Forecasting Traffic Flow in Big Cities Using Modified Tucker Decomposition
An efficient traffic-network is an essential demand for any smart city. Usually, city traffic forms a huge network with millions of locations and trips. Traffic flow prediction using such large data is a classical problem in intelligent transportation system (ITS). Many existing models such as ARIMA, SVR, ANN etc, are deployed to retrieve important characteristics of traffic-network and for forecasting mobility. However, these methods suffer from the inability to handle higher data dimensionality. The tensor-based approach has recently gained success over the existing methods due to its ability to decompose high dimension data into factor components. We present a modified Tucker decomposition method which predicts traffic mobility by approximating very large networks so as to handle the dimensionality problem. Our experiments on two big-city traffic-networks show that our method reduces the forecasting error, for up to 7 days, by around 80% as compared to the existing state of the art methods. Further, our method also efficiently handles the data dimensionality problem as compared to the existing methods.
KeywordsODM CP decomposition Tucker Time-series CUR Traffic flow
This work is funded by Project “TEC4Growth - Pervasive Intelligence, Enhancers and Proofs of Concept with Industrial Impact/NORTE-01-0145-FEDER-000020”, a project financed by North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement.
- 1.Ahn, J.Y., Ko, E., Kim, E.: Predicting spatiotemporal traffic flow based on support vector regression and Bayesian classifier. In: 2015 IEEE Fifth International Conference on Big Data and Cloud Computing (BDCloud), pp. 125–130. IEEE (2015)Google Scholar
- 2.Bhanu, M., Chandra, J., Mendes-Moreira, J.: Enhancing traffic model of big cities: network skeleton & reciprocity. In: 2018 10th International Conference on Communication Systems & Networks (COMSNETS), pp. 121–128. IEEE (2018)Google Scholar
- 4.Gabrielli, L., Rinzivillo, S., Ronzano, F., Villatoro, D.: From tweets to semantic trajectories: mining anomalous urban mobility patterns. In: Nin, J., Villatoro, D. (eds.) CitiSens 2013. LNCS (LNAI), vol. 8313, pp. 26–35. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-04178-0_3CrossRefGoogle Scholar
- 6.Jun, M., Ying, M.: Research of traffic flow forecasting based on neural network. In: Second International Symposium on Intelligent Information Technology Application, IITA 2008, vol. 2, pp. 104–108. IEEE (2008)Google Scholar
- 11.Lv, Y., Duan, Y., Kang, W., Li, Z., Wang, F.-Y.: Traffic flow prediction with big data: a deep learning approach. IEEE Trans. Intell. Transp. Syst. 16(2), 865–873 (2015)Google Scholar
- 12.Priya, S., Bhanu, M., Dandapat, S.K., Ghosh, K., Chandra, J.: Characterizing infrastructure damage after earthquake: a split-query based IR approach. In: 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 202–209. IEEE (2018)Google Scholar
- 13.Ren, J., Xie, Q.: Efficient OD trip matrix prediction based on tensor decomposition. In: 2017 18th IEEE International Conference on Mobile Data Management (MDM), pp. 180–185. IEEE (2017)Google Scholar
- 14.Sun, S., Zhang, C., Zhang, Y.: Traffic flow forecasting using a spatio-temporal bayesian network predictor. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005 Part II. LNCS, vol. 3697, pp. 273–278. Springer, Heidelberg (2005). https://doi.org/10.1007/11550907_43CrossRefGoogle Scholar