The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

A Regional Trip Modes Classification Methodology Using Mobile Phone Data

모바일 데이터를 활용한 지역간 수단통행 분류 방법론 개발

  • Kyuhyuk Kim (Dept. of Urban Eng., Univ. of Chungbuk) ;
  • Hyorim Han (Dept. of Urban Eng., Univ. of Chungbuk) ;
  • Dongho Kim (Transport Big Data Division, The Korea Transport Institute) ;
  • Tai jin Song (Dept. of Urban Eng., Univ. of Chungbuk)
  • 김규혁 (충북대학교 도시공학과) ;
  • 한효림 (충북대학교 도시공학과) ;
  • 김동호 (한국교통연구원 교통빅데이터연구본부) ;
  • 송태진 (충북대학교 도시공학과)
  • Received : 2024.03.26
  • Accepted : 2024.07.17
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The recent development of data collection technology, which conveys various travel data in real-world such as mobile data and probe vehicle data, facilitates transportation planners identifying specified spatio-temporal travel patterns. In this study, an easily implementable travel mode classification methodology was proposed to classify inter-regional trip-modes without modeling by superimposing trajectories generated from mobile phone signaling and transportation infrastructure points into a polygon scale of a shapefile in a GIS system. Each regional mode trip was classified according to the rules such as the presence of transportation infrastructure in the trip trajectory, travel time, and the presence of access trips. An accuracy test generates Type I and Type II error results table to verify the proposed methodology. As a result, it was found that the methodology developed showed the F1-Score of the air mode 1.00, rail mode 0.95, bus mode 0.73.

최근 데이터 수집 기술의 발달은 모바일 데이터 등의 실제 통행이 반영된 데이터가 폭발적으로 증가시키며, 이러한 데이터들을 활용한 교통분야 연구 또한 촉진 시킨다. 본 연구에서는 모바일 데이터 궤적정보와 수단별 주요 교통유발시설 데이터를 매칭하여 모델링 없이 지역간 통행수단을 추정하는 방법론을 개발하였다. 개별 수단통행은 통행궤적 내 교통유발시설 유무, 통행시간, 접근통행 유무 등의 규칙에 따라 분류되었다. 서울, 청주에 거주하는 908명의 개별 통행궤적 데이터에 제안된 방법론을 적용하였고, 통행 다이어리 데이터의 기록된 수단과의 비교 결과를 Type I and II error 결과표로 나타내어 방법론의 정확도 검증을 수행하였다. 검증 결과, 본 연구에서 개발한 방법론은 항공수단 1.00, 철도수단 0.955, 버스수단 0.73 수준의 F1-Score를 보이는 것으로 나타났다.

