Citation

Raslan E, Alrahmawy MF, Mohammed YA, Tolba AS. Sci. Rep. 2024; 14(1): e11620.

Copyright

(Copyright © 2024, Nature Publishing Group)

DOI

10.1038/s41598-024-61757-1

PMID

38773123

Abstract

The accurate classification of road surface conditions plays a vital role in ensuring road safety and effective maintenance. Vibration-based techniques have shown promise in this domain, leveraging the unique vibration signatures generated by vehicles to identify different road conditions. In this study, we focus on utilizing vehicle-mounted vibration sensors to collect road surface vibrations and comparing various data representation techniques for classifying road surface conditions into four classes: normal road surface, potholes, bad road surface, and speedbumps. Our experimental results reveal that the combination of multiple data representation techniques results in higher performance, with an average accuracy of 93.4%. This suggests that the integration of deep neural networks and signal processing techniques can produce a high-level representation better suited for challenging multivariate time series classification issues.

Language: en

Keywords

Frequency domain; Road surface condition classification; Time domain; Time–frequency domain