Research Article
Classification of Distracted Driving Using Transfer Learning and Deep Neural Network
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 187 - Issue 71 |
| Published: January 2026 |
| Authors: Deepthi M. Pisharody, Binu P. Chacko, Mohamed Basheer K.P. |
10.5120/ijca2026926181
|
Deepthi M. Pisharody, Binu P. Chacko, Mohamed Basheer K.P. . Classification of Distracted Driving Using Transfer Learning and Deep Neural Network. International Journal of Computer Applications. 187, 71 (January 2026), 62-67. DOI=10.5120/ijca2026926181
@article{ 10.5120/ijca2026926181,
author = { Deepthi M. Pisharody,Binu P. Chacko,Mohamed Basheer K.P. },
title = { Classification of Distracted Driving Using Transfer Learning and Deep Neural Network },
journal = { International Journal of Computer Applications },
year = { 2026 },
volume = { 187 },
number = { 71 },
pages = { 62-67 },
doi = { 10.5120/ijca2026926181 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2026
%A Deepthi M. Pisharody
%A Binu P. Chacko
%A Mohamed Basheer K.P.
%T Classification of Distracted Driving Using Transfer Learning and Deep Neural Network%T
%J International Journal of Computer Applications
%V 187
%N 71
%P 62-67
%R 10.5120/ijca2026926181
%I Foundation of Computer Science (FCS), NY, USA
Abstract
Distracted driving is a significant contributor to traffic accidents. In order to improve road safety, it is critical to not only detect instances of driver distraction but also to identify the core causes of these distractions. In this study, description about a complete technique to classifying instances of distracted driving that fully incorporates transfer learning technology. Our process is predicated on a precisely produced dataset that has been thoroughly annotated to assure ac- curacy. This dataset is augmented further, and feature extraction is carried out using a wide selection of transfer learning models, including VGG16, Resnet50, Inception, Densenet, and Xception. Following that, the collected features are fed into a DDD classifier which classifies and identifies distraction types. Our experimental results indisputably show that the DNN model, after feature extraction via the Resnet50 transfer learning model, outperforms all other models in the context of distracted driving classification.
References
- Distracted driving. [Internet]. https://seriousaccidents. com/legal-advice/top-causes-of-car-accidents/driver-distractions/
- Q. Xiong, J. Lin, W. Yue, S. Liu, Y. Liu, and C. Ding, A deep learning approach to driver distraction detection of using mobile phone, IEEE Vehicle Power and Propulsion Conference (VPPC), pp. 1– 5, IEEE, 2019. DOI:10.1109/VPPC46532.2019.8952474
- G. Li, Q. Liu, and Z. Guo, Driver distraction detection using advanced deep learning technologies based on images, IEEE Journal of Radio Frequency Identification, vol. 6, pp. 825–831, 2022. Doi: 10.1109/JRFID.2022.3209237
- Pisharody, Deepthi M., Binu P. Chacko, and KP Mohamed Basheer. Driver distraction detection using machine learning techniques. Materials Today: Proceedings 58 (2022): 251-255.doi: https://doi.org/10.1016/j.matpr.2022.02.108
- Hossain, M. U., Rahman, M. A., Islam, M. M., Akhter, A., Uddin, M. A., and Paul, B. K. (2022). Automatic driver distraction detection using deep convolutional neural networks. Intelligent Systems with Applications, 14, 200075. https://doi.org/10.1016/j.iswa.2022.200075
- J. Tang, M. Sharma, and R. Zhang, “Explaining the effect of data augmentation on image classification tasks,” 2020.
- Q. Zheng, M. Yang, X. Tian, N. Jiang, D. Wang, et al., “A full stage data augmentation method in deep convolutional neural network for natural image classification,” Discrete Dynamics in Nature and Society, vol. 2020, 2020.
Index Terms
Keywords