Keywords

References

  1. Alam, M. G. R., Haque, M., Hassan, M. R., Huda, S., Hassan, M. M., Strickland, F. L. and AlQahtani, S. A.(2023), "Feature cloning and feature fusion based transportation mode detection using convolutional neural network", IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 4, pp.4671-4681. https://doi.org/10.1109/TITS.2023.3240500
  2. Anda, C., Erath, A. and Fourie, P. J.(2017), "Transport modelling in the age of big data", International Journal of Urban Sciences, vol. 21, no. sup1, pp.19-42. https://doi.org/10.1080/12265934.2017.1281150
  3. Andersson, A., Engelson, L., Borjesson, M., Daly, A. and Kristoffersson, I.(2022), "Long-distance mode choice model estimation using mobile phone network data", Journal of Choice Modelling, vol. 42, 100337.
  4. Bandyopadhyay, S., Datta, A., Ramakrishnan, R. K. and Pal, A.(2024), "Generalizable journey mode detection using unsupervised representation learning", IEEE Transactions on Intelligent Transportation Systems.
  5. Brandle, N.(2021), "Inferring modal split from mobile phones: Principles", Issues and Policy Recommendations.
  6. Breyer, N., Gundlegard, D. and Rydergren, C.(2021), "Travel mode classification of intercity trips using cellular network data", Transportation Research Procedia, vol. 52, pp.211-218. https://doi.org/10.1016/j.trpro.2021.01.024
  7. Bwambale, A., Choudhury, C. F., Hess, S. and Iqbal, M.(2021), "Getting the best of both worlds: A framework for combining disaggregate travel survey data and aggregate mobile phone data for trip generation modelling", Transportation, vol. 48, no. 5, pp.2287-2314. https://doi.org/10.1007/s11116-020-10129-5
  8. Chen, C., Bian, L. and Ma, J.(2014), "From traces to trajectories: how well can we guess activity locations from mobile phone traces?", Transportation Research Part C: Emerging Technologies, vol. 46, pp.326-337. https://doi.org/10.1016/j.trc.2014.07.001
  9. Chen, C., Ma, J., Susilo, Y., Liu, Y. and Wang, M.(2016), "The promises of big data and small data for travel behavior (aka human mobility) analysis", Transportation Research Part C: Emerging Technologies, vol. 68, pp.285-299. https://doi.org/10.1016/j.trc.2016.04.005
  10. Cho, S. H., Seo, Y. H., Kho, S. Y. and Rhee, S. M.(2017), "Estimation of interregional mode choice models and value of travel time accommodating taste variation of individuals", Journal of the Korean Society for Railway, vol. 20, no. 2, pp.288-298. https://doi.org/10.7782/JKSR.2017.20.2.288
  11. Currans, K. M. and Clifton, K. J.(2015), "Using household travel surveys to adjust ITE trip generation rates", Journal of Transport and Land Use, vol. 8, no. 1, pp.85-119. https://doi.org/10.5198/jtlu.2015.470
  12. Doyle, J., Hung, P., Kelly, D., McLoone, S. F. and Farrell, R.(2011), Utilising mobile phone billing records for travel mode discovery.
  13. Engelson, L.(2021), Long-distance mode choice model estimation using mobile phone network data.
  14. Eromietse, E. J. and Joseph, O. O.(2019), "Comparative assessment of radial basis function neural network and multiple linear regression application to trip generation modelling in Akure Nigeria", International Journal for Traffic & Transport Engineering, vol. 9, no. 2, pp.163-176. https://doi.org/10.7708/ijtte.2019.9(2).03
  15. Etu, J. E. and Oyedepo, O. J.(2018), "Forecasting trip generation for high density residential zones of Akure, Nigeria: Comparability of artificial neural network and regression models", Journal of Civil Engineering, Science and Technology, vol. 9, no. 2, pp.76-86. https://doi.org/10.33736/jcest.988.2018
  16. Fourez, T., Verstaevel, N., Migeon, F., Schettini, F. and Amblard, F.(2023), Transport mode detection on GPS and accelerometer data: A temporality based workflow.
  17. Jiang, S., Ferreira, J. and Gonzalez, M. C.(2017), "Activity-based human mobility patterns inferred from mobile phone data: A case study of Singapore", IEEE Transactions on Big Data, vol. 3, no. 2, pp.208-219. https://doi.org/10.1109/TBDATA.2016.2631141
  18. Jun, S. H.(2011), "A new statistical sampling method for reducing computing time of machine learning algorithms", Journal of The Korean Institute of Intelligent Systems, vol. 21, no. 2, pp.171-177. https://doi.org/10.5391/JKIIS.2011.21.2.171
  19. Kalatian, A. and Shafahi, Y.(2016), "Travel mode detection exploiting cellular network data", In MATEC Web of Conferences, EDP Sciences, vol. 81, 03008.
  20. Kim, J. Y., Kim, S. J., Lee, G. J. and Choo, S. H.(2021a) "Estimating a mode choice model considering shared E-scooter service-Focused on access travel and neighborhood travel", The Journal of Korea Institute of Intelligent Transport Systems, vol. 20, no. 1, pp.22-39. https://doi.org/10.12815/kits.2021.20.1.22
  21. Kim, K. H., Lee, D. Y., Kim, D. H., Won, M. S., Hong, S. M. and Song, T. J.(2021b), "A study on the classification and understanding of travel boundary by city population scale based on mobile travel data", Journal of Korean Society of Transportation, vol. 39, no. 5, pp.662-680. https://doi.org/10.7470/jkst.2021.39.5.662
  22. Lee, G. J. and Choe, G. J.(2010), "A bike mode share estimation model and analysis of the bike demand factor effects", Journal of Korean Society of Transportation, vol. 28, no. 3, pp.145-155.
  23. Phithakkitnukoon, S., Sukhvibul, T., Demissie, M., Smoreda, Z., Natwichai, J. and Bento, C.(2017), "Inferring social influence in transport mode choice using mobile phone data", EPJ Data Science, vol. 6, pp.1-29. https://doi.org/10.1140/epjds/s13688-016-0097-x
  24. Qu, Y., Gong, H. and Wang, P.(2015), "Transportation mode split with mobile phone data", In 2015 IEEE 18th international conference on intelligent transportation systems, IEEE, September, pp.285-289.
  25. Ryu, S. K., Rho, J. H. and Kim, J. E.(2012), "A study on the modal split model using zonal data", Journal of Korean Society of Transportation, vol. 30, no. 1, pp.113-123. https://doi.org/10.7470/jkst.2012.30.1.113
  26. Sadeghvaziri, E., Rojas IV, M. B. and Jin, X.(2016), "Exploring the potential of mobile phone data in travel pattern analysis", Transportation Research Record, vol. 2594, no. 1, pp.27-34. https://doi.org/10.3141/2594-04
  27. Shin, K.(2014), "Improving methods for estimating transportation mode choice model in Busan-Ulsan metropolitan area", Journal of the Korea Academia-Industrial cooperation Society, vol. 15, no. 7, pp.4580-4587. https://doi.org/10.5762/KAIS.2014.15.7.4580
  28. Toole, J. L., Ulm, M., Gonzalez, M. C. and Bauer, D.(2012), "Inferring land use from mobile phone activity", In Proceedings of the ACM SIGKDD International Workshop on Urban Computing, August, pp.1-8.
  29. Wang, H., Calabrese, F., Di Lorenzo, G. and Ratti, C.(2010), "Transportation mode inference from anonymized and aggregated mobile phone call detail records", In 13th International IEEE Conference on Intelligent Transportation Systems, IEEE, September, pp.318-323.
  30. Won, M., Choi, J., Lee, H. and Kim, J.(2021), "Development of an algorithm to analyze home-based work trips using mobile phone data", Journal of Korean Society of Transportation, vol. 39, no. 3, pp.383-398. https://doi.org/10.7470/jkst.2021.39.3.383
  31. Xu, D., Song, G., Gao, P., Cao, R., Nie, X. and Xie, K.(2011), "Transportation modes identification from mobile phone data using probabilistic models", In International Conference on Advanced Data Mining and Applications, Springer, Berlin, Heidelberg, December, pp.359-371.