A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine

Qiang Shang,Ciyun Lin,Zhaosheng Yang,Xiyang Zhou,Qichun Bing,Zhaohong Deng

doi:10.1371/journal.pone.0161259

Qiang Shang, Ciyun Lin + Show 4 more

Open Access

https://doi.org/10.1371/journal.pone.0161259

Copy DOI

Journal: PloS one	Publication Date: Aug 23, 2016
Citations: 37	License type: CC BY 4.0

Affiliation: Jilin University

Abstract

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust.

Highlights

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS) [1,2]
Comparison results of the singular spectrum analysis (SSA)-Kernel Extreme Learning Machine (KELM) model, HPSO-SVR model and Long Short-Term Memory Neural Network (LSTM-NN) model show that the SSA-KELM model can further improve the accuracy of short-term traffic flow prediction
The main contributions of this paper are the introduction of KELM method for traffic flow prediction and how to optimize the model parameters based on gravitational search algorithm (GSA), and considering the chaotic characteristics of short-term traffic flow and determining the model’s optimal input form based on Phase Space Reconstruction (PSR)

Summary

Introduction

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS) [1,2]. Many subsystems of ITS such as Advanced Traffic Management System (ATMS) and Advanced Traveler Information Systems (ATIS) can benefit from improved prediction of traffic flow parameters (such as traffic volume, average traffic speed, and average occupancy) in a short-term future. Many researchers have paid more attention to short-term traffic flow prediction because of its importance. A large number of relevant methods have been published in the academic literature. These methods are categorized into three types [3,4]: traffic model-based methods, statistical methods and machine learning-based methods.

Objectives

Methods

Findings

Conclusion