Modeling the mindfulness people's function based on the recognition of biometric parameters by artificial intelligence elements

Olena Vysotska, Anatolii Davydenko, Oleksandr Potenko

Abstract


The subject matter of this article is the processes of modeling the function of attentiveness of users of critical applications on the basis of recognition of biometric parameters by elements of artificial intelligence. The goal is the development and software implementation of mechanisms for monitoring the work of employees of responsible professions, which, based on the analysis of information from a webcam online, monitor the presence of the employee's focus on the active zone of the critical application and the absence of unauthorized persons near the computer. The tasks to be solved are as follows: to determine a list of factors, the presence of which must be constantly checked to control the focus of the employee's attention on the active zone of the critical application and the absence of unauthorized persons near the computer; to choose the optimal technology for reading and primary processing of information from webcams online, for further use in solving the task; to develop mechanisms for monitoring certain factors, the presence of which must be constantly checked to control the presence of the employee's focus on the active zone of the critical application and the absence of unauthorized persons near the computer; and to programmatically implement the developed mechanisms using the object-oriented programming language Python. The methods used were artificial neural networks, 3D facial modeling, and landmark mapping. The following results were obtained. A list of factors has been identified, the presence of which must be constantly checked to monitor the presence of employee's attention in the active zone of critical use and the absence of unauthorized persons near the computer. On the basis of the analysis of modern technologies for reading and primary processing of information from online webcams, technologies implemented in the MediaPipe library were selected for further use in solving the problem. Mechanisms have been developed for monitoring certain factors, the presence of which must be constantly checked to monitor the presence of employees in the active zone of critical use and the absence of unauthorized persons near the computer. The object-oriented programming language Python is software-implemented using the MediaPipe library, mechanisms are developed and, based on the results of the experiments, the expediency of its use for solving the problem is proved. Conclusions. The scientific novelty of the obtained results is as follows: we have formed a list of factors, the presence of which must be constantly checked to monitor the presence of employee's attention in the active zone of critical application, the absence of unauthorized persons near the computer, and improved facial recognition technologies, which allows us to obtain a solution to the problem of monitoring the attention of users of critical applications in non-ideal conditions.

Keywords


critical application; facial geometry; map of landmarks; mindfulness; MediaPipe; neural networks

Full Text:

PDF

References


Radha Krishna, B., & Srihari Varma, M. Enhancing user-level security: performance analysis of machine learning algorithms for dynamic keystroke analysis. Journal of Theoretical and Applied Information Technology, 15.07.2023, vol.101, no. 13, pp. 5313-5324. Available at: http://www.jatit.org/volumes/Vol101No13/24Vol101No13.pdf. (аccessed 17.08.2023).

Davydenko, A., Vysotska, O., & Shmelova, T. Methods of primary processing handwriting samples at user authentication using a probabilistic neural network. Proceedings of the International Workshop on Cyber Hygiene co-located with 1st International Conference on Cyber Hygiene and Conflict Management in Global Information Networks (CyberConf 2019), Kyiv, Ukraine, 2019, vol. 2654, pp. 723-735. Available at: http://ceur-ws.org/Vol-2654/paper56.pdf. (accessed 24.06.2023).

Longjam, T., Kisku, D. R., & Gupta, P. Writer independent handwritten signature verification on multi-scripted signatures using hybrid CNN-BiLSTM: A novel approach. Expert Systems with Applications, March 2023, vol. 214, 119111. DOI: 10.1016/j.eswa.2022.119111.

Vysotska, O., & Davydenko, A. Additional authentication of privileged users by the geometry of their face in information systems using single sign-on technology. Processing, transmission and security of information, Part of the Monograph, 2021, pp. 257-268. DOI: 10.53052/9788366249868.27.

Zoubida, L., & Adjoudj, R. Integrating Face and the Both Irises for Personal Authentication. International Journal of Intelligent Systems and Applications (IJISA), 2017, vol. 9, no. 3, pp. 8-17. DOI: 10.5815/ijisa.2017.03.02.

Muthana, H. H., & Samah, K. A. Biometric System Design for Iris Recognition Using Intelligent Algorithms. International Journal of Modern Education and Computer Science (IJMECS), 2018, vol. 10, no. 3, pp. 9-16. DOI: 10.5815/ijmecs.2018.03.02.

Melkoz'orova, O., Malakhov, S., & Haykova, V. Veryfikatsiya vidbytkiv pal'tsiv z vykorystannyam rishennya zadachi komivoyazhera i dekompozytsiyi otochennya minutsiy [Fingerprint verification using the traveling salesman problem solution and decomposition of the vicinity of the minutiae]. Computer science and cybersecurity, 2020, no. 2 (18), pp. 25-32. DOI: 10.26565/2519-2310-2020-2-03.

Rassomakhin, S., Budianska, K., Uvarova, A., & Bagmut, M. Mathematical model of the biometric system of fingerprint authentication. Computer science and cybersecurity, 2019, no. 1 (13), pp. 4–16. DOI: 10.26565/2519-2310-2019-1-01.

