Item Infomation
Title: | Mining Spatio-temporal Reachable Regions With Multiple Sources over Massive Trajectory Data |
Authors: | Ding, Yichen |
Participants: | Zhou, Xun Wu, Guojun Li, Yanhua Bao, Jie Zheng, Yu Luo, Jun |
Issue Date: | 2020 |
Publisher: | IEEE Xplore |
Series/Report no.: | IEEE Transactions on Knowledge and Data Engineering |
Abstract: | Given a set of user-specified locations and a massive trajectory dataset, the task of mining spatio-temporal reachable regions aims at finding which road segments are reachable from these locations within a given temporal period based on the historical trajectories. Determining such spatio-temporal reachable regions with high accuracy is vital for many urban applications, such as location-based recommendations and advertising. Traditional approaches to answering such queries essentially perform a distance-based range query over the given road network, which does not consider dynamic travel time at different time of day. By contrast, we propose a data-driven approach to formulate the problem as mining actual reachable regions based on a real historical trajectory dataset. Efficient algorithms for the Single-location spatio-temporal reachability Query (S-Query) and the Union-of-multi-location spatio-temporal reachability Query (U-Query) were presented in our recent work. In this paper, we extend the previous ideas by introducing a new type of reachability query with multiple sources, namely, the Intersection-of-multi-location spatio-temporal reachability Query (I-Query). As we demonstrate, answering I-Queries efficiently is generally more computationally challenging than answering either S-Queries or U-Queries because I-Queries involve complicated intersect conditions. We propose two new algorithms called the Intersection-of-Multi-location Query Maximum Bounding region search (I-MQMB) algorithm and the I-Query Trace Back Search (I-TBS) algorithm to efficiently answer I-Queries, which utilize an indexing schema composed of a spatio-temporal index and a connection index. We evaluate our system extensively by using a large-scale real taxi trajectory dataset that records taxi rides in Shenzhen, China. Our results demonstrate that the proposed approach reduces the running time of I-Queries by 50% on average compared to the baseline method |
URI: | http://tailieuso.tlu.edu.vn/handle/DHTL/10618 |
Source: | https://doi.org/10.1109/TKDE.2019.2959531 |
Appears in Collections: | Tài liệu hỗ trợ nghiên cứu khoa học |
ABSTRACTS VIEWS
20
VIEWS & DOWNLOAD
1
Files in This Item:
Bạn đọc là cán bộ, giáo viên, sinh viên của Trường Đại học Thuỷ Lợi cần đăng nhập để Xem trực tuyến/Tải về
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.