Prediction Model of Traffic Flow Driven Based on Single Data in Smart Traffic Systems
- 25 Downloads
The traffic flow series is a typical time series with some time-varying rules. Because the living and working hours of the house have certain rules, the traffic flow series has a strong periodic variation law. Deterministic predictions can more accurately find the change values of traffic flows, while interval predictions can find the range of changes in traffic flows. Both prediction methods play an important role in improving intelligent transportation systems. In this chapter, traffic flow prediction models are built using historical data from the traffic flow series. The models are divided into the deterministic prediction model and interval prediction model, which are composed of BP prediction model, WD-BP prediction model, BP-GARCH interval prediction model, and WD-BP-GARCH interval prediction model. It can be seen from the experimental results that the predictive performance of the WD-BP predictive model is higher than the BP predictive model in the deterministic forecast of traffic flow. In the interval prediction of traffic flow, BP neural network is used to establish a deterministic prediction model, and the GARCH model is used to calculate the uncertainty of forecasting traffic flow.
- Bernardo, D., Hagras, H., & Tsang, E. (2012). An interval type-2 fuzzy logic system for the modeling and prediction of financial applications. In International conference on autonomous and intelligent systems (pp. 95–105). Springer.Google Scholar
- El-Fouly T, El-Saadany E, Salama M (2006) One day ahead prediction of wind speed using annual trends. In: 2006 IEEE power engineering society general meeting. IEEEGoogle Scholar
- Li J, Cheng J-H, Shi J-Y, Huang F (2012) Brief introduction of back propagation (BP) neural network algorithm and its improvement. In: Advances in computer science and information engineering. Springer, pp 553–558Google Scholar
- Shvachko K, Kuang H, Radia S, Chansler R (2010) The Hadoop distributed file system. 2010. In: IEEE 26th symposium on mass storage systems and technologies (MSST). IEEE, pp 1–10Google Scholar
- Wu Y, Tan H, Qin L, Ran B, Jiang Z (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transportation Research Part C: Emerging Technologies 90:166–180. http://www.sciencedirect.com/science/article/pii/S0968090X18302651CrossRefGoogle Scholar