Distance-To-Mean Continuous Conditional Random Fields: Case Study in Traffic Congestion

Sumarsih C Purbarani,Wisnu Jatmiko,Hadaiq R Sanabila,Ari Wibisono,Hanif A Wisesa,Noverina Alfiany

doi:10.3390/info10120382

Abstract

Traffic prediction techniques are classified as having parametric, non-parametric, and a combination of parametric and non-parametric characteristics. The extreme learning machine (ELM) is a non-parametric technique that is commonly used to enhance traffic prediction problems. In this study, a modified probability approach, continuous conditional random fields (CCRF), is proposed and implemented with the ELM and then utilized to assess highway traffic data. The modification is conducted to improve the performance of non-parametric techniques, in this case, the ELM method. This proposed method is then called the distance-to-mean continuous conditional random fields (DM-CCRF). The experimental results show that the proposed technique suppresses the prediction error of the prediction model compared to the standard CCRF. The comparison between ELM as a baseline regressor, the standard CCRF, and the modified CCRF is displayed. The performance evaluation of the techniques is obtained by analyzing their mean absolute percentage error (MAPE) values. DM-CCRF is able to suppress the prediction model error to ~ 17.047 % , which is twice as good as that of the standard CCRF method. Based on the attributes of the dataset, the DM-CCRF method is better for the prediction of highway traffic than the standard CCRF method and the baseline regressor.

Highlights

The construction of highways is one of the proposed solutions to overcome the problem of vehicle congestion and air increase in metropolitan areas [1]
The results provided by the standard continuous conditional random fields (CCRF) show its ability to suppress suppress errors obtained by the baseline regressor
Each showed scenarioa showed decreased value with the technique the standard. These results show the superiority of the compared with the compared with the standard CCRF and extreme learning machine (ELM)

Summary

Introduction

The construction of highways is one of the proposed solutions to overcome the problem of vehicle congestion and air increase in metropolitan areas [1]. Highways can shorten the travel time of a vehicle compared with normal roadways. Highways are an ideal alternative for long-distance driving. Research to predict traffic flow on highways can be done to study the problem of vehicle congestion [2] by analyzing traffic flow data. There are two early categorizations of traffic flow: macroscopic and microscopic traffic flow models. The macroscopic model is comparable to a fluid moving along a duct (described as a highway), and the microscopic model considers the movement of each individual vehicle while they interact [4]

Methods

Results

Conclusion