Abstract：[Objective] Urban traffic is a vital factor in determining urban competitiveness, which is an essential aspect of determining urban vitality and crucial for improving urban livability. With the increasing demand for urban motorized travel, traffic conflicts and low road efficiency have become more evident in the central parts of cities. These issues hinder the successful development of the city and affect the quality of life of the residents. By further elucidating and analyzing the travel characteristics of different regions, we can implement targeted strategies to improve traffic conflicts, maintain road order, and enhance road efficiency and safety. [Methods] This paper proposes a transportation mode detection method based on signaling data to formulate travel policies to help mid-sized cities for realizing green and sustainable development. The proposed method considers the characteristics of signaling data in mid-sized cities. This paper analyzes the possible range of the traveling time and distance. Moreover, when exploring travel characteristics, the proposed method does not directly trust the signaling timestamp and does not directly use the Euclidean distance between base stations. It neither uses the shortest distance in the road network nor the road network distance based on a certain mapping rule. The traveling speed range is determined according to the base station positioning principle and information reporting mechanism. The map application programming interface (API) is used to obtain the speed of different traffic modes, accurately achieve the travel characteristics of the residents, and formulate targeted policies. When using the map API, the travel strategy of residents, traffic flow information, and network structure are considered. The detection is completed by the speed interval adjustment and the Logit model based on the travel time reliability perception. The limitations of positioning accuracy and time granularity make it a challenging task to mine and verify the characteristics. However, introducing multisource data when the standard dataset has not yet been constructed helps address this issue. [Results] The study used air pollutant emission data and intersection flow data to verify the mode detection results of large-scale areas rather than using only the official mode share statistics for verification. Then the transport modes detection method was used to analyze the travel structure of the central area in Jingzhou. The method could effectively detect transportation modes by extending temporal, and spatial information by considering the road network, and travel strategies of the residents. [Conclusions] The results demonstrate that during peak hours, the high traffic demand of schools and the concentrated parking contradiction around hospitals aggravate traffic congestion. It is necessary to strengthen the traffic organization and management of the academic and medical circles to reduce emissions in the low-speed driving stage of motor vehicles. The attraction of traditional public transportation during peak hours is insufficient, and the local conditions for opening demand-responsive buses are available. The inevitable increase in population will attract more residents who initially used individualized motorized traffic. People have a clear preference for transportation when the origin and destination are the same (interval distance of approximately 3 km) and the travel time of individual motorized travel and cycling is close. Appropriate sharing of nonmotor vehicles, along with traffic organization and management, can encourage specific groups to use nonmotor vehicles.
吕远, 葛浩菁, 焦朋朋. 基于信令数据的中等城市绿色出行政策建议[J]. 清华大学学报（自然科学版）, 2023, 63(11): 1719-1728.
LÜ Yuan, GE Haojing, JIAO Pengpeng. Policy recommendations for green travel in medium cities based on signaling data. Journal of Tsinghua University(Science and Technology), 2023, 63(11): 1719-1728.
