Highlights A novel algorithm is proposed to forecast short-term traffic volume. Overlapping is avoided in selecting k-nearest neighbors. A linearly sewing principle component algorithm is developed. The new algorithm outperformed the competing algorithms in most cases.
Abstract To enhance the performance of the k-nearest neighbors approach in forecasting short-term traffic volume, this paper proposed and tested a two-step approach with the ability of forecasting multiple steps. In selecting k-nearest neighbors, a time constraint window is introduced, and then local minima of the distances between the state vectors are ranked to avoid overlappings among candidates. Moreover, to control extreme values’ undesirable impact, a novel algorithm with attractive analytical features is developed based on the principle component. The enhanced KNN method has been evaluated using the field data, and our comparison analysis shows that it outperformed the competing algorithms in most cases.
Short-term traffic volume forecasting: A k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm
Tramsportation Research, Part C: Emerging Technologies ; 43 ; 143-157
2014-02-13
15 pages
Article (Journal)
Electronic Resource
English
Short-term traffic flow forecasting method based on three-layer K nearest neighbor
European Patent Office | 2016
|A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting
Online Contents | 2016
|