New LSTM Deep Learning Algorithm for Driving Behavior Classification
Nesrine Kadri, Ameni Ellouze, Mohamed Ksantini, Sameh Hbaieb Turki
Abstract
Road safety is an important topic of interest around the world. The road traffic accidents claim more than 1.2 million lives and cause as many as 50 million injuries each year without forgetting their huge impact on health and development. Several factors may result in the high number of accidents among which we can state the driving behavior. This paper focused on the study of drivers’ behavior and aimed to help reduce the number of accidents and consequently improve road safety. To this end, the driving behavior was classified into three categories (normal, drowsy and aggressive) based on smartphone sensors data. A new stacked Long Short-Term Memory (stacked LSTM) Recurrent Neural Networks architecture was proposed for the driving behaviors classification. The accuracy of the obtained drivers’ states results was improved with the use of the Dempster-Shafer (DS) theory of belief functions that overcame the uncertainty of data. The obtained results are clearly better than those existing in other driving behavior classification studies since the obtained F1-measure score achieves 97%.