Performance Comparison of Deep CNN Models for Detecting Driver’s Distraction

CMC-Computers, Materials & Continua, Vol.68, No.3, pp. 4109-4124

16 Pages Posted: 21 Jun 2021

See all articles by Kathiravan Srinivasan

Kathiravan Srinivasan

Vellore Institute of Technology (VIT) - School of Information Technology & Engineering (SITE)

Lalit Garg

University of Malta - Department of Computer Information System

Debajit Datta

Vellore Institute of Technology (VIT), Vellore, School of Computer Science and Engineering

Abdulellah A. Alaboudi

Shaqra University

N. Z. Jhanjhi

Taylor’s University Malaysia

Rishav Agarwal

Vellore Institute of Technology (VIT), Vellore, School of Computer Science and Engineering

Anmol George Thomas

Vellore Institute of Technology (VIT) - School of Computer Science and Engineering

Date Written: June 16, 2021

Abstract

According to various worldwide statistics, most car accidents occur solely due to human error. The person driving a car needs to be alert, especially when travelling through high traffic volumes that permit high-speed transit since a slight distraction can cause a fatal accident. Even though semiautomated checks, such as speed detecting cameras and speed barriers, are deployed, controlling human errors is an arduous task. The key causes of driver’s distraction include drunken driving, conversing with co-passengers, fatigue, and operating gadgets while driving. If these distractions are accurately predicted, the drivers can be alerted through an alarm system. Further, this research develops a deep convolutional neural network (deep CNN) models for predicting the reason behind the driver’s distraction. The deep CNN models are trained using numerous images of distracted drivers. The performance of deepCNNmodels, namely theVGG16,ResNet, and Xception network, is assessed based on the evaluation metrics, such as the precision score, the recall/sensitivity score, the F1 score, and the specificity score. The ResNet model outperformed all other models as the best detection model for predicting and accurately determining the drivers’ activities.

Keywords: Deep-CNN, ResNet, Xception, VGG16, Data, Classification

Suggested Citation

Srinivasan, Kathiravan and Garg, Lalit and Datta, Debajit and Alaboudi, Abdulellah A. and Jhanjhi, N. Z. and Agarwal, Rishav and Thomas, Anmol George, Performance Comparison of Deep CNN Models for Detecting Driver’s Distraction (June 16, 2021). CMC-Computers, Materials & Continua, Vol.68, No.3, pp. 4109-4124, Available at SSRN: https://ssrn.com/abstract=3868549

Kathiravan Srinivasan

Vellore Institute of Technology (VIT) - School of Information Technology & Engineering (SITE) ( email )

Vellore, Tamil Nadu 632014
India

Lalit Garg

University of Malta - Department of Computer Information System

Msida
Malta

Debajit Datta (Contact Author)

Vellore Institute of Technology (VIT), Vellore, School of Computer Science and Engineering ( email )

Vellore, Tamil Nadu
India

Abdulellah A. Alaboudi

Shaqra University ( email )

main street
king saud
Shagra, 11911
Saudi Arabia

N. Z. Jhanjhi

Taylor’s University Malaysia ( email )

Subang Jaya
Malaysia

Rishav Agarwal

Vellore Institute of Technology (VIT), Vellore, School of Computer Science and Engineering

vellore, Tamil Nadu
India

Anmol George Thomas

Vellore Institute of Technology (VIT) - School of Computer Science and Engineering ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
345
Abstract Views
934
Rank
159,857
PlumX Metrics