Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

Rafał Doniec; Justyna Konior; Szymon Sieciński; Artur Piet; Muhammad Tausif Irshad; Natalia Piaseczna; Md Abid Hasan; Frédéric Li; Muhammad Adeel Nisar; Marcin Grzegorzek

doi:10.3390/s23125551

Sensor-Based Classification of Primary and Secondary Car Driver Activities Using Convolutional Neural Networks

Sensors (Basel). 2023 Jun 13;23(12):5551. doi: 10.3390/s23125551.

Authors

Affiliations

¹ Department of Biosensors and Processing of Biomedical Signals, Faculty of Biomedical Engineering, Silesian University of Technology, Roosevelta 40, 41-800 Zabrze, Poland.
² Institute of Medical Informatics, University of Lübeck, Ratzeburger Allee 160, 23562 Lübeck, Germany.
³ Department of Information Technology, University of the Punjab, Lahore 54000, Pakistan.
⁴ Department of Knowledge Engineering, University of Economics in Katowice, Bogucicka 3, 40-287 Katowice, Poland.

Abstract

To drive safely, the driver must be aware of the surroundings, pay attention to the road traffic, and be ready to adapt to new circumstances. Most studies on driving safety focus on detecting anomalies in driver behavior and monitoring cognitive capabilities in drivers. In our study, we proposed a classifier for basic activities in driving a car, based on a similar approach that could be applied to the recognition of basic activities in daily life, that is, using electrooculographic (EOG) signals and a one-dimensional convolutional neural network (1D CNN). Our classifier achieved an accuracy of 80% for the 16 primary and secondary activities. The accuracy related to activities in driving, including crossroad, parking, roundabout, and secondary activities, was 97.9%, 96.8%, 97.4%, and 99.5%, respectively. The F1 score for secondary driving actions (0.99) was higher than for primary driving activities (0.93-0.94). Furthermore, using the same algorithm, it was possible to distinguish four activities related to activities of daily life that were secondary activities when driving a car.

Keywords: convolutional neural networks; driving a car; driving behavior; electrooculography.

MeSH terms

Accidents, Traffic / prevention & control
Algorithms
Automobile Driving* / psychology
Automobiles
Neural Networks, Computer

Grants and funding

This research received funding for car simulator from the pro-quality grant 57/2021 of the Rector of the Silesian University of Technology, Gliwice, Poland; decision number ZP/165980.