Estimation Method of Traffic Volume Using Big-Data
Traffic jams have recently become a significant problem in provincial cities that tend to have poor railway services in Japan. Therefore, the main means of transportation are public buses, taxies, and private vehicles. Moreover, traffic accidents and road construction sites frequently block traffic. It is therefore difficult to estimate the travelling time from the origin to destination in real-time. To estimate the travelling time, we must predict the behaviors of many vehicles that depend on an “origin to destination” (OD) traffic volume. In our previous study, we proposed an estimation method for OD traffic volume using two types of big data, a road traffic census and mobile spatial statistics. In this study, we evaluated our proposed method on various situations through a traffic simulation.
This work was supported by JSPS KAKENHI Grant No. 16K00433. Data on the Mobile Spatial Statistics in Kanazawa and Nonoichi were provided by NTT DoCoMo.
- 1.MILT: International visitor survey. http://www.mlit.go.jp/kankocho/en/siryou/toukei/syouhityousa.html
- 2.Uesaka, K., Monma, T., Matsumoto, S., Hashimoto, H., Mizuki, T.: The FY2010 Road Traffic Census Results of the General Traffic Volume Surveys (Overview). www.nilim.go.jp/english/annual/annual2012/84.pdf
- 3.Murase, A.: How mobile spatial statistics Began. NTT Docomo J. 14(3), 1Google Scholar
- 6.Akagi, Y., Nishimura, T., Kurashima, T., Toda, H.: A fast and accurate method for estimating people flow from spatiotemporal population data. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) (2018)Google Scholar
- 7.NTT DoCoMo: AI Bus. https://www.itsap-fukuoka.jp/demo/AI_Bus.html
- 8.Nakashima, H., Sano, S., Hirata, K., Shiraishi, Y., Matsubara, H., Kanamori, R., Koshiba, H., Noda, I.: One cycle of smart access vehicle service developmentGoogle Scholar
- 10.Open Street Map Japan. https://openstreetmap.jp