Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters
This work aims at classifying the road condition with data mining methods using simple acceleration sensors and gyroscopes installed in vehicles. Two classifiers are developed with a support vector machine (SVM) to distinguish between different types of road surfaces, such as asphalt and concrete, a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2018/8647607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832548766145576960 |
|---|---|
| author | Johannes Masino Jakob Thumm Guillaume Levasseur Michael Frey Frank Gauterin Ralf Mikut Markus Reischl |
| author_facet | Johannes Masino Jakob Thumm Guillaume Levasseur Michael Frey Frank Gauterin Ralf Mikut Markus Reischl |
| author_sort | Johannes Masino |
| collection | DOAJ |
| description | This work aims at classifying the road condition with data mining methods using simple acceleration sensors and gyroscopes installed in vehicles. Two classifiers are developed with a support vector machine (SVM) to distinguish between different types of road surfaces, such as asphalt and concrete, and obstacles, such as potholes or railway crossings. From the sensor signals, frequency-based features are extracted, evaluated automatically with MANOVA. The selected features and their meaning to predict the classes are discussed. The best features are used for designing the classifiers. Finally, the methods, which are developed and applied in this work, are implemented in a Matlab toolbox with a graphical user interface. The toolbox visualizes the classification results on maps, thus enabling manual verification of the results. The accuracy of the cross-validation of classifying obstacles yields 81.0% on average and of classifying road material 96.1% on average. The results are discussed on a comprehensive exemplary data set. |
| format | Article |
| id | doaj-art-65bac7161bd8421889695e51bb492e6d |
| institution | Kabale University |
| issn | 0197-6729 2042-3195 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-65bac7161bd8421889695e51bb492e6d2025-02-03T06:13:10ZengWileyJournal of Advanced Transportation0197-67292042-31952018-01-01201810.1155/2018/86476078647607Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle ParametersJohannes Masino0Jakob Thumm1Guillaume Levasseur2Michael Frey3Frank Gauterin4Ralf Mikut5Markus Reischl6Institute of Vehicle System Technology, Karlsruhe Institute of Technology, GermanyInstitute of Vehicle System Technology, Karlsruhe Institute of Technology, GermanyArtificial Intelligence Research Laboratory, Université Libre de Bruxelles, BelgiumInstitute of Vehicle System Technology, Karlsruhe Institute of Technology, GermanyInstitute of Vehicle System Technology, Karlsruhe Institute of Technology, GermanyInstitute for Automation and Applied Informatics, Karlsruhe Institute of Technology, GermanyInstitute for Automation and Applied Informatics, Karlsruhe Institute of Technology, GermanyThis work aims at classifying the road condition with data mining methods using simple acceleration sensors and gyroscopes installed in vehicles. Two classifiers are developed with a support vector machine (SVM) to distinguish between different types of road surfaces, such as asphalt and concrete, and obstacles, such as potholes or railway crossings. From the sensor signals, frequency-based features are extracted, evaluated automatically with MANOVA. The selected features and their meaning to predict the classes are discussed. The best features are used for designing the classifiers. Finally, the methods, which are developed and applied in this work, are implemented in a Matlab toolbox with a graphical user interface. The toolbox visualizes the classification results on maps, thus enabling manual verification of the results. The accuracy of the cross-validation of classifying obstacles yields 81.0% on average and of classifying road material 96.1% on average. The results are discussed on a comprehensive exemplary data set.http://dx.doi.org/10.1155/2018/8647607 |
| spellingShingle | Johannes Masino Jakob Thumm Guillaume Levasseur Michael Frey Frank Gauterin Ralf Mikut Markus Reischl Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters Journal of Advanced Transportation |
| title | Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters |
| title_full | Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters |
| title_fullStr | Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters |
| title_full_unstemmed | Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters |
| title_short | Characterization of Road Condition with Data Mining Based on Measured Kinematic Vehicle Parameters |
| title_sort | characterization of road condition with data mining based on measured kinematic vehicle parameters |
| url | http://dx.doi.org/10.1155/2018/8647607 |
| work_keys_str_mv | AT johannesmasino characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT jakobthumm characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT guillaumelevasseur characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT michaelfrey characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT frankgauterin characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT ralfmikut characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters AT markusreischl characterizationofroadconditionwithdataminingbasedonmeasuredkinematicvehicleparameters |