Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Comparison of Pattern Recognition Techniques for Classification of the Acoustics of Loose Gravel
Dalarna University, School of Technology and Business Studies, Microdata Analysis.
Dalarna University, School of Technology and Business Studies, Statistics.ORCID iD: 0000-0002-3183-3756
Dalarna University, School of Technology and Business Studies, Information Systems.ORCID iD: 0000-0003-4812-4988
Halmstad University.ORCID iD: 0000-0001-7713-8292
Show others and affiliations
2020 (English)In: 2020 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020, 2020, p. 237-243, article id 9311569Conference paper, Published paper (Refereed)
Abstract [en]

Road condition evaluation is a critical part of gravel road maintenance. One of the parameters that are assessed is loose Gravel. An expert does this evaluation by subjectively looking at images taken and written text for deciding on the road condition. This method is labor-intensive and subjected to an error of judgment; therefore, it is not reliable. Road management agencies are looking for more efficient and automated objective measurement methods. In this study, acoustic data of gravel hitting the bottom of the car is used, and the relation between these acoustics and the condition of loose gravel on gravel roads is seen. A novel acoustic classification method based on Ensemble bagged tree (EBT) algorithm is proposed in this study for the classification of loose gravel sounds. The accuracy of the EBT algorithm for Gravel and Non-gravel sound classification is found to be 97.5. The detection of the negative classes, i.e., non-gravel detection, is preeminent, which is considerably higher than Boosted Trees, RUSBoosted Tree, Support vector machines (SVM), and decision trees.

Place, publisher, year, edition, pages
2020. p. 237-243, article id 9311569
Keywords [en]
Supervised learning, Sound analysis, Fast Fourier Transform, FFT, Gravel roads, Pattern recognition
National Category
Engineering and Technology Computer Systems
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
URN: urn:nbn:se:du-35796DOI: 10.1109/ISCMI51676.2020.9311569ISI: 000750622300045Scopus ID: 2-s2.0-85100349048ISBN: 9781728175591 (electronic)OAI: oai:DiVA.org:du-35796DiVA, id: diva2:1517755
Conference
7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020; Virtual, Stockholm; Sweden; 14 November 2020 through 15 November 2020
Projects
Automated gravel road condition assessmentAvailable from: 2021-01-14 Created: 2021-01-14 Last updated: 2022-05-12Bibliographically approved
In thesis
1. Automated Gravel Road Condition Assessment: A Case Study of Assessing Loose Gravel using Audio Data
Open this publication in new window or tab >>Automated Gravel Road Condition Assessment: A Case Study of Assessing Loose Gravel using Audio Data
2021 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Gravel roads connect sparse populations and provide highways for agriculture and the transport of forest goods. Gravel roads are an economical choice where traffic volume is low. In Sweden, 21% of all public roads are state-owned gravel roads, covering over 20,200 km. In addition, there are some 74,000 km of gravel roads and 210,000 km of forest roads that are owned by the private sector. The Swedish Transport Administration (Trafikverket) rates the condition of gravel roads according to the severity of irregularities (e.g. corrugations and potholes), dust, loose gravel, and gravel cross-sections. This assessment is carried out during the summertime when roads are free of snow. One of the essential parameters for gravel road assessment is loose gravel. Loose gravel can cause a tire to slip, leading to a loss of driver control.  Assessment of gravel roads is carried out subjectively by taking images of road sections and adding some textual notes. A cost-effective, intelligent, and objective method for road assessment is lacking. Expensive methods, such as laser profiler trucks, are available and can offer road profiling with high accuracy. These methods are not applied to gravel roads, however, because of the need to maintain cost-efficiency. 

In this thesis, we explored the idea that, in addition to machine vision, we could also use machine hearing to classify the condition of gravel roads in relation to loose gravel. Several suitable classical supervised learning and convolutional neural networks (CNN) were tested. When people drive on gravel roads, they can make sense of the road condition by listening to the gravel hitting the bottom of the car. The more we hear gravel hitting the bottom of the car, the more we can sense that there is a lot of loose gravel and, therefore, the road might be in a bad condition. Based on this idea, we hypothesized that machines could also undertake such a classification when trained with labeled sound data. Machines can identify gravel and non-gravel sounds. In this thesis, we used traditional machine learning algorithms, such as support vector machines (SVM), decision trees, and ensemble classification methods. We also explored CNN for classifying spectrograms of audio sounds and images in gravel roads. Both supervised learning and CNN were used, and results were compared for this study. In classical algorithms, when compared with other classifiers, ensemble bagged tree (EBT)-based classifiers performed best for classifying gravel and non-gravel sounds. EBT performance is also useful in reducing the misclassification of non-gravel sounds. The use of CNN also showed a 97.91% accuracy rate. Using CNN makes the classification process more intuitive because the network architecture takes responsibility for selecting the relevant training features. Furthermore, the classification results can be visualized on road maps, which can help road monitoring agencies assess road conditions and schedule maintenance activities for a particular road.

Place, publisher, year, edition, pages
Borlänge: Dalarna University, 2021
Series
Dalarna Licentiate Theses ; 17
Keywords
Gravel roads, road maintenance, convolutional neural network (CNN), SVM, decision trees, ensemble bagged trees, GoogLeNet, ResNet50, ResNet18, sound analysis
National Category
Infrastructure Engineering Computer and Information Sciences
Identifiers
urn:nbn:se:du-36402 (URN)978-91-88679-14-7 (ISBN)
Presentation
2021-05-28, a digital seminar and room 244, Campus Borlänge, 13:00 (English)
Opponent
Supervisors
Note

Due to unforeseen circumstances the seminar was postponed from May 7 to 28, as duly stated in the new posting page.

Available from: 2021-04-08 Created: 2021-04-06 Last updated: 2023-04-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Saeed, NausheenAlam, MoududNyberg, Roger G.Dougherty, MarkRebreyend, PascalJomaa, Diala

Search in DiVA

By author/editor
Saeed, NausheenAlam, MoududNyberg, Roger G.Dougherty, MarkRebreyend, PascalJomaa, Diala
By organisation
Microdata AnalysisStatisticsInformation SystemsComputer Engineering
Engineering and TechnologyComputer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 158 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf