Version 1
: Received: 18 June 2023 / Approved: 19 June 2023 / Online: 19 June 2023 (07:16:59 CEST)
How to cite:
Vrtagic, S.; Dordevic, M.; Dogan, F.; Codur, M.; Hoxha, M.; Softic, E. Unlocking Road Stability: Machine Learning-powered Prediction of Bitumen Distortion under Traffic Flow Influence. Preprints2023, 2023061310. https://doi.org/10.20944/preprints202306.1310.v1
Vrtagic, S.; Dordevic, M.; Dogan, F.; Codur, M.; Hoxha, M.; Softic, E. Unlocking Road Stability: Machine Learning-powered Prediction of Bitumen Distortion under Traffic Flow Influence. Preprints 2023, 2023061310. https://doi.org/10.20944/preprints202306.1310.v1
Vrtagic, S.; Dordevic, M.; Dogan, F.; Codur, M.; Hoxha, M.; Softic, E. Unlocking Road Stability: Machine Learning-powered Prediction of Bitumen Distortion under Traffic Flow Influence. Preprints2023, 2023061310. https://doi.org/10.20944/preprints202306.1310.v1
APA Style
Vrtagic, S., Dordevic, M., Dogan, F., Codur, M., Hoxha, M., & Softic, E. (2023). Unlocking Road Stability: Machine Learning-powered Prediction of Bitumen Distortion under Traffic Flow Influence. Preprints. https://doi.org/10.20944/preprints202306.1310.v1
Chicago/Turabian Style
Vrtagic, S., Mario Hoxha and Edis Softic. 2023 "Unlocking Road Stability: Machine Learning-powered Prediction of Bitumen Distortion under Traffic Flow Influence" Preprints. https://doi.org/10.20944/preprints202306.1310.v1
Abstract
Road intersections are made of asphalt pavement, a popular road surface material used worldwide. The pavement may suffer deformities and deterioration, resulting in higher maintenance expenses and an elevated likelihood of road accidents, due to factors such as heavy vehicles and environmental variables like temperature and rainfall. To tackle these obstacles, researchers have devised several machine-learning algorithms and optimization techniques. These tools aim to forecast and scrutinize pavement deformation, with the goal of refining pavement design and maintenance approaches, as well as obtaining a more comprehensive comprehension of the factors that impact pavement effectiveness. This paper shows that heavy vehicles contribute significantly more to road erosion, and the retention and braking of vehicles greatly impact roadways. We also emphasize the statistical errors computed on the actual data range and demonstrate the results of the multilayer perceptron (MLP) model. The MLP model used the lath erosion standard to simulate future impact. Even though the model given is based on a small sample of data from one intersection, its estimates for road erosion in a year were found to be accurate when contrasted to real data. Controlling traffic flow can significantly improve road conditions, reducing erosion decay by reducing the time spent at intersections and other parameters. We conclude that machine learning can help control traffic flow, which can significantly improve road conditions, reducing vehicle time stretches at intersections.
Keywords
Regression; Modeling erosion coefficients; Simulation; Back propagation; Lath and nail method
Subject
Engineering, Civil Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
