Human Fatigue Evaluation by Face's Image Analysis Based upon Convolutional Neural Networks
Main Article Content
Abstract
This article presents solutions to the person's fatigue recognition problem by the face's image analysis based on convolutional neural networks. In the present paper, existing algorithms were considered. A new model's architecture was proposed and implemented. Resultant metrics of the model were evaluated.
Article Details
References
2. Levashov S.P. Monitoring i analiz professional'nykh riskov v Rossii i za rubezhom. Kurganskii gosudarstvennyi universitet.
3. Phillips R.O. et al. Fatigue in transport: a review of exposure, risks, checks and controls // Transport Reviews. Routledge, 2017. Vol. 37, No. 6. P. 742–766.
4. Qiang Ji, Zhiwei Zhu, Lan P. Real-time nonintrusive monitoring and prediction of driver fatigue // IEEE Transactions on Vehicular Technology. 2004. Vol. 53, No. 4. P. 1052–1068.
5. Sharafutdinova A.F. Sistema opredeleniya ustalosti voditelya // Vestnik Sov-remennykh Issledovanii. 2018. № 7.1 (22).
6. Singh S., Papanikolopoulos N.P. Monitoring driver fatigue using facial analysis techniques // Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No. 99TH8383). Tokyo, Japan: IEEE, 1999. P. 314–318.
7. Wen-Bing Horng et al. Driver fatigue detection based on eye tracking and dy-namic template matching // IEEE International Conference on Networking, Sensing and Control, 2004. Taipei, Taiwan: IEEE, 2004. P. 7–12.
8. Sklonnost' k neschastnym sluchayam i faktory, ee obuslavlivayushchie | Ekstremal'na ta krizova psikhologіya [Electronic resource]. URL: http://extrpsy.nuczu.edu.ua/statya18 (accessed: 31.03.2021).
9. Prichiny neschastnykh sluchaev – Okhrana truda [Electronic resource]. URL: http://okhrana-truda.com/neschastnye-sluchai-i-professionalnye-zabolevaniya/prichiny-neschastnykh-sluchaev.html (accessed: 31.03.2021).
10. Chelovecheskii faktor kak prichina proizvodstvennogo travmatizma | Inter-aktivnyi portal Departamenta truda i zanyatosti naseleniya Tyumenskoi oblasti [Elec-tronic resource]. URL: https://czn.admtyumen.ru/News/Detail/7efb0823-7fee-4366-836e-5f4affa7f6d5 (accessed: 12.04.2021).
11. Obyazan li rabotodatel' vyplachivat' kompensatsiyu rabotniku, poluchivshemu travmu na proizvodstve? // Upravlenie personalom [Electronic resource]. URL: https://www.top-personal.ru/lawissue.html?2294 (accessed: 31.03.2021).
12. Evija.Feierabende. Glavnaya prichina travm na rabote – legkomyslennoe otnoshenie k bezopasnosti [Electronic resource]: Text // www.balta.lv. 2017. URL: https://www.balta.lv/ru/content/glavnaya-prichina-travm-na-rabote-–-legkomyslennoe-otnoshenie-k-bezopasnosti (accessed: 31.03.2021).
13. Sikander G., Anwar S. Driver Fatigue Detection Systems: A Review // IEEE Trans. Intell. Transport. Syst. 2019. Vol. 20, No. 6. P. 2339–2352.
14. David F. Dinges, Richard Grace. PERCLOS: A Valid Psychophysiological Meas-ure of Alertness As Assessed by Psychomotor Vigilance. P. 4.
15. Yadav N., Banerjee K., Bali V. A Survey on Fatigue Detection of Workers Using Machine Learning // International Journal of E-Health and Medical Communications. 2020. Vol. 11, No. 3. P. 1–8.
16. Bengio Y., Lecun Y. Convolutional Networks for Images, Speech, and Time-Series. 1997.
17. He K. et al. Deep Residual Learning for Image Recognition // arXiv:1512.03385 [cs]. 2015.
18. Realizuem i sravnivaem optimizatory modelei v glubokom obuchenii [Electron-ic resource]. URL: https://habr.com/ru/company/skillfactory/blog/525214/ (accessed: 10.05.2021).
19. Global Z. Brutalk – Funktsiya aktivatsii Softmax s Python [Electronic resource] // URL: https://www.brutalk.com/ru/brutalk-blog/view/funkciya-aktivacii-softmax-s-python-6046b4a524b71 (accessed: 10.05.2021).
18. Fatigue_detection (Dataset) [Electronic resource]. URL: https://kaggle.com/timmjy/fatigue-detection (accessed: 05.04.2021).
19. Colaboratory – Google [Electronic resource]. URL: https://research.google.com/colaboratory/faq.html (accessed: 11.05.2021).
20. Keras: the Python deep learning API [Electronic resource]. URL: https://keras.io/ (accessed: 10.05.2021).
21. TensorFlow [Electronic resource]. URL: https://www.tensorflow.org/ (ac-cessed: 10.05.2021).
22. Fatigure-detection [Electronic resource]. URL: https://github.com/bairamovazat/fatigure-detection (accessed: 10.05.2021).
23. Advances in Face Detection and Facial Image Analysis / ed. Kawulok M., Celebi M.E., Smolka B. Cham: Springer International Publishing, 2016.
24. NeuralSetStorage [Electronic resource]. URL: https://github.com/bairamovazat/NeuralSetStorage (accessed: 10.05.2021).
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.