TripImputor: Real-Time Imputing Taxi Trip Purpose Leveraging Multi-Sourced Urban Data

TripImputor: Real-Time Imputing Taxi Trip Purpose Leveraging Multi-Sourced Urban Data
复制标题

TripImputor:利用多源城市数据实时输入出租车出行目的

DOI:
10.1109/tits.2017.2771231
复制
发表时间:
2018-10
影响因子:
8.5
通讯作者:
Yasha Wang
Yasha Wang
中科院分区:
工程技术1区
文献类型:
--
作者:
Chao Chen;Shuhai Jiao;Shu Zhang;Weichen Liu;Liang Feng;Yasha Wang

文献摘要

参考文献

被引文献

相似文献

出行行为理解是智慧城市领域一个长期存在且至关重要的课题。基于GPS的大量出行数据可以很容易地收集,其中出租车GPS轨迹数据是一个典型的例子。然而,GPS轨迹数据中关于旅行者活动的信息通常很少,因此只能支持有限的应用。相当多的研究都集中在丰富原始数据的语义意义上,例如旅行方式/目的推断。不幸的是,旅行目的插补得到相对较少的关注,不需要实时响应。为了缩小差距,我们提出了一个概率两阶段框架命名为TripImputor,使实时出租车出行目的插补和推荐服务的乘客在他们的下车点。具体来说,在第一阶段,我们提出了一个两阶段的聚类算法来确定候选活动区(CAAs)在城市空间。然后,我们从foursquare签到数据中提取CAA内部人类行为的细粒度空间和时间模式,以近似每个活动的先验概率,并计算后验概率(即,推断旅行目的)使用贝叶斯定理。在第二阶段,我们采取了一个复杂的过程,集群的历史衰减点和匹配的衰减集群和CAA沉浸的实时响应。最后,我们使用真实世界的数据集,其中包括道路网络,超过38 000名用户在一年内产生的登记数据,并在一个月内超过19 000辆出租车在曼哈顿,纽约市,美国产生的大规模出租车行程数据的有效性和效率的建议的两阶段框架进行评估。实验结果表明,该系统能够准确推断出行目的,在曼哈顿平均1.6 s内向乘客提供推荐结果。
Travel behavior understanding is a long-standing and critically important topic in the area of smart cities. Big volumes of various GPS-based travel data can be easily collected, among which the taxi GPS trajectory data is a typical example. However, in GPS trajectory data, there is usually little information on travelers’ activities, thereby they can only support limited applications. Quite a few studies have been focused on enriching the semantic meaning for raw data, such as travel mode/purpose inferring. Unfortunately, trip purpose imputation receives relatively less attention and requires no real-time response. To narrow the gap, we propose a probabilistic two-phase framework named TripImputor, for making the real-time taxi trip purpose imputation and recommending services to passengers at their dropoff points. Specifically, in the first phase, we propose a two-stage clustering algorithm to identify candidate activity areas (CAAs) in the urban space. Then, we extract fine-granularity spatial and temporal patterns of human behaviors inside the CAAs from foursquare check-in data to approximate the priori probability for each activity, and compute the posterior probabilities (i.e., infer the trip purposes) using Bayes’ theorem. In the second phase, we take a sophisticated procedure that clusters historical dropoff points and matches the dropoff clusters and CAAs to immerse the real-time response. Finally, we evaluate the effectiveness and efficiency of the proposed two-phase framework using real-world data sets, which consist of road network, check-in data generated by over 38 000 users in one year, and the large-scale taxi trip data generated by over 19 000 taxis in a month in Manhattan, New York City, USA. Experimental results demonstrate that the system is able to infer the trip purpose accurately, and can provide recommendation results to passengers within 1.6 s in Manhattan on average, just using a single normal PC.
DOI: 10.1002/047172212x
发表时间: 2004-04
期刊: --
影响因子: --
作者:
W. M. Bolstad
通讯作者: W. M. Bolstad
CROWDDELIVER:利用出租车人群规划全市包裹递送路径
DOI: 10.1109/tits.2016.2607458
发表时间: 2017-06
影响因子: 8.5
作者:
Chen Chao;Zhang Daqing;Ma Xiaojuan;Guo Bin;Wang Leye;Wang Yasha;Sha Edwin
通讯作者: Sha Edwin
T-DesP:基于轨迹大数据的目的地预测
DOI: 10.1109/tits.2016.2518685
发表时间: 2016
影响因子: 8.5
作者:
Li Xiang;Li Mengting;Gong Yue-Jiao;Zhang Xing-Lin;Yin Jian
通讯作者: Yin Jian
DOI: 10.18757/ejtir.2015.15.4.3103
发表时间: 2015-09
影响因子: 1.7
作者:
T. Feng;H. Timmermans
通讯作者: T. Feng;H. Timmermans
DOI: 10.1108/9781786359551-016
发表时间: 2003-05
期刊: --
影响因子: --
作者:
K. Clifton;S. Handy
通讯作者: K. Clifton;S. Handy