Registration Number
0224U031597,
0122U001731
, R & D reports
Title
Development of theoretical foundations and new methods of processing, recognition, forecasting of human-oriented processes and systems to solve problems of artificial intelligence
popup.stage_title
Head
Krak Yurii V., Доктор фізико-математичних наук
Registration Date
22-05-2024
Organization
Taras Shevchenko National University of Kyiv
popup.description2
The creation and theoretical substantiation of new models of presenting the information obtained about the socially significant state of a person from various sources is proposed. New methods of artificial intelligence, machine learning, neurocomputation, construction of classifiers for human-oriented data research were developed. The stability conditions and assessment of the convergence of the dynamic learning processes of artificial discrete neural networks described in terms of differential equations with the aftereffect were studied. The functioning of Hopfield's artificial discrete neural network was considered. Using the direct Lyapunov method, conditions for the absolute stability of solutions for differential equations and systems that modelling the operation of discrete neural networks have been established and rigorously proven. New methods of processing, recognizing, forecasting of human-oriented processes using small data in the field of health care, improving the quality of life and education were developed. New learning technologies related to improving the processes of teaching the mathematical subjects in English using modern information technologies and elements of artificial intelligence were proposed. Methodological problems of a collaborative approach in online teaching of mathematical disciplines using Google Workspace for Education tools were considered. New methods of data analysis of electrocardiogram monitoring for diagnosis, prevention and treatment of cardiovascular diseases were developed. Machine learning algorithms were built based on convolutional neural networks for processing and analysing the human-oriented information. Using the random fields in convolutional neural networks for various tasks in deep learning and data analysis is considered, the properties of random fields are investigated.
Product Description
popup.authors
Volchyna Iryna I.
Kasianiuk Veda S.
Pashko Anatolii O.
Stelia Оleh B.
Khusainov Denys Ya.
Andrii V. Shatyrko
popup.nrat_date
2024-05-22
