Vehicle's Density Prediction Based on History Data of e-Toll in PT Jasamarga Pandaan Tol Using Hidden Markov Model

The Gempol-Pandaan toll is a strategic center for regional development. In 2017, the number of vehicles passing through this toll has increased. This condition could impact on traffic jam and road damage because of passes by many cars, especially trucks with loads that exceed their capacity. Therefo...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2020-03, Vol.1490 (1), p.12017
Main Authors: Asrori, N I, Iriawan, N, Winahju, W S
Format: Article
Language:English
Subjects:
Algorithms
Automobiles
Bayesian analysis
Density
Impact damage
Markov chains
Mathematical models
Parameter estimation
Physics
Regional development
Toll roads
Traffic congestion
Traffic jams
Trucks
Vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Gempol-Pandaan toll is a strategic center for regional development. In 2017, the number of vehicles passing through this toll has increased. This condition could impact on traffic jam and road damage because of passes by many cars, especially trucks with loads that exceed their capacity. Therefore, it is necessary to do a vehicle's density prediction not only from the Gempol toll gate but also from Kejapanan, Bangil and Rembang toll gates that will exit through Pandaan toll gate. In this research, vehicle's density is viewed from the probability and number of each vehicles category I, II, III, IV, V. The origin gate and vehicle category can not be observed directly, but the car must pass the toll gate to do tapping the e-toll card, so the method used in this research is the Hidden Markov Model (HMM). Two estimate methods for HMM parameters are employed in this research, the Expectation-Maximization (EM) algorithm and Bayesian approach. The result shows that HMM parameters estimation using Bayesian is better than the EM algorithm. The Bayesian estimated parameter values are closer to the input parameters so that the model is more representative to explain the vehicle's density prediction.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1490/1/012017