大数据驱动的多源移动终端位置数据重复设备检测框架
A Big Data Driven Framework for Duplicate Device Detection from Multi-sourced Mobile Device Location Data
摘要：
移动终端位置数据（MDLD）已经在各种领域中被广泛使用。然而，其大规模的应用是有限的，因为从个别数据供应商的数据的偏见或不足的空间覆盖。提高数据覆盖率的一种方法是利用来自多个数据供应商的数据，并将它们集成以构建更具代表性的数据集。对于数据集成，由于多种原因，需要对多源数据集进行进一步处理。首先，携带多个设备的可能性可能会导致同一数据主体的重复观察。此外，当利用多个数据源时，同一设备可能被多个数据提供者捕获。我们的论文提出了一种多源数据的数据集成方法，以研究集成来自多个源的数据而不对数据引入额外偏差的可行性。通过利用每个设备的行进模式的唯一性，识别重复设备。所提出的方法被证明是具有成本效益的，同时它达到了所需的精度水平。我们的研究结果表明，在一个月内共享相同估算的家庭位置和前五个访问量最大的位置的设备可以在MDLD中代表相同的用户。结果表明，超过99.6%的样品设备具有上述属性的共同观察到在同一位置同时。最后，该算法已成功应用于2020年国家级MDLD，为下一代全国家庭旅行调查（NextGen NHTS）计划生成全国乘客始发地-目的地数据。
英文摘要：
Mobile Device Location Data (MDLD) has been popularly utilized in various fields. Yet its large-scale applications are limited because of either biased or insufficient spatial coverage of the data from individual data vendors. One approach to improve the data coverage is to leverage the data from multiple data vendors and integrate them to build a more representative dataset. For data integration, further treatments on the multi-sourced dataset are required due to several reasons. First, the possibility of carrying more than one device could result in duplicated observations from the same data subject. Additionally, when utilizing multiple data sources, the same device might be captured by more than one data provider. Our paper proposes a data integration methodology for multi-sourced data to investigate the feasibility of integrating data from several sources without introducing additional biases to the data. By leveraging the uniqueness of travel pattern of each device, duplicate devices are identified. The proposed methodology is shown to be cost-effective while it achieves the desired accuracy level. Our findings suggest that devices sharing the same imputed home location and the top five most-visited locations during a month can represent the same user in the MDLD. It is shown that more than 99.6% of the sample devices having the aforementioned attribute in common are observed at the same location simultaneously. Finally, the proposed algorithm has been successfully applied to the national-level MDLD of 2020 to produce the national passenger origin-destination data for the NextGeneration National Household Travel Survey (NextGen NHTS) program.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
