Adaptive Delivery of Educational and Methodological Materials Based on Neurolinguistic Programming Models Based on the Results of Assessing the Student’s Posture at the Computer or in the Classroom Using Machine Learning
( Pp. 81-88)

The article investigates the use of neurolinguistic programming (NLP) and machine learning methods for the adaptive delivery of educational materials, taking into account students’ individual perception characteristics. The primary goal of the work is to create and optimize individualized learning trajectories based on the analysis of students’ posture and behavior during their interaction with educational materials. The article examines three main types of perception – visual, auditory, and kinesthetic – and proposes methods for adapting educational content for each of them. To determine the type of perception, data analysis is conducted on head position, gaze direction, facial expressions, and other physiological parameters obtained through computer vision and neural networks such as FSA-Net. The authors propose algorithms for dynamic calibration and analysis of students’ posture, which can be applied in both individual and group learning contexts. The possibility of using these algorithms in distance learning systems to enhance the quality of student interaction with the educational platform and improve their learning outcomes is considered. The article also discusses the potential application of the proposed technologies for assessing student engagement in lectures and creating adaptive learning trajectories that take into account dynamic characteristics such as emotional state and cognitive effort, which can be evaluated through pupil dilation analysis.

Zhivetyev A.V., Belov M.A. Adaptive Delivery of Educational and Methodological Materials Based on Neurolinguistic Programming Models Based on the Results of Assessing the Student’s Posture at the Computer or in the Classroom Using Machine Learning. Computational Nanotechnology. 2024. Vol. 11. No. 3. Pp. 81–88. (In Rus.). DOI: 10.33693/2313-223X-2024-11-3-81-88. EDN: QIUKZS

Grishko S., Belov M., Cheremisina E., Sychev P. Model for creating an adaptive individual learning path for training digital transformation professionals and big data engineers using Virtual Computer Lab. Communications in Computer and Information Science. 2021. Vol. 1448 CCIS. Pp. 496–507.
Volkov N.G. Neuro-linguistic programming and basic concepts of education in a technological university and a military educational institution. Bulletin of the Kazan Technological University. 2014. Vol. 17. No. 8. Pp. 315–322. (In Rus.)
Qin H., Gong R., Liu X., Shen M. Forward and backward information retention for accurate binary neural networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): Proceedings. 2020. Pp. 2257–2265.
Belov M.A., Grishko S.I., Zhivetyev A.V. et al. Application of fuzzy logic methods to form an adaptive individual learning trajectory based on dynamic control of course complexity. Modeling, Optimization and Information Technology. 2022. No. 10 (4). (In Rus.)
Kahneman D. et al. Pupillary, heart rate, and skin resistance changes during a mental task. Journal of Experimental Psychology. 1969. No. 79. Pp. 164–167.
Albiero V., Chen X., Yin X., Pang G. img2pose: Face alignment and detection via 6DoF, face pose estimation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): Proceedings. 2021. Pp. 755–764.
Esin R.V., Zykova T.V., Kustitskaya T.A., Kytmanov A.A. Digital educational history as a component of the digital profile of a student in the context of education transformation. Prospects of Science and Education. 2022. No. 5 (59). Pp. 566–584. (In Rus.)

methods for adapting the educational process, modern educational technologies, innovations in education, neurolinguistic programming, pose estimation, learner’s perception types, digital profile, task selection, individualized learning trajectories.