Classification of the Acoustics of Loose Gravel
Road condition evaluation is a critical part of gravel road maintenance. One of the assessed parameters is the amount of loose gravel, as this determines the driving quality and safety. Loose gravel can cause tires to slip and the driver to lose control. An expert assesses the road conditions subjec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4944 |
| _version_ | 1797526053290246144 |
|---|---|
| author | Nausheen Saeed Roger G. Nyberg Moudud Alam Mark Dougherty Diala Jooma Pascal Rebreyend |
| author_facet | Nausheen Saeed Roger G. Nyberg Moudud Alam Mark Dougherty Diala Jooma Pascal Rebreyend |
| author_sort | Nausheen Saeed |
| collection | DOAJ |
| description | Road condition evaluation is a critical part of gravel road maintenance. One of the assessed parameters is the amount of loose gravel, as this determines the driving quality and safety. Loose gravel can cause tires to slip and the driver to lose control. An expert assesses the road conditions subjectively by looking at images and notes. This method is labor-intensive and subject to error in judgment; therefore, its reliability is questionable. Road management agencies look for automated and objective measurement systems. In this study, acoustic data on gravel hitting the bottom of a car was used. The connection between the acoustics and the condition of loose gravel on gravel roads was assessed. Traditional supervised learning algorithms and convolution neural network (CNN) were applied, and their performances are compared for the classification of loose gravel acoustics. The advantage of using a pre-trained CNN is that it selects relevant features for training. In addition, pre-trained networks offer the advantage of not requiring days of training or colossal training data. In supervised learning, the accuracy of the ensemble bagged tree algorithm for gravel and non-gravel sound classification was found to be 97.5%, whereas, in the case of deep learning, pre-trained network GoogLeNet accuracy was 97.91% for classifying spectrogram images of the gravel sounds. |
| first_indexed | 2024-03-10T09:23:42Z |
| format | Article |
| id | doaj.art-5c132da66bef4c6c931eb1d18c05d0a6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:23:42Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5c132da66bef4c6c931eb1d18c05d0a62023-11-22T04:58:24ZengMDPI AGSensors1424-82202021-07-012114494410.3390/s21144944Classification of the Acoustics of Loose GravelNausheen Saeed0Roger G. Nyberg1Moudud Alam2Mark Dougherty3Diala Jooma4Pascal Rebreyend5School of Technology and Business Studies, Dalarna University, 78170 Borlänge, SwedenSchool of Technology and Business Studies, Dalarna University, 78170 Borlänge, SwedenSchool of Technology and Business Studies, Dalarna University, 78170 Borlänge, SwedenSchool of Information Technology, Halmstad University, 30250 Halmstad, SwedenSchool of Technology and Business Studies, Dalarna University, 78170 Borlänge, SwedenSchool of Technology and Business Studies, Dalarna University, 78170 Borlänge, SwedenRoad condition evaluation is a critical part of gravel road maintenance. One of the assessed parameters is the amount of loose gravel, as this determines the driving quality and safety. Loose gravel can cause tires to slip and the driver to lose control. An expert assesses the road conditions subjectively by looking at images and notes. This method is labor-intensive and subject to error in judgment; therefore, its reliability is questionable. Road management agencies look for automated and objective measurement systems. In this study, acoustic data on gravel hitting the bottom of a car was used. The connection between the acoustics and the condition of loose gravel on gravel roads was assessed. Traditional supervised learning algorithms and convolution neural network (CNN) were applied, and their performances are compared for the classification of loose gravel acoustics. The advantage of using a pre-trained CNN is that it selects relevant features for training. In addition, pre-trained networks offer the advantage of not requiring days of training or colossal training data. In supervised learning, the accuracy of the ensemble bagged tree algorithm for gravel and non-gravel sound classification was found to be 97.5%, whereas, in the case of deep learning, pre-trained network GoogLeNet accuracy was 97.91% for classifying spectrogram images of the gravel sounds.https://www.mdpi.com/1424-8220/21/14/4944gravel roadsloose gravelensemble bagged treessound analysisroad maintenanceGoogLeNet |
| spellingShingle | Nausheen Saeed Roger G. Nyberg Moudud Alam Mark Dougherty Diala Jooma Pascal Rebreyend Classification of the Acoustics of Loose Gravel Sensors gravel roads loose gravel ensemble bagged trees sound analysis road maintenance GoogLeNet |
| title | Classification of the Acoustics of Loose Gravel |
| title_full | Classification of the Acoustics of Loose Gravel |
| title_fullStr | Classification of the Acoustics of Loose Gravel |
| title_full_unstemmed | Classification of the Acoustics of Loose Gravel |
| title_short | Classification of the Acoustics of Loose Gravel |
| title_sort | classification of the acoustics of loose gravel |
| topic | gravel roads loose gravel ensemble bagged trees sound analysis road maintenance GoogLeNet |
| url | https://www.mdpi.com/1424-8220/21/14/4944 |
| work_keys_str_mv | AT nausheensaeed classificationoftheacousticsofloosegravel AT rogergnyberg classificationoftheacousticsofloosegravel AT moududalam classificationoftheacousticsofloosegravel AT markdougherty classificationoftheacousticsofloosegravel AT dialajooma classificationoftheacousticsofloosegravel AT pascalrebreyend classificationoftheacousticsofloosegravel |