Driver cellphone usage detection using wavelet scattering and convolutional neural networks

This paper provides an automated system based on machine learning and computer vision to detect cellphone usage during driving. We used Wavelet Scattering Networks, which is a simple and efficient type of architecture. The presented model is straightforward and compact and requires little hyper-para...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Besharati, Ali Nahvi, Serajeddin Ebrahimian
Format: Article
Language:English
Published: Amirkabir University of Technology 2025-07-01
Series:AUT Journal of Mathematics and Computing
Subjects:
Online Access:https://ajmc.aut.ac.ir/article_5229_b3827b345e600a3ed1a2eb1a7b1bdc13.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688220280815616
author Ali Besharati
Ali Nahvi
Serajeddin Ebrahimian
author_facet Ali Besharati
Ali Nahvi
Serajeddin Ebrahimian
author_sort Ali Besharati
collection DOAJ
description This paper provides an automated system based on machine learning and computer vision to detect cellphone usage during driving. We used Wavelet Scattering Networks, which is a simple and efficient type of architecture. The presented model is straightforward and compact and requires little hyper-parameter tuning. The speed of this model is similar to the Convolutional Neural Networks. We monitored the driver from two viewpoints: a frontal view of the driver’s face and a side view of the driver’s whole body. We created a new dataset for the first viewpoint, and used a publicly available dataset for the second viewpoint. Our model achieved the test accuracy of 91% for our new dataset and 99% for the publicly available one.
format Article
id doaj-art-2d834c7c7a0f4dfc8490de79f78c15f8
institution DOAJ
issn 2783-2449
2783-2287
language English
publishDate 2025-07-01
publisher Amirkabir University of Technology
record_format Article
series AUT Journal of Mathematics and Computing
spelling doaj-art-2d834c7c7a0f4dfc8490de79f78c15f82025-08-20T03:22:04ZengAmirkabir University of TechnologyAUT Journal of Mathematics and Computing2783-24492783-22872025-07-016325726810.22060/ajmc.2023.22580.11775229Driver cellphone usage detection using wavelet scattering and convolutional neural networksAli Besharati0Ali Nahvi1Serajeddin Ebrahimian2Virtual Reality Laboratory, K.N. Toosi University of Technology, Tehran, IranVirtual Reality Laboratory, K.N. Toosi University of Technology, Tehran, IranVirtual Reality Laboratory, K.N. Toosi University of Technology, Tehran, IranThis paper provides an automated system based on machine learning and computer vision to detect cellphone usage during driving. We used Wavelet Scattering Networks, which is a simple and efficient type of architecture. The presented model is straightforward and compact and requires little hyper-parameter tuning. The speed of this model is similar to the Convolutional Neural Networks. We monitored the driver from two viewpoints: a frontal view of the driver’s face and a side view of the driver’s whole body. We created a new dataset for the first viewpoint, and used a publicly available dataset for the second viewpoint. Our model achieved the test accuracy of 91% for our new dataset and 99% for the publicly available one.https://ajmc.aut.ac.ir/article_5229_b3827b345e600a3ed1a2eb1a7b1bdc13.pdfmobile use detectionwavelet scattering networkcnncascade object detectortransfer learning
spellingShingle Ali Besharati
Ali Nahvi
Serajeddin Ebrahimian
Driver cellphone usage detection using wavelet scattering and convolutional neural networks
AUT Journal of Mathematics and Computing
mobile use detection
wavelet scattering network
cnn
cascade object detector
transfer learning
title Driver cellphone usage detection using wavelet scattering and convolutional neural networks
title_full Driver cellphone usage detection using wavelet scattering and convolutional neural networks
title_fullStr Driver cellphone usage detection using wavelet scattering and convolutional neural networks
title_full_unstemmed Driver cellphone usage detection using wavelet scattering and convolutional neural networks
title_short Driver cellphone usage detection using wavelet scattering and convolutional neural networks
title_sort driver cellphone usage detection using wavelet scattering and convolutional neural networks
topic mobile use detection
wavelet scattering network
cnn
cascade object detector
transfer learning
url https://ajmc.aut.ac.ir/article_5229_b3827b345e600a3ed1a2eb1a7b1bdc13.pdf
work_keys_str_mv AT alibesharati drivercellphoneusagedetectionusingwaveletscatteringandconvolutionalneuralnetworks
AT alinahvi drivercellphoneusagedetectionusingwaveletscatteringandconvolutionalneuralnetworks
AT serajeddinebrahimian drivercellphoneusagedetectionusingwaveletscatteringandconvolutionalneuralnetworks