NORMA eResearch @NCI Library

Identifying Driver Distraction Using Deep Neural Networks

Dashpute, Pushkar (2020) Identifying Driver Distraction Using Deep Neural Networks. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (906kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


With the rise in globalization, Distracted Driving induces many deaths in road accidents and has become an increasingly relevant matter to discuss in recent traffic safety research. Driver Distraction has a major effect on people's safety and is an important subject for a variety of applications, ranging from automated driving assistance to insurance firms and research. The aim of the research in this paper is to design a system that can detect the distraction of drivers caused due to driving. The dataset used for the research was selected from Kaggle which was publicly accessible. This dataset was from State Farm Insurance company. This data was later transferred into binary form by data structure automation using Python. Further, the proposed design exploited Deep Learning models namely Convolutional Neural Networks (CNN), Xception, VGG19, and Thin MobileNet. These models are further assessed based on evaluation metrics namely accuracy and computational time required by each model. It was observed that Thin MobileNet outperformed all the other models in terms of accuracy which was 98.39% and computational time of 45 min for the training period of 10 epochs.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 22 Jan 2021 11:35
Last Modified: 22 Jan 2021 11:35

Actions (login required)

View Item View Item