Abstract
The purpose of the article is to prepare a methodology for an advanced system that implements screening among children of early school age. The screening will be implemented in classrooms using cameras. Cameras in bi-weekly windows will study children’s behavior and the system will report alerts when abnormal behavior is detected. The alerts are intended to recommend in-depth examinations with a specialist. In this article, the authors present a preliminary study to assess the feasibility of rapidly creating classifiers that detect specific behavioral elements (e.g., open mouth, putting fingers in mouth, asymmetrical closing of eyes, etc.). The article aims to define a methodology for detecting anomalies in children’s behavior, which in the next stages of the project will be used to detect undesirable behaviors such as lack of concentration, hyperactivity, epilepsy, undesirable behavior to noise and stress. The aim of the presented research is to create a methodology based on proprietary neural network-based classifiers in later studies implementing screening tests. The presented article presents research comparing the performance of two different neural network architectures: an advanced ResNet-based model and a simpler custom convolutional neural network (CNN). The research presented here demonstrates that both advanced and simple models have their place in the rapid development of microclassifiers and allow acceptance of the chosen methodology for further work on student screening.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bi, X., Chen, Z., Yue, J.: A Novel one-step method based on YOLOv3-tiny for fatigue driving detection. In: 2020 IEEE 6th International Conference on Computer and Communications (ICCC), pp. 1241–1245. IEEE (2020)
Bodla, N., Zheng, J., Xu, H., Chen, J.C., Castillo, C., Chellappa, R.: Deep heterogeneous feature fusion for template-based face recognition. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 586–595. IEEE (2017)
Chen, H., Zhou, G., Jiang, H.: Student behavior detection in the classroom based on improved YOLOv8. Sensors 23(20), 8385 (2023)
Cheng, Y.: Video-based student classroom classroom behavior state analysis. Int. J. Educ. Humanit. 5(2), 229–233 (2022)
Cowton, J., Kyriazakis, I., Bacardit, J.: Automated individual pig localisation, tracking and behaviour metric extraction using deep learning. IEEE Access 7, 108049–108060 (2019)
Dhillon, A., Verma, G.K.: Convolutional neural network: a review of models, methodologies and applications to object detection. Prog. Artif. Intell. 9(2), 85–112 (2020)
Feng, J., Guo, Q., Guan, Y., Wu, M., Zhang, X., Ti, C.: 3D face recognition method based on deep convolutional neural network. In: Panigrahi, B.K., Trivedi, M.C., Mishra, K.K., Tiwari, S., Singh, P.K. (eds.) Smart Innovations in Communication and Computational Sciences. AISC, vol. 670, pp. 123–130. Springer, Singapore (2019). https://doi.org/10.1007/978-981-10-8971-8_12
Han, Y.K., Choi, Y.B.: Human action recognition based on LSTM model using smartphone sensor. In: 2019 Eleventh International Conference on Ubiquitous and Future Networks (ICUFN), pp. 748–750. IEEE (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Jiang, B., Xu, W., Guo, C., Liu, W., Cheng, W.: A classroom concentration model based on computer vision. In: Proceedings of the ACM Turing Celebration Conference-China, pp. 1–6 (2019)
Khan, M.A., et al.: Human action recognition using fusion of multiview and deep features: an application to video surveillance. Multimedia Tools and Appl. 83(5), 1–27 (2020)
La Cava, S.M., Orrù, G., Drahansky, M., Marcialis, G.L., Roli, F.: 3D face reconstruction: the road to forensics. ACM Comput. Surv. 56(3), 1–38 (2023)
Lu, Z., Jiang, X., Kot, A.: Feature fusion with covariance matrix regularization in face recognition. Signal Process. 144, 296–305 (2018)
Mandal, B., Okeukwu, A., Theis, Y.: Masked face recognition using resnet-50. arXiv preprint arXiv:2104.08997 (2021)
Moustafa, A.A., Elnakib, A., Areed, N.F.: Age-invariant face recognition based on deep features analysis. SIViP 14, 1027–1034 (2020)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, H., et al.: A real-time and long-term face tracking method using convolutional neural network and optical flow in IoT-based multimedia communication systems. Wirel. Commun. Mob. Comput. 2021, 1–15 (2021)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Sharma, V., Gupta, M., Kumar, A., Mishra, D.: Video processing using deep learning techniques: a systematic literature review. IEEE Access 9, 139489–139507 (2021)
Simanjuntak, F., Azzopardi, G.: Fusion of CNN- and COSFIRE-based features with application to gender recognition from face images. In: Arai, K., Kapoor, S. (eds.) CVC 2019. AISC, vol. 943, pp. 444–458. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-17795-9_33
Simón, M.O., et al.: Improved RGB-D-T based face recognition. Iet Biometrics 5(4), 297–303 (2016)
Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human action recognition from various data modalities: a review. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3200–3225 (2022)
Taskiran, M., Kahraman, N., Erdem, C.E.: Face recognition: past, present and future (a review). Digital Signal Proc. 106, 102809 (2020)
Tian, W., et al.: Learning better features for face detection with feature fusion and segmentation supervision. arXiv preprint arXiv:1811.08557 (2018)
Verma, Kamal Kant, Singh, Brij Mohan, Dixit, Amit: A review of supervised and unsupervised machine learning techniques for suspicious behavior recognition in intelligent surveillance system. Int. J. Inf. Technol. 1–14 (2019). https://doi.org/10.1007/s41870-019-00364-0
Zhao, Z., Alzubaidi, L., Zhang, J., Duan, Y., Gu, Y.: A comparison review of transfer learning and self-supervised learning: definitions, applications, advantages and limitations. Expert Syst. Appl. 122807 (2023)
Zhu, H., Wei, H., Li, B., Yuan, X., Kehtarnavaz, N.: A review of video object detection: datasets, metrics and methods. Appl. Sci. 10(21), 7834 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dziczkowski, G., Jach, T., Probierz, B., Stefanski, P., Kozak, J. (2024). Selection of Rapid Classifier Development Methodology Used to Implement a Screening Study Based on Children’s Behavior During School Lessons. In: Campos Ferreira, M., Wachowicz, T., Zaraté, P., Maemura, Y. (eds) Human-Centric Decision and Negotiation Support for Societal Transitions. GDN 2024. Lecture Notes in Business Information Processing, vol 509. Springer, Cham. https://doi.org/10.1007/978-3-031-59373-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-59373-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-59372-7
Online ISBN: 978-3-031-59373-4
eBook Packages: Computer ScienceComputer Science (R0)