基于WiFi探针数据的城市出行轨迹提取

doi:10.12082/dqxxkx.2021.200777

地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (11): 1946-1955.doi: 10.12082/dqxxkx.2021.200777

• 地球信息科学理论与方法 • 上一篇下一篇

基于WiFi探针数据的城市出行轨迹提取

廖嘉欣¹(), 吴启用¹, 兰小机¹^,^*(), 张红庆²

1. 江西理工大学土木与测绘工程学院,赣州 341000
2. 广东矩阵流大数据科技有限公司,东莞 523000

收稿日期:2020-12-22 修回日期:2021-02-18 出版日期:2021-11-25 发布日期:2022-01-25
通讯作者: *兰小机（1965— ）,男,江西高安人,博士,二级教授,主要从事GIS应用开发。E-mail: landcom8835@163.com
作者简介:廖嘉欣（1997— ）,男,江西定南人,硕士,主要从事无线传感器网络与GIS研究。E-mail: 1204163777@qq.com
基金资助:
国家自然科学基金项目(41561085);国家自然科学基金项目(40971234)

Urban Travel Trajectory Extraction based on WiFi Probe Data

LIAO Jiaxin¹(), WU Qiyong¹, LAN Xiaoji¹^,^*(), ZHANG Hongqing²

1. School of Civil and Surveying and Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China
2. Guangdong Matrix Flow Big Data Technology Company Limited, Dongguan 523000, China

Received:2020-12-22 Revised:2021-02-18 Online:2021-11-25 Published:2022-01-25
Contact: *LAN Xiaoji, E-mail: landcom8835@163.com
Supported by:
National Natural Science Foundation of China, No(41561085);National Natural Science Foundation of China, No(40971234)

摘要/Abstract

摘要：

为了更便捷地提取城市居民的出行轨迹,从而分析个体的日常空间行为,进而为城市管理的各项措施决策提供数据支撑,本文提出基于WiFi探针数据的城市出行轨迹提取方法,主要解决WiFi探针数据的路网匹配及丢失轨迹重构问题。首先,通过对终端MAC码和时间戳进行多列排序后提取出轨迹记录序列,利用信号强度RSSI值为每条记录提取坐落在路网上的候选点集。其次,设计基于局部评价的算法,对于每一个候选点,利用其前后相邻的几条记录提取的候选点集与其之间的时空关系,先后对其进行时间一致性评价和空间一致性评价,再结合以时间反比动态构建的权函数,得到最终评分;然后将每个候选点集中评分最高的点作为最佳匹配点,至此完成轨迹记录的路网匹配。最后,先采用基于深度优先的路径搜索算法搜索出丢失轨迹上下点之间的所有可行路径,再基于TOPSIS法决策出最优的重构路径。本文以东莞市市中心区域收集的WiFi探针数据为实验数据进行测试,平均每日可提取6万多条轨迹,与其中获取的GPS数据相比较验证了方法的可行性,为城市出行轨迹挖掘提供了新的解决方案。

关键词: WiFi探针数据, 轨迹提取, RSSI值, 局部评价, 路网匹配, 深度优先搜索, TOPSIS决策法, 轨迹重构

Abstract:

In order to extract the travel trajectory of urban residents more conveniently, analyze the daily spatial behavior of individuals, and provide data support for the decision-making of urban management measures, this paper proposes an urban travel trajectory extraction method based on WiFi probe data, which mainly solves the problem of map matching and lost trajectory reconstruction of WiFi probe data. First, extract the track record sequence by sorting the terminal MAC code and timestamp in multiple columns, and use the RSSI value to extract the candidate point set located on the road network for each record. Secondly, an algorithm based on local evaluation is designed: for each candidate point, the spatio-temporal relationship between the candidate point set extracted from the adjacent records is used to evaluate its temporal consistency and spatial consistency, and then the final score is obtained by combining with the weight function dynamically constructed in inverse time ratio, then the highest score point in each candidate point set is selected as the best matching point. Finally, a depth-first-based path search algorithm is used to search for all feasible paths between the upper and lower points of the lost trajectory, and then the optimal reconstruction path is determined based on the TOPSIS method. In this paper, the WiFi probe data collected in the central area of Dongguan City is used as the experimental data to test, and more than 60 000 tracks can be extracted every day on average. Compared with the GPS data, the feasibility of the method is verified, which provides a new solution for urban travel trajectory mining.

