Distracted Driver Classification for Low-computing Power Devices using Simple CNNs

Long Nguyen; Sukmoon Chang

doi:10.1109/AMLDS63918.2025.11159410

Distracted Driver Classification for Low-computing Power Devices using Simple CNNs

Long Nguyen
, Sukmoon Chang

School of Science, Engineering & Technology (Harrisburg)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Distracted driving is one of the major causes of traffic accidents. To help more drivers become aware of their driving behavior, this paper proposes a distracted driver classifier built specifically for low-computing power devices. The classifier is based on a simple Convolutional Neural Network (CNN) with Depthwise Separable convolution. The classifier was evaluated with the State Farm Distracted Driver Dataset and achieved a 99.15% accuracy while maintaining a speed of about 29.76 frames per second (FPS) on the Raspberry Pi 4 model B. Our proposed classifier will allow more cars to implement distracted driver detection systems, and thus, will help reduce the number of traffic accidents overall.

Original language	English (US)
Title of host publication	Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	720-726
Number of pages	7
ISBN (Electronic)	9798331510992
DOIs	https://doi.org/10.1109/AMLDS63918.2025.11159410
State	Published - 2025
Event	2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025 - Tokyo, Japan Duration: Jul 19 2025 → Jul 21 2025

Publication series

Name	Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025

Conference

Conference	2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025
Country/Territory	Japan
City	Tokyo
Period	7/19/25 → 7/21/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

All Science Journal Classification (ASJC) codes

Epidemiology
Computer Vision and Pattern Recognition
Computer Science Applications
Artificial Intelligence

Access to Document

10.1109/AMLDS63918.2025.11159410

Cite this

Nguyen, L., & Chang, S. (2025). Distracted Driver Classification for Low-computing Power Devices using Simple CNNs. In Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025 (pp. 720-726). (Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AMLDS63918.2025.11159410

Nguyen, Long ; Chang, Sukmoon. / Distracted Driver Classification for Low-computing Power Devices using Simple CNNs. Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 720-726 (Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025).

@inproceedings{90ef3c376ff74d47b1b0094025d0452b,

title = "Distracted Driver Classification for Low-computing Power Devices using Simple CNNs",

abstract = "Distracted driving is one of the major causes of traffic accidents. To help more drivers become aware of their driving behavior, this paper proposes a distracted driver classifier built specifically for low-computing power devices. The classifier is based on a simple Convolutional Neural Network (CNN) with Depthwise Separable convolution. The classifier was evaluated with the State Farm Distracted Driver Dataset and achieved a 99.15\% accuracy while maintaining a speed of about 29.76 frames per second (FPS) on the Raspberry Pi 4 model B. Our proposed classifier will allow more cars to implement distracted driver detection systems, and thus, will help reduce the number of traffic accidents overall.",

author = "Long Nguyen and Sukmoon Chang",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025 ; Conference date: 19-07-2025 Through 21-07-2025",

year = "2025",

doi = "10.1109/AMLDS63918.2025.11159410",

language = "English (US)",

series = "Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "720--726",

booktitle = "Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025",

address = "United States",

}

Nguyen, L & Chang, S 2025, Distracted Driver Classification for Low-computing Power Devices using Simple CNNs. in Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025. Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025, Institute of Electrical and Electronics Engineers Inc., pp. 720-726, 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025, Tokyo, Japan, 7/19/25. https://doi.org/10.1109/AMLDS63918.2025.11159410

Distracted Driver Classification for Low-computing Power Devices using Simple CNNs. / Nguyen, Long; Chang, Sukmoon.
Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 720-726 (Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Distracted Driver Classification for Low-computing Power Devices using Simple CNNs

AU - Nguyen, Long

AU - Chang, Sukmoon

PY - 2025

Y1 - 2025

N2 - Distracted driving is one of the major causes of traffic accidents. To help more drivers become aware of their driving behavior, this paper proposes a distracted driver classifier built specifically for low-computing power devices. The classifier is based on a simple Convolutional Neural Network (CNN) with Depthwise Separable convolution. The classifier was evaluated with the State Farm Distracted Driver Dataset and achieved a 99.15% accuracy while maintaining a speed of about 29.76 frames per second (FPS) on the Raspberry Pi 4 model B. Our proposed classifier will allow more cars to implement distracted driver detection systems, and thus, will help reduce the number of traffic accidents overall.

AB - Distracted driving is one of the major causes of traffic accidents. To help more drivers become aware of their driving behavior, this paper proposes a distracted driver classifier built specifically for low-computing power devices. The classifier is based on a simple Convolutional Neural Network (CNN) with Depthwise Separable convolution. The classifier was evaluated with the State Farm Distracted Driver Dataset and achieved a 99.15% accuracy while maintaining a speed of about 29.76 frames per second (FPS) on the Raspberry Pi 4 model B. Our proposed classifier will allow more cars to implement distracted driver detection systems, and thus, will help reduce the number of traffic accidents overall.

UR - https://www.scopus.com/pages/publications/105019058120

UR - https://www.scopus.com/pages/publications/105019058120#tab=citedBy

U2 - 10.1109/AMLDS63918.2025.11159410

DO - 10.1109/AMLDS63918.2025.11159410

M3 - Conference contribution

AN - SCOPUS:105019058120

T3 - Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025

SP - 720

EP - 726

BT - Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025

Y2 - 19 July 2025 through 21 July 2025

ER -

Nguyen L, Chang S. Distracted Driver Classification for Low-computing Power Devices using Simple CNNs. In Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 720-726. (Proceedings of the 2025 International Conference on Advanced Machine Learning and Data Science, AMLDS 2025). doi: 10.1109/AMLDS63918.2025.11159410

Distracted Driver Classification for Low-computing Power Devices using Simple CNNs

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this