A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections

The delay at signalized intersections is a crucial parameter that determines the performance and level of service (LOS). The estimation models are commonly used to model delay; however, inaccurate predictions from these models can pose a significant limitation. Consequently, this study aimed to comp...

Full description

Saved in:
Bibliographic Details
Main Authors: Yazan Alatoom, Abdallah Al-Hamdan
Format: Article
Language:English
Published: Pouyan Press 2025-01-01
Series:Journal of Soft Computing in Civil Engineering
Subjects:
Online Access:https://www.jsoftcivil.com/article_196451_5dc528466073e5ded39b18da885fda4c.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849411958570221568
author Yazan Alatoom
Abdallah Al-Hamdan
author_facet Yazan Alatoom
Abdallah Al-Hamdan
author_sort Yazan Alatoom
collection DOAJ
description The delay at signalized intersections is a crucial parameter that determines the performance and level of service (LOS). The estimation models are commonly used to model delay; however, inaccurate predictions from these models can pose a significant limitation. Consequently, this study aimed to compare a wide array of machine learning algorithms, including Artificial Neural Networks (ANN), Random Forest (RF), decision tree, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), AdaBoost, Gradient Boost, XGBoost, and Partial Least Squares (PLS) regression. A comprehensive evaluation was undertaken across prediction accuracy, training-testing performance discrepancy, sensitivity to outliers, computational time cost, and model robustness. Additionally, the proposed methods were benchmarked against the Highway Capacity Manual (HCM), Webster, and Akçelik models. The results demonstrated that the RF model exhibited the most balanced performance across the specified criteria, with an average error below 4% and a rating of 35 out of 45 according to the proposed criteria. Moreover, the findings revealed that adopted analytical models should not be employed for vehicular delay estimation without calibration, as RMSE values were about 5 to 58 times higher than other models, varying by model.
format Article
id doaj-art-3847f5d2d29f4e669d1bf84970b97585
institution Kabale University
issn 2588-2872
language English
publishDate 2025-01-01
publisher Pouyan Press
record_format Article
series Journal of Soft Computing in Civil Engineering
spelling doaj-art-3847f5d2d29f4e669d1bf84970b975852025-08-20T03:34:36ZengPouyan PressJournal of Soft Computing in Civil Engineering2588-28722025-01-019112215710.22115/scce.2024.418800.1725196451A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized IntersectionsYazan Alatoom0Abdallah Al-Hamdan1Ph.D. Student, Department of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, Iowa, 50011, United StatesPh.D. Student, Department of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, Iowa, 50011, United StatesThe delay at signalized intersections is a crucial parameter that determines the performance and level of service (LOS). The estimation models are commonly used to model delay; however, inaccurate predictions from these models can pose a significant limitation. Consequently, this study aimed to compare a wide array of machine learning algorithms, including Artificial Neural Networks (ANN), Random Forest (RF), decision tree, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), AdaBoost, Gradient Boost, XGBoost, and Partial Least Squares (PLS) regression. A comprehensive evaluation was undertaken across prediction accuracy, training-testing performance discrepancy, sensitivity to outliers, computational time cost, and model robustness. Additionally, the proposed methods were benchmarked against the Highway Capacity Manual (HCM), Webster, and Akçelik models. The results demonstrated that the RF model exhibited the most balanced performance across the specified criteria, with an average error below 4% and a rating of 35 out of 45 according to the proposed criteria. Moreover, the findings revealed that adopted analytical models should not be employed for vehicular delay estimation without calibration, as RMSE values were about 5 to 58 times higher than other models, varying by model.https://www.jsoftcivil.com/article_196451_5dc528466073e5ded39b18da885fda4c.pdfvehicle delay estimationtraffic signal delay modelingmachine learning for delay predictionsignalized intersection delaystop delay modelsdata-driven delay modelscomparative study of delay algorithmsrandom forest for delay estimation
spellingShingle Yazan Alatoom
Abdallah Al-Hamdan
A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
Journal of Soft Computing in Civil Engineering
vehicle delay estimation
traffic signal delay modeling
machine learning for delay prediction
signalized intersection delay
stop delay models
data-driven delay models
comparative study of delay algorithms
random forest for delay estimation
title A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
title_full A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
title_fullStr A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
title_full_unstemmed A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
title_short A Comparative Study between Different Machine Learning Algorithms for Estimating the Vehicular Delay at Signalized Intersections
title_sort comparative study between different machine learning algorithms for estimating the vehicular delay at signalized intersections
topic vehicle delay estimation
traffic signal delay modeling
machine learning for delay prediction
signalized intersection delay
stop delay models
data-driven delay models
comparative study of delay algorithms
random forest for delay estimation
url https://www.jsoftcivil.com/article_196451_5dc528466073e5ded39b18da885fda4c.pdf
work_keys_str_mv AT yazanalatoom acomparativestudybetweendifferentmachinelearningalgorithmsforestimatingthevehiculardelayatsignalizedintersections
AT abdallahalhamdan acomparativestudybetweendifferentmachinelearningalgorithmsforestimatingthevehiculardelayatsignalizedintersections
AT yazanalatoom comparativestudybetweendifferentmachinelearningalgorithmsforestimatingthevehiculardelayatsignalizedintersections
AT abdallahalhamdan comparativestudybetweendifferentmachinelearningalgorithmsforestimatingthevehiculardelayatsignalizedintersections