Сучасні інформаційні системи

Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/62915

У журналі публікуються результати досліджень з експлуатації та розробки сучасних інформаційних систем у різних проблемних галузях.

Рік заснування: 2017. Періодичність: 4 рази на рік. ISSN 2522-9052 (Print)

Новини

Включений до "Переліку наукових фахових видань України, в яких можуть публікуватися результати дисертаційних робіт на здобуття наукових ступенів доктора і кандидата наук" (технічні науки) наказом Міністерства освіти і науки України від 04.04.2018 № 326 (додаток 9, п. 56).

Переглянути

Зараз показуємо 1 - 3 з 3

A system for monitoring the progress of rehabilitation of patients with musculoskeletal disorder
(Національний технічний університет "Харківський політехнічний інститут", 2024) Barkovska, Olesia; Oliinyk, Dmytro; Sorokin, Anton; Zabroda, Ivan; Sedlaček, Peter
The work is devoted to the development of a system for monitoring the rehabilitation process of patients with musculoskeletal disorders, as well as identifying possible postural distortions in both children and adults based on anthropometric data, which confirms the relevance and practical significance of the work during the period of military operations in Ukraine and a large number of people with musculoskeletal injuries. The paper proposes a model of a system consisting of two subsystems: a subsystem for collecting pododynamic parameters based on a dynamic baropodometric platform and a visual posture monitoring subsystem. The combination of different gait and posture analysis methods in a single system provides high diagnostic and prognostic value. The main purpose of the proposed system is to monitor the progress of patient rehabilitation using hardware and computer-optical diagnostic methods without radiation exposure with the ability to easily transport the created system, the possibility of high-precision diagnostics in real time, as well as the ability to store and analyze changes in the musculoskeletal system over time. For the collection and analysis of pododynamometric parameters, computer data visualization methods, methods of statistical and dynamic data analysis, and data segmentation methods were used. To collect and analyze anthropometric parameters, methods of detecting objects in the image, methods of computer classification, segmentation and image processing, methods of analyzing graphic information were used. In addition, the paper researches the influence of marker characteristics (shape, color model of representation) and lighting conditions during the acquisition of kinematic parameters on the accuracy of marker detection for further determination of the angles of the pelvis and shoulder line.
Analysis of text augmentation algorithms in artificial language machine translation systems
(Національний технічний університет "Харківський політехнічний інститут", 2023) Havrashenko, Anton; Barkovska, Olesia
The work is devoted to the development of an organizational model of the machine translation system of artificial languages. The main goal is the analysis of text augmentation algorithms, which are significant elements of the developed machine translation system at the stage of improvement of new dictionaries created on the basis of already existing dictionaries. In the course of the work was developed a model of the machine translation system, created dictionaries based on texts and based on already existing dictionaries using augmentation methods such as back translation and crossover; improved dictionary based on algorithms of n-grams, Knuth-Morris-Pratt and word search in the text (such as binary search, tree search, sqrt decomposition). In addition, the work implements the possibility of using the prepared dictionary for translation. Obtained results can improve existing systems of machine translation of the text of artificial languages. Practical significance of this work is the analysis and improvement of text augmentation algorithms by changing the prefix tree type. Compared to the conventional algorithm, the improved algorithm reduced the memory usage by almost 13 times, which allows it to be used on much larger test data. This was achieved by changing the internal system of the node of the prefix tree from constant references to an expandable list.
Study of noise reduction methods in the sound sequence when solving the speech-to-textproblem
(Національний технічний університет "Харківський політехнічний інститут", 2022) Barkovska, Olesia; Kholiev, Vladyslav; Lytvynenko, Vladyslav
The subject of this research is noise reduction methods in the sound sequence as a part of the proposed speech-to-text (STT) module for converting a verbal lecture or a lesson into a written text form ondigital educational platforms.The goalis to investigate the influence of noise reduction methods on the operation of the acoustic signal recognition system. 3 methodsof noise reduction were considered for integration in the proposed acoustic artifact recognition system and for the researching: spectral subtraction method; fast Fourier transform; Wiener filter withsoftware modelingof every method. The obtained results: after testing the system with integrated noise reduction modules in it, based on the fast Fourier transform, Wiener filter and spectral subtraction method, it was concluded that the module using the Wiener filter improves the identification results by 25%, which is the highest result. However, performance testing has shownthat fast Fourier transform is the fastest method.The practical significanceof the work is –the identifying acoustic events system was developed, different noise reduction methods were integrated and researched into the module for converting a verbal lecture or a lesson into a written text form in a proposed system with the aim of increasing of speed and accuracy.