Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality

This study integrates e-scooter vibrational data with smartphone sensors, employing machine learning to evaluate road surfaces. The goal is to classify the road surface roughness level(s) equivalent to the high cycle fatigue threshold(s) experienced by the e-scooter. This information is fundamentall...

Full description

Saved in:
Bibliographic Details
Main Authors: Asher Virin, Lalitphat Khongsomchit, Sakdirat Kaewunruen
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Built Environment
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fbuil.2025.1497331/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119786896293888
author Asher Virin
Lalitphat Khongsomchit
Sakdirat Kaewunruen
author_facet Asher Virin
Lalitphat Khongsomchit
Sakdirat Kaewunruen
author_sort Asher Virin
collection DOAJ
description This study integrates e-scooter vibrational data with smartphone sensors, employing machine learning to evaluate road surfaces. The goal is to classify the road surface roughness level(s) equivalent to the high cycle fatigue threshold(s) experienced by the e-scooter. This information is fundamentally critical in determining the remaining service life prior to repairing or reconditioning the e-scooter. Three machine learning models—Random Forest Classifier, Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) with k-means clustering—were tested using various hyperparameter tuning, post-processing, and data splitting strategies. The models achieved high accuracies above 95%, with the SVM and k-means clustering model consistently reaching up to 100% accuracy and processing times under 700 ms, indicating potential for real-time applications. Despite challenges in data collection and preprocessing, the top SVM configuration using 5-fold cross-validation demonstrated substantial promise. An 80/20 data split initially resulted in lower accuracies due to inappropriate sequencing, which was rectified by adjusting data handling methods. The most successful model has promising applications in monitoring rider comfort and support preventative maintenance for e-scooters. For instance, a sudden change in classification outputs (e.g. derived from large ampitude vibrations) of an e-scooter could indicate maintenance needs, enabling timely interventions. This approach aligns with data collection efforts by companies such as Beryl and could be integrated into existing infrastructures. Future research could expand on these findings by examining a wider variety of surfaces and speeds and incorporating regression analysis to advance the models from classification to predictive analytics.
format Article
id doaj-art-582b31fd2f654ccaaa1c6a6ec31a223a
institution OA Journals
issn 2297-3362
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Built Environment
spelling doaj-art-582b31fd2f654ccaaa1c6a6ec31a223a2025-08-20T02:35:33ZengFrontiers Media S.A.Frontiers in Built Environment2297-33622025-06-011110.3389/fbuil.2025.14973311497331Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride qualityAsher Virin0Lalitphat Khongsomchit1Sakdirat Kaewunruen2Department of Mechanical Engineering, School of Engineering, University of Birmingham, Birmingham, United KingdomDepartment of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, United KingdomDepartment of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, United KingdomThis study integrates e-scooter vibrational data with smartphone sensors, employing machine learning to evaluate road surfaces. The goal is to classify the road surface roughness level(s) equivalent to the high cycle fatigue threshold(s) experienced by the e-scooter. This information is fundamentally critical in determining the remaining service life prior to repairing or reconditioning the e-scooter. Three machine learning models—Random Forest Classifier, Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) with k-means clustering—were tested using various hyperparameter tuning, post-processing, and data splitting strategies. The models achieved high accuracies above 95%, with the SVM and k-means clustering model consistently reaching up to 100% accuracy and processing times under 700 ms, indicating potential for real-time applications. Despite challenges in data collection and preprocessing, the top SVM configuration using 5-fold cross-validation demonstrated substantial promise. An 80/20 data split initially resulted in lower accuracies due to inappropriate sequencing, which was rectified by adjusting data handling methods. The most successful model has promising applications in monitoring rider comfort and support preventative maintenance for e-scooters. For instance, a sudden change in classification outputs (e.g. derived from large ampitude vibrations) of an e-scooter could indicate maintenance needs, enabling timely interventions. This approach aligns with data collection efforts by companies such as Beryl and could be integrated into existing infrastructures. Future research could expand on these findings by examining a wider variety of surfaces and speeds and incorporating regression analysis to advance the models from classification to predictive analytics.https://www.frontiersin.org/articles/10.3389/fbuil.2025.1497331/fullmachine learningrandom forestextreme gradient boostingsupport vector machinee-scooterroad surface roughness level
spellingShingle Asher Virin
Lalitphat Khongsomchit
Sakdirat Kaewunruen
Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
Frontiers in Built Environment
machine learning
random forest
extreme gradient boosting
support vector machine
e-scooter
road surface roughness level
title Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
title_full Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
title_fullStr Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
title_full_unstemmed Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
title_short Deep learning application to roughness classification of road surface conditions through an e-scooter’s ride quality
title_sort deep learning application to roughness classification of road surface conditions through an e scooter s ride quality
topic machine learning
random forest
extreme gradient boosting
support vector machine
e-scooter
road surface roughness level
url https://www.frontiersin.org/articles/10.3389/fbuil.2025.1497331/full
work_keys_str_mv AT ashervirin deeplearningapplicationtoroughnessclassificationofroadsurfaceconditionsthroughanescootersridequality
AT lalitphatkhongsomchit deeplearningapplicationtoroughnessclassificationofroadsurfaceconditionsthroughanescootersridequality
AT sakdiratkaewunruen deeplearningapplicationtoroughnessclassificationofroadsurfaceconditionsthroughanescootersridequality