Using Random Forests for Data Mining and Drowsy Driver Classification Using FOT Data
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.
KeywordsData mining Random Forest Drowsy Driver Detection Proximity Outlier detection Variable selection Field operational test
Unable to display preview. Download preview PDF.
- 9.Lesemann, M.: Testing and evaluation methods for ict-based safety systems, deliverable D1.1: State of the art and evalue scope. Technical report, eValue project (2008), http://www.evalue-project.eu/pdf/evalue-080402-d11-v14-final.pdf
- 10.Kircher, A.: Vehicle control and drowsiness. VTI Meddelande 922A, Swedish National Road Transport Resesarch Institute, Linköping (2002)Google Scholar
- 14.Breiman, L., Cutler, A.: RFtools—for predicting and understanding data, Technical Report. Berkeley University, Berkeley, USA (2004)Google Scholar
- 15.Breiman, L.: Manual on setting up, using, and understanding random forests v3.1. Berkeley University, Berkeley (2002)Google Scholar
- 16.Kruskal, J., Wish, M.: Multidimensional scaling. Quantitative applications in the social sciences. Sage Publications (1978)Google Scholar
- 18.Wolpert, D.H., Macready, W.G.: No free lunch theorems for search. Technical Report SFI-TR-05-010, Santa Fe Institute (1995)Google Scholar