Estimation of Origin and Destination Information from Bluetooth and Wi-Fi Sensing for Transit
Estimation of Origin and Destination Information from Bluetooth and Wi-Fi Sensing for Transit
复制标题
通过蓝牙和 Wi-Fi 传感估计交通的出发地和目的地信息
DOI：
10.3141/2595-02
复制
发表时间：
2016
影响因子：
1.7
通讯作者：
Yinhai Wang
中科院分区：
文献类型：
--
作者：
M. Dunlap;Zhibin Li;Kristian C. Henrickson;Yinhai Wang
城市公共交通为许多人提供了一种方便，负担得起和可持续的交通方式。然而，有限的补贴和从公共汽车票价中收取的收入限制了可以运营的公共汽车线路的数量;这些限制反过来又限制了可以从公共交通中受益的人数。要为公交规划和运营做出明智的运营决策，了解乘客的出发地和目的地模式至关重要。然而，传统的过境数据收集方法是劳动密集型和昂贵的。虽然一些交通机构使用智能卡交易的数据来容易地获得行程起点信息，但不能直接推断出行程目的地信息。为了帮助运输数据采集工作，本研究提出了一种新的技术，使用蓝牙和无线保真（Wi-Fi）传感技术来估计运输线路的起源和目的地信息。在四辆公共汽车上安装了传感器，以收集为期4周的蓝牙，Wi-Fi和GPS位置数据。采用了新的数据处理和简化方法，以排除无效检测。在有效样本的基础上，估计了一个大学运营的公交线路在不同公交站点的始发地和目的地信息。所开发的方法有可能被应用于大规模的过境网络。
Public urban transit offers a convenient, affordable, and sustainable mode of transportation for many. However, limited subsidies and revenue collected from bus fares place restrictions on the number of bus lines that can operate; these restrictions in turn limit the number of individuals who can benefit from public transit. To make well-informed operational decisions for transit planning and operations, understanding the origin and destination patterns of riders is crucial. However, traditional methods of transit data collection are labor-intensive and costly. Although some transit agencies use data from smart card transactions to obtain trip origin information readily, the trip destination information cannot be directly inferred. To aid in transit data acquisition efforts, this study presents a new technique that uses the Bluetooth and wireless fidelity (Wi-Fi) sensing technologies to estimate the origin and destination information for transit lines. Sensors were installed on four buses to collect Bluetooth, Wi-Fi, and GPS location data for a 4-week period. New methods for data processing and reduction were introduced to exclude invalid detections. On the basis of valid samples, the origin and destination information at different bus stops was estimated for a university operated transit line. The developed methods have the potential to be applied for large-scale transit networks.