Analyzing the Effectiveness of Imbalanced Data Handling Techniques in Predicting Driver Phone Use

Distracted driving leads to a significant number of road crashes worldwide. Smartphone use is one of the most common causes of cognitive distraction among drivers. Available data on drivers’ phone use presents an invaluable opportunity to identify the main factors behind this behavior. Machine learning (ML) techniques are among the most effective techniques for this purpose. However, the potential and usefulness of these techniques are limited, due to the imbalance of available data. The majority class of instances collected is for drivers who do not use their phones, while the minority class is for those who do use their phones. This paper evaluates two main approaches for handling imbalanced datasets on driver phone use. These methods include oversampling and undersampling. The effectiveness of each method was evaluated using six ML techniques: Multilayer Perceptron (MLP), Support Vector Machine (SVM), Naive Bayes (NB), Bayesian Network (BayesNet), J48, and ID3. The proposed methods were also evaluated on three Deep Learning (DL) models: Arch1 (5 hidden layers), Arch2 (10 hidden layers), and Arch3 (15 hidden layers). The data used in this document were collected through a direct observation study to explore a set of human, vehicle, and road surface characteristics. The results showed that all ML methods, as well as DL methods, achieved balanced accuracy values for both classes. ID3, J48, and MLP methods outperformed the rest of the ML methods in all scenarios, with ID3 achieving slightly better accuracy. The DL methods also provided good performances, especially for the undersampling data. The results also showed that the classification methods performed best on the undersampled data. It was concluded that road classification has the highest impact on cell phone use, followed by driver age group, driver gender, vehicle type, and, finally, driver seatbelt usage.