The master's thesis developed an automated system for assessing the quality and effectiveness of cardiopulmonary resuscitation. The explanatory note contains the following components: a list of symbols and abbreviations, an introduction, four sections of the main material, the development of a startup project, conclusions and a list of references to the sources used. In total, the master's thesis contains 102 pages, 18 figures, 30 tables and 30 references.
Purpose and objectives. Development of an automated system for assessing the quality and effectiveness of cardiopulmonary resuscitation designed to help lay rescuers who are forced to perform resuscitation measures directly at the scene of an accident, before the arrival of medical workers.

In the current conditions of industrial development and increasing requirements for the reliability and safety of technical objects, non-destructive testing methods are becoming particularly relevant. Magnetic particle testing is one of the most effective methods for detecting surface and subsurface defects in ferromagnetic materials. At the same time, traditional methods of magnetic particle inspection are largely dependent on the human factor, which reduces the reproducibility and objectivity of the results.
The relevance of this study is determined by the need to automate the processes of recording, processing, and analyzing the results of magnetic particle inspection using modern methods of computer vision and artificial intelligence. The use of neural networks allows to significantly increase the accuracy of defect detection, reduce the influence of the operator, and ensure the stability of control.

In the modern era of rapid development of intelligent robotic systems, quadrupedal robots occupy a special place due to their high maneuverability and ability to adapt to complex, dangerous conditions (in particular, in the military and search and rescue fields). The relevance of the research is determined by a dual need: to create affordable prototypes for training and to develop a universal hardware and software platform that can be quickly and inexpensively modified for specialized tasks (e.g., integration of a thermal imager, GPS, more powerful engines). Existing industrial analogues, such as Spot, are too expensive and have a closed architecture, which makes it impossible to use them widely as a basis for R&D prototyping in educational and research institutions. That is why the development of an affordable and modifiable prototype is of great strategic and practical importance.

The dissertation is devoted to the development and justification of an automated ultrasonic therapy system for the human eye, intended for non-invasive therapeutic impact on biological tissues aimed at treatment and stimulation of regenerative processes.
    The object of the research is the process of ultrasonic transducer interaction with the tissues of the human eye.
    The subject of the research is methods for improving the efficiency of therapeutic ultrasound.
    The scientific novelty lies in the creation of a universal multifunctional system for generating therapeutic signals and a new design of an ultrasonic transducer with increased efficiency in human eye therapy, as well as in the development of a method for continuous contact monitoring during therapy.

In the master's thesis, an automated ultrasonic skin regeneration system based on the digital generation of an ultrasonic signal with a Sinc waveform was developed and investigated. The work is dedicated to solving the relevant scientific and technical task of creating compact, energy-efficient, and affordable medical equipment for dermatology and aesthetic medicine.
The relevance of the master's thesis topic is conditioned by the rapid development of non-invasive therapy methods, among which ultrasonic exposure occupies a leading position due to its safety and proven effectiveness in stimulating regenerative processes. Existing devices for ultrasonic therapy on the market are predominantly built on traditional analog circuitry, which leads to significant dimensions, high energy consumption due to the low efficiency of output stages, and high production costs. Furthermore, analog generators have limited capabilities regarding flexible control of the signal's shape and spectral composition, which reduces the selectivity of the therapeutic effect.

Page 1 of 29

АСНК КПІ ім. Ігоря Сікорського, 2021