In the era of data technologies for medical diagnostic cognitive software systems, new informative data has been obtained based on topological data analysis in the form of Betti numbers. These new, more informative data can be applied to medical diagnostic cognitive software systems and obtain a higher accuracy in the diagnosis of neurodegenerative diseases, which is extremely important, since the choice of a patient's treatment protocol depends on their accuracy. The higher accuracy of the functioning of medical diagnostic cognitive software systems is achieved due to the fact that new informative data are topological data, which in their values take into account the nature of the topological structure of experimentally measured data in the form of electroencephalographic (EEG) signals characterizing the activity of the patient's brain. On the basis of experimental data - EEG signals and methods of data science - topological data analysis, new more informative topological data were obtained for the development of high-precision medical diagnostic cognitive software systems in neurology. The scientific approach is based on the methods and analytical techniques of algebraic topology, in particular, the theory of categories and simplicial geometry (simplicial complexes). In particular, topological data – Betti numbers, obtained on the basis of topological analysis of data on experimentally measured EEG signals of the human brain, represent the number of simplexes with holes of different dimensions of the Vietoris-Rips simplex complex.

1. Pastukh O. et al. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies. Sci. J. TNTU, vol. 115, no. 3, pp. 82–90.

2. Pastukh O. et al. (2024). Robustness of AI algorithms for neurocomputer interfaces based on software and hardware technologies. CEUR Workshop Proceedings, 3742, pp. 137–149.

3. Petryk M. et al. (2023). Processing of Cerebral Cortex Neurosignals from EEG Sensors and Recognizing Specific Types of Mechanical Movements Elements of Pacient Limbs under the Cognitive Feedback Influenses. CEUR Workshop Proceedings, 3468, pp. 61–70.

4. Petryk M. et al. (2024). Multi-sensor analysis of cognitive signals for neurological disorders and diseases. CEUR Workshop Proceedings, 3742, pp. 304–315.

5. Stefanyshyn V. et al. (2023) Mathematics and software for controlling mobile software devices based on brain activity signals. CEUR Workshop Proceedings, 3628, pp. 684–689.

6. Palamar A. et al. (2023) Real-time Health Monitoring Computer System Based on Internet of Medical Things. CEUR Workshop Proceedings, 3628, pp. 672–683.

 

1. Pastukh O. et al. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies. Sci. J. TNTU, vol. 115, no. 3, pp. 82–90.

2. Pastukh O. et al. (2024). Robustness of AI algorithms for neurocomputer interfaces based on software and hardware technologies. CEUR Workshop Proceedings, 3742, pp. 137–149.

3. Petryk M. et al. (2023). Processing of Cerebral Cortex Neurosignals from EEG Sensors and Recognizing Specific Types of Mechanical Movements Elements of Pacient Limbs under the Cognitive Feedback Influenses. CEUR Workshop Proceedings, 3468, pp. 61–70.

4. Petryk M. et al. (2024). Multi-sensor analysis of cognitive signals for neurological disorders and diseases. CEUR Workshop Proceedings, 3742, pp. 304–315.

5. Stefanyshyn V. et al. (2023) Mathematics and software for controlling mobile software devices based on brain activity signals. CEUR Workshop Proceedings, 3628, pp. 684–689.

6. Palamar A. et al. (2023) Real-time Health Monitoring Computer System Based on Internet of Medical Things. CEUR Workshop Proceedings, 3628, pp. 672–683.