|Table of Contents|

Empirical evaluation of travel survey based on mobile phone sensor data(PDF)

《交通运输工程学报》[ISSN:1671-1637/CN:61-1369/U]

Issue:
2020年01期
Page:
226-238
Research Field:
交通信息工程及控制
Publishing date:

Info

Title:
Empirical evaluation of travel survey based on mobile phone sensor data
Author(s):
YANG Fei1;  GUO Yu-dong1;  JIN J P2;  WU Hai-tao1
(1. School of Transportation and Logistics, Southwest Jiaotong University, Chengdu 610031, Sichuan, China; 2. Department of Civil and Environmental Engineering, Rutgers University, Piscataway 08854, New Jersey, USA)
Keywords:
traffic information;  mobile phone sensor;  spatio-temporal clustering algorithm;  support vector machine;  travel characteristics;  questionnaire
PACS:
U491.1
DOI:
10.19818/j.cnki.1671-1637.2020.01.019
Abstract:
The mobile phone sensor and questionnaire were used to collect the real travel trajectories of college students on campus for 2 weeks. The characteristics of mobile phone sensor data in real travel environment were considered, and the Gaussian filter was applied to pre-process the data. According to the spatio-temporal clustering characteristics of trajectory points, the travel endpoints and travel times were identified by spatio-temporal clustering algorithm. Based on the characteristics of velocity and acceleration of trajectory points, the travel modes were identified by using support vector machine. Comparing the data of mobile phone sensor with the data of questionnaire and screen line, the accuracies of travel feature recognition of mobile phone sensor data were analyzed, and the extraction effect of travel feature was verified. Analysis result shows that the matching degree of travel chain between the mobile phone sensor and questionnaire is 81.66%, which indicates that mobile phone sensor data can effectively record the travel trajectory. When the spatial radius of the core point is 26.92 m, the minimum sample points are 129, and the time constraint is 129 s in the parameters of the spatio-temporal clustering algorithm, the travel endpoint and travel time identification accuracy are 93.02% and 90.84%, respectively, which indicates that the mobile phone sensor can identify the travel endpoint and travel time effectively. The accuracy of travel mode identification is 89.86% when the support vector machine type is classical, the kernel function is radial basis function, the penalty coefficient is 0.797, and the kernel parameter is 2.260, which indicates that mobile phone sensor can effectively identify the travel modes. Therefore, the recognition result of mobile phone sensor data is reasonable, which can support the application of mobile phone sensor data in actual travel survey. 8 tabs, 12 figs, 31 refs.

References:

