The Application of Artificial Neural Network in Identifying Driver Distraction

• Activity Number: 172
• Type: Topic Contributed
• Date/Time: Monday, August 10, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Transportation Statistics Interest Group
• Author(s): Shan Bao* and Zizheng Guo and Jim Sayer
• Companies: University of Michigan Transportation Research Institute and University of Michigan Transportation Research Institute and University of Michigan Transportation Research Institute
• Keywords: Artificial Neural Network ; Driver distraction ; Field Test

Abstract

Many studies use vehicle kinematic signal data to predict or monitor drivers' state. Artificial Neural Network (ANN) is a stochastic method that can characterize the statistical properties of these signals. ANN is widely used for pattern classification and fitting nonlinear relationships between variables and has been successfully applied for detection, verification, and recognition of objects and text, and the retrieval of information and images. Based on the performance of ANN in pattern classification and the fact that the influence of cellphone use while driving could be reflected by vehicle operating and running states, we applied ANN in detecting drivers' engagement in different cellphone use while driving by using the vehicle sensor data collected from 108 drivers who participated in the Integrated Vehicle based Safety System Field Operational Test (IVBSS) project. Their behavior and performance with and without cell phone use while driving were extracted and used in this analysis. The ANN was applied to categorize the driving situations and drivers' activities. The findings suggest that the safety consequences of cell phone use were quite different across drivers.