A Special Event-Based K-Nearest Neighbor Model for Short-Term Traffic State Prediction

Haiyang Yu,Nan Ji,Can Yang,Yilong Ren

doi:10.1109/access.2019.2923663

Abstract

Recently, short-term traffic state prediction for urban transportation networks has become a popular topic. However, due to the uncontrollable and unpredictable elements of special events, it is difficult to get abundant data and desired predictions under such condition. As k-nearest neighbor (KNN) has a competitive advantage over other approaches, it could predict traffic state based on a small correlative part of data. Thus, a special event-based KNN (SEKNN) model is proposed for the short-term traffic state prediction with three key points presented in this paper. First, the evolution of the traffic states is redefined as a multipart object, state unit, which includes the benchmark state and the trend vector. Second, to select the nearest neighbors, the state distances of the state units are designed to be compatible with the benchmark states and the trend vectors by fusing the Euclidean distance and the cosine distance. Finally, the prediction results are forced to adjust the benchmark states based on the prediction function using the Gaussian weighted method. The proposed SEKNN is implemented in the district of the Beijing Workers' Stadium (257 links), where special events occur frequently. The results show that the proposed model performs significantly better under special events than the other traditional machine-learning approaches and state-of-the-art deep-learning approaches.

Highlights

Traffic state prediction contributes to foreknowledge of the variation of traffic states on different future time scales, from minutes to hours or even days
This study suggests a problem that is mentioned in other studies [37]: deep learning approaches rely heavily on feeding a great quantity of high-quality training data; otherwise, the model will probably face the problem of overfitting
special event-based KNN (SEKNN) is improved based on the original k-nearest neighbor (KNN) in all three basic elements around network-wide traffic state evolution, including the multiapart state unit, a novel distance metric and prediction function

Summary

Introduction

Traffic state prediction contributes to foreknowledge of the variation of traffic states on different future time scales, from minutes to hours or even days. Short-term traffic state prediction is a vital real-time decision-making tool of intelligent transportation systems for traffic managers and travelers who must make decisions in minutes. In intelligent transportation systems, advanced traffic management systems and advanced traveler information systems depend on timely and accurate predictions of traffic states. In addition to traffic accidents, adverse weather and land closures, special events refer to important unexpected events or incidents that cause nonrecurrent congestion [1].

Objectives

Methods

Findings

Conclusion