Aerospace Technic and Technology

The subject of the article is a methodological basis for ensuring the adaptability of educational systems (ES) with biometric feedback to the user in real time, which ensures the personalization of the learning process. The goal is to increase the efficiency of computer-aided learning tools by developing methods for forming an ES user profile based on the integration of previous psychometric assessments of the level of training, analysis of learning results, and subsequent conversion of information about the user's state into discrete levels of complexity for the dispatching of training modules within the ES. Tasks that need to be solved are the following: to conduct a critical analysis of approaches to creating adaptive ES with biometric feedback and means of personalizing the learning process; to develop a method for forming an individual ES user profile that will ensure a rational learning trajectory, considering the specifics of the process of acquiring knowledge, skills, and abilities inherent in each individual learner; and to develop a method for assessing the current state of the ES user in real time, based on data received from mobile sensors, considering the existing operational and cost limitations of biometric monitoring devices. The following results were obtained. A method for the automated formation of the user profile of the educational software system by assessing the latent abilities of the user, using psychometric models, determining on this basis the levels of complexity of test tasks, describing typical errors, and forming a vector of the individual profile of the ES user, and a method for the online assessment of the current psychophysical state of the user were developed. The practical advantage of the developed methods is that they ensure the integration of the state assessment component into the software architectures of adaptive ES in various subject areas, based on a standardized representation of the vector of the current state of the user. Such integration can be performed in soft real-time mode in virtual reality driving training systems, pilot training simulators with the ability to monitor cognitive load in critical flight situations, in training platforms with monitoring of attention and reaction speed for operators controlling complex equipment (for example, nuclear power plant power units), training systems to support management competencies, etc. Conclusions. As a result of the conducted research, an approach was created to ensure the proper level of adaptability of the ES, through the consistent application of user personalization methods in the training process, namely the formation of their individual profile, and monitoring of the current psychophysical state in online mode. The scientific novelty of the obtained results lies in the following. For the first time, a method for the automated user profile formation of an educational software system by assessing the latent abilities of the user using psychometric models, determining on this basis the levels of complexity of tasks for the user, describing typical errors and forming a user profile vector as a formal specification of the user interface, which makes it possible to automate the process of dispatching and verifying software modules of the ES, depending on the values of the components of the vector of the individual user profile. The method of online assessment of the user's state in real time for adaptive ES has been improved, in which, unlike existing ones, an integral biometric index is formed based on the analysis of heart rate variability, heart-rate patterns are determined and, as a result, a vector of the current user state is formed, which can be represented within the framework of a software interface for the automated dispatching of software modules of the ES. The results of the experimental verification demonstrated the effectiveness of the developed methodological tools in solving problems related to increasing the efficient functioning of the ЕS.

training system; adaptability; psychometric characteristics of the user; biometric feedback; cognitive load; Computerized Adaptive Testing; Item Response Theory; Maximum Likelihood Estimation; level of complexity of the test task; trajectory of skill chan

Embretson, S. E., & Reise, S. P. Item response theory for psychologists. New York, Publ. Psychology Press, 2000. 384 p. DOI: 10.4324/9781410605269.

Weiss, D. J., & Kingsbury, G. G. Application of computerized adaptive testing to educational problems. Journal of Educational Measurement, 1984, vol. 21, iss. 4, pp. 361–375. DOI: 10.1111/j.1745-3984.1984.tb01040.x.

Boboc, R. G., Butilă, E. V., & Butnariu, S. Leveraging wearable sensors in virtual reality driving simulators: A review of techniques and applications. Sensors, 2024, vol. 24, iss. 13, article no. 4417. DOI: 10.3390/s24134417.

Nasri, M. Towards Intelligent VR Training: A Physiological Adaptation Framework for Cognitive Load and Stress Detection. arXiv, 2025. DOI: 10.48550/arXiv.2504.06461.

González-Calatayud, V., Prendes-Espinosa, P., & Roig-Vila, R. Artificial intelligence for student assessment: A systematic review. Applied Sciences, 2021, vol. 11, iss. 12, article no. 5467. DOI: 10.3390/app11125467.

Lord, F. M. Applications of Item Response Theory to Practical Testing Problems. New York, Routledge, 1980. 288 p. DOI: 10.4324/9780203056615.

Birnbaum, A., Lord, F. M., & Novick, M. R. Some Latent Trait Models and Their Use in Inferring an Examinee's Ability. Statistical Theories of Mental Test Scores. Reading, MA: Addison-Wesley, 1968. Available at: https://cir.nii.ac.jp/crid/1573668924705145728?lang=en. (accessed 15.05.2025).

Koedinger, K. R., Corbett, A. T., & Perfetti, C. The Knowledge-Learning-Instruction (KLI) framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive Science, 2012, vol. 36, iss. 5, pp. 757–798. DOI: 10.1111/j.1551-6709.2012.01245.x.

Sharma, K., Papamitsiou, Z., & Giannakos, M. Building pipelines for educational data using AI and multimodal analytics: A “grey-box” approach. British Journal of Educational Technology, 2020, vol. 51, iss. 6, pp. 3004–3031. DOI: 10.1111/bjet.12854.

DSTU ISO/IEC/IEEE 42010:2018. Inzheneriya system i prohramnykh zasobiv. Opys arkhitektury (ISO/IEC/IEEE 42010:2011, IDT) [DSTU ISO/IEC/IEEE 42010:2018. Systems and software engineering. Architecture description (ISO/IEC/IEEE 42010:2011, IDT)]. Kyiv: Ministry of Economic Development of Ukraine. Available at: https://online.budstandart.com/ua/catalog/doc-page.html?id_doc=77960 (accessed 15.05.2025). (In Ukrainian).

Weiss, D. J. Improving measurement quality and efficiency with adaptive testing. Applied Psychological Measurement, 1982, vol. 6, iss. 4, pp. 473–492. DOI: 10.1177/014662168200600408.

Rasch, G. Probabilistic Models for Some Intelligence and Attainment Tests. Copenhagen: Danish Institute for Educational Research, 1960. 184 p. Available at: https://books.google.com.ua/books/about/Probabilistic_Models_for_Some_Intelligen.html?id=aB9qLgEACAAJ&redir_esc=y. (accessed 15.05.2025.)

van der Linden, W. J., & Glas, C. A. W. Elements of adaptive testing. Springer, 2010. DOI: 10.1007/978-0-387-85461-8

Wood, D., Bruner, J. S., & Ross, G. The role of tutoring in problem solving. Journal of Child Psychology and Psychiatry, 1976, vol. 17, iss. 2, 89–100. DOI: 10.1111/j.1469-7610.1976.tb00381.x.

Shaffer, F., & Ginsberg, J. P. An overview of heart rate variability metrics and norms. Frontiers in Public Health, 2017, vol. 5, article no. 258. DOI: 10.3389/fpubh.2017.00258.

Malik, M., Bigger, J. T., Camm, A. J., Kleiger, R. E., Malliani, A., Moss, A. J., & Schwartz, P. J. Heart rate variability: Standards of measurement, physiological interpretation, and clinical use. Circulation, 1996, vol. 93, iss. 5, pp. 1043–1065. DOI: 10.1161/01.CIR.93.5.1043.

Kim, H. G., Cheon, E. J., Bai, D. S., Lee, Y. H., & Koo, B. H. Stress and heart rate variability: A meta-analysis and review of the literature. Psychiatry Investigation, 2018, vol. 15, iss. 3, pp. 235–245. DOI: 10.30773/pi.2017.08.17.