Sökning: onr:"swepub:oai:DiVA.org:ri-27845" >
Using random forest...
Using random forests for data mining data and drowsy driver classification using FOT data
-
- Englund, Cristofer (författare)
- RISE,Viktoria,Kooperativa System
-
- Kovaceva, Jordanka (författare)
- Volvo, Sweden
-
- Lindman, Magdalena (författare)
- Volvo, Sweden
-
visa fler...
-
- Grönvall, John-Fredrik (författare)
- Volvo, Sweden
-
visa färre...
-
(creator_code:org_t)
- Berlin, Heidelberg : Springer Berlin Heidelberg, 2012
- 2012
- Engelska.
-
Ingår i: Proceedings of On the Move to Meaningful Internet Systems. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 9783642336140 ; , s. 748-758
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Data mining techniques based on Random forests are explored to gain knowledge about data in a Field Operational Test (FOT) database. We compare the performance of a Random forest, a Support Vector Machine and a Neural network used to separate drowsy from alert drivers. 25 variables from the FOT data was utilized to train the models. It is experimentally shown that the Random forest outperforms the other methods while separating drowsy from alert drivers. It is also shown how the Random forest can be used for variable selection to find a subset of the variables that improves the classification accuracy. Furthermore it is shown that the data proximity matrix estimated from the Random forest trained using these variables can be used to improve both classification accuracy, outlier detection and data visualization.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
Nyckelord
- Data mining
- Drowsy Driver Detection
- Field operational test
- Outlier detection
- Proximity
- Random Forest
- Variable selection
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas