A Machine Learning Approach for Transportation Mode Detection

Enrique DELAHOZ-DOMINGUEZ, Tomás FONTALVO-HERRERA and Hoolyana Ojeda

Abstract:

In this study, an automatic learning approach is used to identify the transportation mode of a smartphone user, using as predictor variables the outputs of the accelerometer, gyroscope and sound sensors. Finally, a comparison of the performances obtained by the algorithms GLMNET, Random Forest, kNN and XGboost is presented. The algorithm with the highest accuracy was Random Forest with 85.6%.