[1] HUANG H S, CHENG Y, WEIBEL R. Transport mode detection based on mobile phone network data:A systematic review[J]. Transportation Research Part C:Emerging Technologies, 2019, 101(4):297-312. [2] ZHU L, YU F R, WANG Y G, et al. Big data analytics in intelligent transportation systems:A survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(1):383-398. [3] GADZINŃSKI J. Perspectives of the use of smartphones in travel behaviour studies:Findings from a literature review and a pilot study[J]. Transportation Research Part C:Emerging Technologies, 2018, 88(5):74-86. [4] BURKHARD O, BECKER H, WEIBEL R, et al. On the requirements on spatial accuracy and sampling rate for transport mode detection in view of a shift to passive signalling data[J]. Transportation Research Part C:Emerging Technologies, 2020, 114(5):99-117. [5] QU Y C, GONG H, WANG P. Transportation mode split with mobile phone data[C]//Proceedings of 2015 IEEE 18th International Conference on Intelligent Transportation Systems. Gran Canaria, Spain:IEEE, 2015:285-289. [6] YAMADA Y, UCHIYAMA A, HIROMORI A, et al. Travel estimation using control signal records in cellular networks and geographical information[C]//Proceedings of 20169th IFIP Wireless and Mobile Networking Conference. Colmar, France:IEEE, 2016:138-144. [7] PHITHAKKITNUKOON S, SUKHVIBUL T, DEMISSIE M, et al. Inferring social influence in transport mode choice using mobile phone data[J]. EPJ Data Science, 2017, 6(1):11. [8] PENG Z H, BAI G K, WU H, et al. Travel mode recognition of urban residents using mobile phone data and map API[J]. Environment and Planning B:Urban Analytics and City Science, 2021, 48(9):2574-2589. [9] GU M C, SUN S, JIAN F, et al. Analysis of changes in intercity highway traffic travel patterns under the impact of COVID-19[J]. Journal of Advanced Transportation, 2021, 2021(1):7709555. [10] DANAFAR S, PIORKOWSKI M, KRYSCZCUK K. Bayesian framework for mobility pattern discovery using mobile network events[C]//Proceedings of 201725th European Signal Processing Conference. Kos, Greece:IEEE, 2017:1070-1074. [11] SUN H D, CHEN Y Y, WANG Y, et al. Trip purpose inference for tourists by machine learning approaches based on mobile signaling data[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(2):923-937. [12] CHEN J T, XIONG C, CAI M. A travel mode identification framework based on cellular signaling data[J]. Mobile Information Systems, 2022, 4:1-19. [13] CHEN X X, WAN X, LI Q, et al. Trip-chain-based travel-mode-shares-driven framework using cellular signaling data and web-based mapping service data[J]. Transportation Research Record:Journal of the Transportation Research Board, 2019, 2673(3):51-64. [14] ZHAO P J, LIU D, YU Z, et al. Long commutes and transport inequity in China's growing megacity:New evidence from Beijing using mobile phone data[J]. Travel Behaviour and Society, 2020, 20(7):248-263. [15] AGUILÉRA V, ALLIO S, BENEZECH V, et al. Using cell phone data to measure quality of service and passenger flows of Paris transit system[J]. Transportation Research Part C:Emerging Technologies, 2014, 43:198-211. [16] 朱顺应,邓爽,王红,等.具有模糊特性变量的出行方式预测Logit模型[J].交通运输工程学报, 2013, 13(3):71-78. ZHU S Y, DENG S, WANG H, et al. Predictive LOGIT model of trip mode with fuzzy attribute variables[J]. Journal of Traffic and Transportation Engineering, 2013, 13(3):71-78.(in Chinese) [17] 荆州市人民政府.荆州市城市综合交通体系规划(2015-2030)[R/OL].(2015-09-25)[2022-09-17]. http://www.jingzhou.gov.cn. Jingzhou Municipal People's Government. Comprehensive transportation system planning of Jingzhou city (2015-2030)[R/OL].(2015-09-25)[2022-09-17]. http://www.jingzhou.gov.cn.(in Chinese) [18] ZHAI Z Q, SONG G H, LIU Y, et al. Characteristics of operating mode distributions of light duty vehicles by road type, average speed, and driver type for estimating on-road emissions:Case study of Beijing[J]. Journal of Intelligent Transportation Systems, 2019, 23(2):191-202. [19] 生态环境部.关于发布《大气可吸入颗粒物一次源排放清单编制技术指南(试行)》等5项技术指南的公告[EB/OL].(2014-12-31)[2022-09-17]. https://www.mee.gov.cn/gkml/hbb/bgg/201501/t20150107_293955.htm. Ministry of Ecological Environment of the People's Republic of China. Technical guidelines for the preparation of air pollutant emission inventory for road vehicles (trial)[EB/OL].(2014-12-31)[2022-09-17]. https://www.mee.gov.cn/gkml/hbb/bgg/201501/t20150107_293955.htm.(in Chinese) [20] 荆州市生态环境局. 2020年荆州市生态环境统计公报[R/OL].(2022-04-25)[2022-09-17]. http://sthjj.jingzhou.gov.cn/fbjd/xxgkml/hjgh/202204/t20220425_723263.shtml. Jingzhou Municipal Ecological Environment Bureau. 2020 Jingzhou city ecological environment statistical bulletin[R/OL].(2022-04-25)[2022-09-17]. http://sthjj.jingzhou.gov.cn/fbjd/xxgkml/hjgh/202204/t20220425_723263.shtml.(in Chinese)
2023, Vol. 63 
