Abstract: Future traffic volume is one of crucial elements in the area of advanced traffic signal control for intelligent transportation systems (ITS). Unfortunately, the temporal development of the urban traffic volume, i.e. the urban traffic volume (UTV), shows rapidly intensive fluctuations in nature. This is inevitably or frequently related to the well-known forecasting failure in the ITS forecast modeling. Despite the several remarkable achievements of single-interval UTV forecasting in the literature, it remains one of the major challenges when predicting reliable multi-interval UTVs for more proactive and tactical traffic signal operations. On the other hand, data-driven, knowledge discovery approaches.......
Key Word: Big data; Urban traffic flow; Advanced data management system; K-nearest neighbor non-parametric regression; Multi-interval forecasting
[1]. Altman, N.S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46, 175-185.
[2]. Cai, P., Wang, Y., Lu, G., Chen, P., Ding, C., and Sun, J. (2016). A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting. Transportation Research Part C, 10.1016/j.trc.2015.11.002, 62, 21-34.
[3]. Chang, H., Park, D., Lee, S., Lee, H., and Baek, S. (2010). Dynamic multi-interval bus travel time prediction using bus transit data. Transportmetrica, 6(1), 19-38.
[4]. Chang, H., Seong, J.N., Lee, Y., and Yoon, B. (2011). Dynamic freeway path travel time prediction based on nonparametric regression approach using dedicated short-range communications data. Proc. 90th Annual Meeting of Transportation Research Board, Washington, DC, 2011.
[5]. Chang, H., Park, D., Lee, Y., and Yoon, B. (2012a). Multiple time period imputation technique for multiple missing traffic variables: nonparametric regression approach. Canadian Journal of Civil Engineering, 39, 448-459