Shanmukhappa, A. A., & Sanjeevakumar, M. H. Biometric Person Identification System: A Multimodal Approach Employing Spectral Graph Characteristics of Hand Geometry and Palmprint. International Journal of Intelligent Systems and Applications (IJISA), 2016, vol. 8, no. 3, pp. 48-58. DOI: 10.5815/ijisa.2016.03.06.

Paulini, M., Rathgeb, C., Nautsch, A., Reichau, H., Reininger, H., & Busch, C. Multi-Bit Allocation: Preparing Voice Biometrics for Template Protection. Proceedings the Speaker and Language Recognition Workshop (Odyssey 2016), Bilbao, Spain, 2016, pp. 291-296. DOI: 10.21437/Odyssey.2016-42.

Huang, Yu-H., & Chen, H. H. Deep face recognition for dim images. Pattern Recognition, June 2022, vol. 126, article no. 108580. DOI: 10.1016/j.patcog.2022.108580.

Ullah, N., Javed, A., Ghazanfar, M. A., Alsufyani, A., & Bourouis, S. A novel DeepMaskNet model for face mask detection and masked facial recognition. Journal of King Saud University - Computer and Information Sciences, 2022, vol. 34, no. 10 (B), pp. 9905-9914. DOI: 10.1016/j.jksuci.2021.12.017.

Tereikovskyi, I., Korchenko, O., Bushuyev, S., Tereikovskyi, O., Ziubina, R., & Veselska, O. A neural network model for object mask detection in medical images. International Journal of Electronics and Telecommunications, 2023, vol. 69, no. 1, pp. 41–46. DOI: 10.24425/ijet.2023.144329.

Batool, A., Nisar, M. W., Khan, M. A., Shah, J. H., Tariq, U., & Damasevicius, R. Traffic sign recognition using proposed lightweight twig-net with linear discriminant classifier for biometric application. Image and Vision Computing, 2023, vol. 135, article no. 104711. DOI: 10.1016/j.imavis.2023.104711.

Dergachov, K., Krasnov, L., Bilozerskyi, V., & Zymovin, A. Data pre-processing to in-crease the quality of optical text recognition systems. Radioelectronic and computer systems, 2021, no. 4, pp. 183-198. DOI: 10.32620/reks.2021.4.15.

Wawrzynski, T. Artificial intelligence and cuberculture. Radioelectronic and computer systems, 2020, no. 3, pp. 20-26. DOI: 10.32620/reks.2020.3.02.

Davydenko, A., Korchenko, O., Vysotska, O., & Ivanchenko, I. Model and method for identification of functional security profile. Proceedings of the 3rd International Conference on Information Security and Information Technologies (ISecIT 2021) co-located with 1st International Forum "Digital Reality" (DRForum 2021), Odesa, Ukraine, 2021, vol. 3200, pp. 274-280. Available at: https://ceur-ws.org/Vol-3200/paper40.pdf. (accessed 24.06.2023).

Kazmirchuk, S., Ilyenko, A., & Ilyenko, S. Digital signature authentication scheme with message recovery based on the use of elliptic curves. Advances in Computer Science for Engineering and Education II. ICCSEEA 2019. Advances in Intelligent Systems and Computing, 2019, vol. 938, pp. 279–288. DOI: 10.1007/978-3-030-16621-2_26.

Face landmark detection guide. Available at: https://developers.google.com/mediapipe/solutions/vision/face_landmarker. (accessed 24.06.2023).

Facial landmark detection made easy with MediaPipe guide. Available at: https://www.samproell.io/posts/yarppg/yarppg-face-detection-with-mediapipe/#fn:1. (accessed 24.06.2023).

Simplified_mediapipe_face_landmarks. Availa¬ble at: https://github.com/k-m-irfan/simplified_mediapipe_face_landmarks. (accessed 24.06.2023).

OpenCV Tutorials − Image Processing (imgproc module). Available at: https://opencv.org. (аccessed 24.06.2023).

FaceNet: A Unified Embedding for Face Recognition and Clustering. Available at: https://github.com/ZJCV/facenet. (аccessed 24.06.2023).

MobileNet-1. Available at: https://github.com/lyk125/MobileNet-1. (аccessed 24.06.2023).

Face detection guide. Available at: https://developers.google.com/mediapipe/solutions/vision/face_detector#blazeface_short-range. (аccessed 17.08.2023).

Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Computer Vision and Pattern Recognition, 17.04.2017. DOI: 10.48550/arXiv.1704.04861.

Review: MobileNetV2 — Light Weight Model (Image Classification). Available at: https://towardsdatascience.com/review-mobilenetv2-light-weight-model-image-classification-8febb490e61c. (accessed 20.08.2023).




DOI: https://doi.org/10.32620/reks.2023.3.11

Refbacks

  • There are currently no refbacks.