[1] MURAKAMI E, WAGNER D P. Can using global positioning system(GPS)improve trip reporting?[J]. Transportation Research Part C: Emerging Technologies, 1999, 7(2/3): 149-165.
[2] WOLF J. Using GPS data loggers to replace travel diaries in the collection of travel data[D]. Atlanta: Georgia Institute of Technology, 2000.
[3] BOHTE W, MAAT K. Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: a large-scale application in the Netherlands[J]. Transportation Research Part C: Emerging Technologies, 2009, 17(3): 285-297.
[4] FENG Tao, TIMMERMANS H J P. Transportation mode recognition using GPS and accelerometer data[J]. Transportation Research Part C: Emerging Technologies, 2013, 37: 118-130.
[5] AULD J, WILLIAMS C, MOHAMMADIAN A, et al. An automated GPS-based prompted recall survey with learning algorithms[J]. Transportation Letters, 2008, 1(1): 59-79.
[6] BIERLAIRE M, CHEN Jing-min, NEWMAN J. A probabilistic map matching method for smartphone GPS data[J]. Transportation Research Part C: Emerging Technologies, 2013, 26: 78-98.
[7] OLIVEIRA M G S, VOVSHA P, WOLF J, et al. Evaluation of two methods for identifying trip purpose in GPS-based household travel surveys[J]. Transportation Research Record, 2014, 2406: 33-41.
[8] GEURS K T, THOMAS T, BIJLSMA M, et al. Automatic trip and mode detection with move smarter: first results from the dutch mobile mobility panel[J]. Transportation Research Procedia, 2015, 11: 247-262.
[9] 冉 斌.手机数据在交通调查和交通规划中的应用[J].城市交通,2013,11(1):72-81,32. RAN Bin. Use of cellphone data in travel survey and transportation planning[J]. Urban Transport of China, 2013, 11(1): 72-81, 32.(in Chinese)
[10] FENG Yi-heng, HOURDOS J, DAVIS G A. Probe vehicle based real-time traffic monitoring on urban roadways[J]. Transportation Research Part C: Emerging Technologies, 2014, 40: 160-178.
[11] 吴子啸,任西锋,胡静宇.基于公交GPS和IC卡数据的综合交通建模新思路[J].城市交通,2011,9(1):47-51. WU Zi-xiao, REN Xi-feng, HU Jing-yu. Comprehensive transportation modeling with information from GPS and IC card on public transit vehicles[J]. Urban Transport of China, 2011, 9(1): 47-51.(in Chinese)
[12] 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 Xin, SUN Mao-peng, SUN Hao. Taxi commute recognition and temporal-spatial characteristics analysis based on GPS data[J]. China Journal of Highway and Transport, 2017, 30(7): 134-143.(in Chinese)
[13] 杨 飞,姚振兴.基于手机传感器数据的出行特征提取方法[J].城市交通,2016,14(1):9-14. YANG Fei, YAO Zhen-xing. Travel characteristics extracting method by smartphone sensor data [J]. Urban Transport of China, 2016, 14(1): 9-14.(in Chinese)
[14] 戴 露.基于手机GPS数据的出行端点识别方法研究[D].成都:西南交通大学,2017. DAI Lu. Research on extraction method of trip end based on cellphone GPS data[D]. Chengdu: Southwest Jiaotong University, 2017.(in Chinese)
[15] 韩 旭.基于手机加速度传感器数据的交通出行方式识别方法研究[D].成都:西南交通大学,2016. HAN Xu. Research of travel mode recognition method based on cellphone accelerometer data[D]. Chengdu: Southwest Jiaotong University, 2016.(in Chinese)
[16] 赵 瑜.不同交通状态下基于手机GPS轨迹的出行信息采集效果评估研究[D].成都:西南交通大学,2016. ZHAO Yu.Research on evaluation of acquisition effect of travel information based on cellphone GPS trajectory under different traffic states[D]. Chengdu: Southwest Jiaotong University, 2016.(in Chinese)
[17] BROACH J, DILL J, MCNEIL N W. Travel mode imputation using GPS and accelerometer data from a multi-day travel survey[J]. Journal of Transportation Geography, 2019, 78: 194 -204.
[18] 曾大堃.手机GPS定位频率对交通出行信息提取精度的影响研究[D].成都:西南交通大学,2016. ZENG Da-kun. Research on impact of the logging frequency of cellphone GPS on the extration accuracy of travel information [D]. Chengdu: Southwest Jiaotong University, 2016.(in Chinese)
[19] YANG Fei, YAO Zhen-xing, JIN J P. GPS and acceleration data in multimode trip data recognition based on wavelet transform modulus maximum algorithm[J]. Transportation Research Record, 2015, 2526: 90-98.
[20] GONG Lei, KANAMORI R, YAMAMOTO T. Data selection in machine learning for identifying trip purposes and travel modes from longitudinal GPS data collection lasting for seasons[J]. Travel Behaviour and Society, 2018, 11: 131-140.
[21] ASSEMI B, SAFI H, MESBAH M, et al. Developing and validating a statistical model for travel mode identification on smartphones[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(7): 1920-1931.
[22] REHRL K, BRUNAUER R, GRÖCHENIG S. Collecting floating car data with smartphones: results from a field trial in Austria[J]. Journal of Location Based Services, 2016, 10(1): 16-30.
[23] MARRA A D, BECKER H, AXHAUSEN K W, et al. Developing a passive GPS tracking system to study long-term travel behavior[J]. Transportation Research Part C: Emerging Technologies, 2019, 104: 348-368.
[24] CISCAL-TERRY W, DELL'AMICO M, HADJIDIMITRIOU N S, et al. An analysis of drivers route choice behaviour using GPS data and optimal alternatives[J]. Journal of Transport Geography, 2016, 51: 119-129.
[25] PETRONEA, FRANZ M L. Probe vehicle based trajectory data visualization and applications[J]. International Journal of Transportation, 2018, 6(1): 59-74.
[26] BORIO D, CANO E, BALDINI G. Speed consistency in the smart tachograph[J]. Sensors, 2018, 18(5): 1-21.
[27] CHEN C, GONG H, LAWSON C, et al. Evaluating the feasibility of a passive travel survey collection in a complex urban environment: lessons learned from the New York City case study[J]. Transportation Research Part A: Policy and Practice, 2010, 44(10): 830-840.
[28] 张国云.支持向量机算法及其应用研究[D].长沙:湖南大学,2006. ZHANG Guo-yun. Research on support vector machine algorithm and its application[D]. Changsha: Hunan University, 2006.(in Chinese)
[29] 李 晔.基于一种改进遗传算法的神经网络[D].太原:太原理工大学,2007. LI Ye.Neural network based on improved genetic algorithm[D]. Taiyuan: Taiyuan University of Technology, 2007.(in Chinese)
[30] ERHARDT G D, RIZZO L. Evaluating the biases and sample size implications of multi-day GPS-enabled household travel surveys[J]. Transportation Research Procedia, 2018, 32: 279-290.
[31] 卫 宇.考虑地球曲率情况下两点距离问题的求解[J].航空兵器,2008(3):7-12. WEI Yu. Solution of distance between two points considering curvature of the earth[J]. Aero Weapon, 2008(3): 7-12.(in Chinese)

Memo

Memo:
-
Last Update: 2020-03-24