Crack damage prediction of asphalt pavement based on tire noise: A comparison of machine learning algorithms
Predicting road pavement damage is a vital aspect of traffic management aimed at decreasing accident rates. Compared with other pavement non-destructive testing methods, using tire noise for testing has the advantages of low cost and convenient detection. This study introduces a machine learning (ML) algorithm specifically designed to predict road pavement damage based on tire noise propagation. Five machine learning algorithms, Support Vector Classifier (SVC), Random Forest Classifier (RFC), AdaBoost, Multilayer Perceptron (MLP), and Stacked Classifier were utilized to enhance the accuracy of damage prediction using tire noise. The data for this study was collected from Yuanjiang Road, Fuzhou City, Fujian, China, in September 2022, using a microphone, camera, and GPS to create an audio dataset. This data was then split into training and testing sets to assess the performance of the algorithms. The RFC method proved superior to the other models, demonstrating accuracy, precision, recall, and F1-scores of 99%, 98%, 99%, and 96%, respectively. The findings show that tire noise propagation datasets can be used to detect road damage through various classification prediction models. This approach is reliable, efficient, cost-effective, and highly effective.
- Record URL:
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/09500618
-
Supplemental Notes:
- © 2024 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
-
Authors:
- Li, Huixia
- Nyirandayisabye, Ritha
- 0000-0002-1824-8923
- Dong, Qiming
- Niyirora, Rosette
- Hakuzweyezu, Theogene
- Zardari, Irshad Ali
- Nkinahamira, François
- Publication Date: 2024-2-2
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: 134867
-
Serial:
- Construction and Building Materials
- Volume: 414
- Issue Number: 0
- Publisher: Elsevier
- ISSN: 0950-0618
- Serial URL: http://www.sciencedirect.com/science/journal/09500618?sdc=1
Subject/Index Terms
- TRT Terms: Cracking of asphalt concrete pavements; Data files; Machine learning; Predictive models; Tire/pavement noise
- Geographic Terms: Fuzhou (China)
- Subject Areas: Data and Information Technology; Highways; Maintenance and Preservation; Pavements;
Filing Info
- Accession Number: 01909942
- Record Type: Publication
- Files: TRIS
- Created Date: Feb 27 2024 10:09AM