Using Random Forests for Data Mining and Drowsy Driver Classification Using FOT Data

Abstract

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.