Key words: WiFi probe data, trajectory extraction, RSSI value, local evaluation, map matching, depth first search, TOPSIS, trajectory reconstruction

廖嘉欣, 吴启用, 兰小机, 张红庆. 基于WiFi探针数据的城市出行轨迹提取[J]. 地球信息科学学报, 2021, 23(11): 1946-1955.DOI:10.12082/dqxxkx.2021.200777

LIAO Jiaxin, WU Qiyong, LAN Xiaoji, ZHANG Hongqing. Urban Travel Trajectory Extraction based on WiFi Probe Data[J]. Journal of Geo-information Science, 2021, 23(11): 1946-1955.DOI:10.12082/dqxxkx.2021.200777

图/表 12

表1

表2

图1

图2

图3

图4

图5

图6

图7

表3

表4

图8

参考文献 21

[1]	刘瑜, 肖昱, 高松, 等. 基于位置感知设备的人类移动研究综述[J]. 地理与地理信息科学, 2011, 27(4):8-13,31,2.
	[ Liu Y, Xiao Y, Gao S, et al. A review of human mobility research based on location aware devices[J]. Geography and Geo-information Science, 2011, 27(4):8-13,31,2. ]
[2]	付鑫, 孙茂棚, 孙皓. 基于GPS数据的出租车通勤识别及时空特征分析[J]. 中国公路学报, 2017, 30(7):134-143.
	[ Fu X, Sun M P, Sun H. Taxi commute recognition and temporal-spatial characteristics analysis based on GPS data[J]. China Journal of Highway and Transport, 2017, 30(7):134-143. ]
[3]	Moreira-Matias L, Gama J, Ferreira M, et al. Time-evolving O-D matrix estimation using high-speed GPS data streams[J]. Expert Systems With Applications, 2016, 44:275-288. doi: 10.1016/j.eswa.2015.08.048
[4]	Luo X, Dong L, Dou Y, et al. Analysis on spatial-temporal features of taxis' emissions from big data informed travel patterns: A case of Shanghai, China[J]. Journal of Cleaner Production, 2016, 142:926-935. doi: 10.1016/j.jclepro.2016.05.161
[5]	钟炜菁, 王德, 谢栋灿, 等. 上海市人口分布与空间活动的动态特征研究——基于手机信令数据的探索[J]. 地理研究, 2017, 36(5):972-984. doi: 10.11821/dlyj201705013
	[ Zhong W J, Wang D, Xie D C, et al. Dynamic characteristics of Shanghai's population distribution using cell phone signaling data[J]. Geographical Research, 2017, 36(5):972-984. ]
[6]	秦萧, 甄峰, 熊丽芳, 等. 大数据时代城市时空间行为研究方法[J]. 地理科学进展, 2013, 32(9):1352-1361.
	[ Qin X, Zhen F, Xiong L F, et al. Methods in urban temporal and spatial behavior research in the big data era[J]. Progress in Geography, 2013, 32(9):1352-1361. ]
[7]	方家, 王德, 谢栋灿, 等. 上海顾村公园樱花节大客流特征及预警研究——基于手机信令数据的探索[J]. 城市规划, 2016, 40(6):43-51.
	[ Fang J, Wang D, Xie D C, et al. Research on dynamic change and early warning of large tourist flow based on mobile signal data analysis: A case study of Gucun park sakura festival in Shanghai[J]. City Planning Review, 2016, 40(6):43-51.]
[8]	周涛, 赵必成, 俞博. 基于CRISP-DM的交通大数据分析方法及实践——以重庆市手机信令数据和RFID数据为例[J]. 城市交通, 2017, 15(5):42-51.
	[ Zhou T, Zhao B C, Yu B. Transportation big data analysis methodology based on CRISP-DM: An example of cellular signaling and RFID data in Chongqing[J]. Urban Transport of China, 2017, 15(5):42-51. ]
[9]	蒋寅, 郑海星, 于士元, 等. 天津市职住空间分布与轨道交通网络耦合关系——基于手机信令数据分析[J]. 城市交通, 2018, 16(6):26-35.
	[ Jiang Y, Zheng H X, Yu S Y, et al. Relationship between job-housing spatial distribution and rail transit network in Tianjin: An analysis based on cellular data[J]. Urban Transport of China, 2018, 16(6):26-35. ]
[10]	陆振波, 龙振, 余启航. 基于手机信令数据的昆山市职住分布与通勤特征分析[J]. 现代城市研究, 2019, 34(3):50-55.
	[ Lu Z B, Long Z, Yu Q H. Analysis on the job-housing spatial distribution and commuting characteristics of Kunshan city based on cellular signaling data[J]. Modern Urban Research, 2019, 34(3):50-55. ]
[11]	李萍. 基于校园WiFi探测的用户移动性研究[D]. 北京:北京邮电大学, 2016.
	[Li P. Research on user mobility based on campus WiFi detection[D]. Beijing: Beijing University of Posts and Telecommunications, 2016. ]
[12]	陈菁菁, 江志彬. 基于WiFi嗅探数据的地铁网络客流分析技术[J]. 城市轨道交通研究, 2018, 21(5):153-157.
	[ Chen J J, Jiang Z B. Passenger flow analysis technology in metro network based on wi fi probing data[J]. Urban Mass Transit, 2018, 21(5):153-157. ]
[13]	李思杰, 朱炜, 黄兆东. 基于WIFI数据的城市轨道交通乘客出行时空轨迹推定[J]. 华东交通大学学报, 2017, 34(2):85-92.
	[ Li S J, Zhu W, Huang Z D. Travel time-space trajectory characterization of urban rail transit network based on WIFI data[J]. Journal of East China Jiaotong University, 2017, 34(2):85-92. ]
[14]	徐洋, 孙建忠, 黄磊, 等. 基于WiFi定位的区域人群轨迹模型[J]. 山东大学学报(理学版), 2019, 54(5):8-20.
	[ Xu Y, Sun J Z, Huang L, et al. Trajectory model of area crowd based on WiFi positioning[J]. Journal of Shandong University (Natural Science), 2019, 54(5):8-20. ]
[15]	朱晨迪, 贾俊, 张斌, 等. 融合地图信息与 WiFi地标的室内粒子滤波定位算法[J]. 山东科技大学学报(自然科学版), 2020, 39(1):91-99.
	[ Zhu C D, Jia J, Zhang B, et al. Indoor particle filter positioning algorithm based on fusion of map information and WiFi landmark[J]. Journal of Shandong University of Science and Technology(Natural Science), 2020, 39(1):91-99. ]
[16]	高文超, 李国良, 塔娜. 路网匹配算法综述[J]. 软件学报, 2018, 29(2):225-250.
	[ Gao W C, Li G L, Ta N. Survey of map matching algorithms[J]. Journal of Software, 2018, 29(2):225-250. ]
[17]	Thiagarajan A, Ravindranath L, LaCurts K, et al. VTrack: accurate, energy-aware road traffic delay estimation using mobile phones[C]//Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems - SenSys '09. New York: ACM Press, 2009.
[18]	郑诗晨, 盛业华, 吕海洋. 基于粒子滤波的行车轨迹路网匹配方法[J]. 地球信息科学学报, 2020, 22(11):2109-2117. doi: 10.12082/dqxxkx.2020.190738
	[ Zheng S C, Sheng Y H, Lv H Y. Vehicle trajectory-map matching based on particle filter[J]. Journal of Geo-Information Science, 2020, 22(11):2109-2117. ]
[19]	Yang J H, Sun J A. Vehicle path reconstruction using automatic vehicle identification data: An integrated particle filter and path flow estimator[J]. Transportation Research Part C: Emerging Technologies, 2015, 58:107-126. doi: 10.1016/j.trc.2015.07.003
[20]	阮树斌, 王福建, 马东方, 等. 基于车牌识别数据的机动车出行轨迹提取算法[J]. 浙江大学学报(工学版), 2018, 52(5):836-844.
	[ Ruan S B, Wang F J, Ma D F, et al. Vehicle trajectory extraction algorithm based on license plate recognition data[J]. Journal of Zhejiang University (Engineering Science), 2018, 52(5):836-844. ]
[21]	Erceg V, Greenstein L J, Tjandra S Y, et al. An empirically based path loss model for wireless channels in suburban environments[J]. IEEE Journal on Selected Areas in Communications, 1999, 17(7):1205-1211. doi: 10.1109/49.778178

