針對路網週邊交通監控查詢探索動態扇形

Abstract

在本論文中，我們首先介紹 CarWeb 系統提供的即時交通路況預測服務，該服務針對使用者的移動行為即時的提供附近的交通路況預測。本論文著重在研究如何有效率又精準的提供使用者最適當的資訊，我們特別將問題聚焦在交通路網上移動的個體其連續的範圍查詢所涵蓋的路段上，為了解決這個問題，我們研究不同參數設定下圓形和扇形範圍查詢的特性與使用者移動行為的關係，我們提出了「動態扇形連續查詢架構」動態的改變扇型參數以有效率又不妥協系統效能的情況下取得較有用的查詢結果，我們最後採用真實世界所紀錄的交通軌跡並實作了廣泛的實驗以驗證該架構的適用性。

While people are driving, realtime traffic information on their way is informative and useful. With the prevalence of global positioning system (GPS) and portable devices, people can share and acquire traffic information by location-based applications. In this paper, we first introduce the traffic status estimation service, a location-based continuous range query application provided by the CarWeb system. The service provides users nearby with realtime traffic estimations according to their current locations and moving behaviors. This paper focuses on how to provide users with the most relevant traffic information efficiently and accurately. We emphasize the problem for objects moving on road networks requesting continuous range queries for traffic information of all road segments covered within the range. To tackle the problem, we study both circular and fan shaped range queries with different parameters comparing their coverage features with different moving behaviors of objects. We propose the Continuous Query with Dynamic Fan-Shape (CQ-DFS) framework which dynamically changes the parameters of the fan shaped range query to efficiently acquire useful traffic information without compromising the performance of the system. We conduct extensive experiments to demonstrate the effectiveness of the CQ-DFS framework using real world vehicle trajectories.