Short-Term Traffic Forecasting Using Self-Adjusting k-Nearest Neighbours

Short-term traffic forecasting is becoming more important in intelligent transportation systems. The k-nearest neighbours (kNN) method is widely used for short-term traffic forecasting. However, the self-adjustment of kNN parameters has been a problem due to dynamic traffic characteristics. This paper proposes a fully automatic dynamic procedure kNN (DP-kNN) that makes the kNN parameters self-adjustable and robust without predefined models or training for the parameters. A real-world dataset with more than one year traffic records is used to conduct experiments. The results show that DP-kNN can perform better than manually adjusted kNN and other benchmarking methods in terms of accuracy on average. This study also discusses the difference between holiday and workday traffic prediction as well as the usage of neighbour distance measurement.