discovery Framework for Geographical Databases-The Case Study of Traffic Flow in Taipei City

指導教授 : 朱子豪
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


地理視覺化探索分析是一種利用地理空間的互動展示來探索多維度時空資料的方法,自組織映射圖網路的視覺化技術是目前最有效的方法,但仍存在部分問題,如資料的分類方法以及類神經網路的大小需依賴研究者主觀判斷。本研究提出「先分解再重新聚類」的方法,整合自組織映射圖及空間自組織映射圖兩種類神經網路演算法以及群聚演算法,利用逐步合併神經元的群聚資料,達到動態調整分類數量的方式,再配合其他視覺化及空間地圖的展示,來探索資料隱含的關係與空間特徵。本研究使用兩個案例進行視覺化探索,第一案例使用台北市早晚尖峰時間車流量資料進行分析,發現無法找出資料關連的原始資料,再經由地理視覺化探索分析後,可在尖峰時間的東西向汽車車流量資料當中找到兩個主要的集合。此兩集合不但在相關係數及判定係數上均有顯著的改善,同時在空間上也可區分為兩個不同的分區。第二個案例使用機車車流量進行分析,在早晨尖峰時間的資料當中,經過地理視覺化探索分析後,可以發現六個主要的空間群聚以及線型的空間特徵。顯示地理視覺化探索分析對於發現地理資料的空間特性,以及辨識不同區域資料的差異性具有不錯的效果。研究結果顯示本研究提出的方法容易觀測到空間或是資料的關連特徵,未來可應用本研究的方法分析其他的時空資料。

並列摘要


Geovisualization is a method of exploring spatial knowledge hidden in multidimensional geographic and temporal data via interaction with map and graph. The visualization of Self-Organizing Map (SOM) is one of the most effective methods but still has problems of what size the network should be. This research proposed a novel method called “Divide and Regroup”, to integrate clustering analysis and two SOM algorithms (SOM and Geo-SOM) interactively and dynamically for finding hidden data relations and spatial patterns. Two different rush-hour traffic flow data of Taipei City were selected and two cases were done to demonstrate the effectiveness of this novel method. In the first case, the correlation coefficient and coefficient of determination of the unclassified data were low. Two major groups of traffic flow data were recognized using the Geovisualization approach. The correlation coefficients and coefficients of determination of the classified data have improved significantly. In the second case, six major spatial clusters and liner feature groups were recognized. Furthermore, these groups showed different data patterns indicate that the Geovisualization approach is useful for identifying spatial and data characteristics hidden in geographic data. The results demonstrated the effectiveness of the novel method of Geovisualization.

參考文獻


Aditya, T. & Kraak M. (2005) Reengineering the Geoportal: Applying HCI and Geovisualization Disciplines. Proceedings of 11th EC-GI & GIS Workshop, ESDI: Setting the Framework, Alghero.
Aggarwal, C. & Yu, P. (2001) Outlier detection for high dimensional data. ACM SIGMOD Record, 30 (2), 37-46.
Andrienko, G. & Andrienko, N. (2005) Visual exploration of the spatial distribution of temporal behaviors. Information Visualisation, 2005. Proceedings. Ninth International Conference on, 799-806.
Andrienko, G. & Andrienko, N. (1999) Interactive maps for visual data exploration. International Journal of Geographical Information Science, 13 (4), 355-374
Andrienko, N., Andrienko, G. & Gatalsky, P. (2003) Exploratory spatio-temporal visualization: An analytical review. Journal of Visual Languages & Computing, 14 (6), 503-541

被引用紀錄


李美儀(2015)。車輛路線相關問題之回顧與國內發展之分析〔碩士論文,國立交通大學〕。華藝線上圖書館。https://doi.org/10.6842/NCTU.2015.00488
陳俊傑(2004)。使用種子導引的蟻拓分群優化法求解車輛途程問題〔碩士論文,國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU.2004.00687

延伸閱讀