问题	描述	特征/例子
数据错误	信号源自身故障或环境干扰导致的终端MAC、时间、RSSI值错乱	终端MAC全为“0”或全为“F”时间属性缺失或记录错误RSSI为“-1”或小于-100
MAC随机跳变	部分苹果和华为的设备存在MAC码随机跳变情况	MAC码仅出现一次
“乒乓效应”	数据重复	终端处于2个或多个探针之间时,短时间内被重复检测到
固定设备干扰	不构成轨迹的设备如路由器、闲置的笔记本、手机平板等	长时间仅被个别探针重复检测到

探针的MAC地址	终端的MAC地址	时间戳	信号强度
00117F1B93CC	BCE******7E0	2020-07-09 09:20:50	-85
00117F14C3D4	BCE******7E0	2020-07-09 09:22:45	-80
00117F1B9584	BCE******7E0	2020-07-09 09:30:35	-76
……	……	……	……

轨迹	实际匹配长度	提取长度	提取正确	提取错误	未提取
一号轨迹	17 750	16 596	14 177	2419	3573
二号轨迹	11 324	10 727	10 727	0	597
三号轨迹	2634	2634	2634	0	0
四号轨迹	2940	2940	2940	0	0
五号轨迹	15 217	13 663	13 407	256	1810

重构点个数	重构次数/次	占比/%
1	234 826	70.50
2	55 073	16.53
3	24 915	7.48
4	10 083	3.03
≥5	8184	2.46

基于WiFi探针数据的城市出行轨迹提取

Urban Travel Trajectory Extraction based on WiFi Probe Data

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 1

Metrics

本文评价

推荐阅读 0