Monday, 22 August 2022

Hidden Markov Model Applied for Vehicles Density Prediction| Chapter 7 | Novel Research Aspects in Mathematical and Computer Science Vol. 7

 A key location for regional development is the Gempol-Pandaan toll. 2017 saw a rise in the volume of traffic going through this toll. It is possible for traffic congestion and road damage to occur as a result of the passing of multiple vehicles, especially trucks carrying loads that are too heavy for them. Because of this, it is crucial to estimate the number of cars that will enter through the Pandaan toll gate from the Gempol, Kejapanan, Bangil, and Rembang toll gates as well. In this study, vehicle density is analysed using the likelihood and amount of each vehicle category—I, II, III, IV, and V. The Hidden Markov Model (HMM) method was chosen in this study since the origin gate and vehicle category cannot be detected directly, but the car must pass the toll gate in order to tap the e-toll card. The two estimation methods for HMM parameters employed in this study are the Expectation-Maximization (EM) algorithm and the Bayesian approach. The result shows that the EM approach is inferior to Bayesian parameter estimation for HMM. The Bayesian calculated parameter values are closer to the input parameters, making the model more adequate to explain the expected vehicle density.


Author(s) Details:

N. I. Asrori,
Department of Statistics, Faculty of Mathematics, Computing, and Data Science, Institut Teknologi Sepuluh Nopember, Indonesia.

N. Iriawan,
Department of Statistics, Faculty of Mathematics, Computing, and Data Science, Institut Teknologi Sepuluh Nopember, Indonesia.

Please see the link here: https://stm.bookpi.org/NRAMCS-V7/article/view/7952

No comments:

Post a Comment