Перегляд за автором "Megel, Y. E."
Зараз показано 1 - 5 з 5
Результатів на сторінку
Варіанти сортування
Публікація A method for determining the parameters of an optical system during the spatial scanning of a biological solution(Технический университет - София - Технологии, 2018) Rybalka, A. V.; Megel, Y. E.; Kalimanova, I. I.; Shlyakhov, V. V.; Kovalenko, S. I.; Kovalenko, S. N.In research, control of biological processes for determining the motility of microorganisms, (estimation of the impact of chemical compounds, electrophoretic mobility, evaluation of severity of pathology, etc.) using a scanning optoelectronic system as the most effective means of solving applied problems, it is necessary to determine the objects number in the optical system field of vision since the measurement accuracy of the solution concentration and the objects motion speed in the solution depend on their number. In the article a probabilistic method for estimation the number of objects and the number of frames during frame-by-frame filming for providing a given accuracy with a given probability is presented.Публікація Assessment of the effectiveness of laser-acoustic transformation(Technical University of Sofia, 2019) Rybalka, A. I.; Megel, Y. E.; Kalimanova, I.For some biotechnological technologies, there is a problem of separating living cells or destroying their membranes in order to obtain individual elements of the inner structure of the cell. This is usually done using microsurgical operations. In practice, the method of obtaining individual cell fragments without surgery using an acoustic wave is of interest. In this paper, a mathematical model and the results of modeling the process of the formation of an acoustic pressure wave in a liquid biological solution for the destruction of the membrane of a biological object is considered.Публікація Cattle breed identification and live weight evaluation the basis of machine learning and computer vision(Національний університет "Запорізька політехніка", 2020) Megel, Y. E.; Rudenko, O. G.; Bezsonov, O. O.; Rybalka, A. I.The problem of the cow’s live weight estimation is considered. A convolutional neural network based method for animal recognition and its breed identification in combination with epipolar geometry approach for object’s size measurement is proposed. Information regarding animal’s size and its breed is further used for LW estimation by multilayer perceptron based predictive model. This approach can be used to replace traditional methods of direct observation and measurement. The proposed system can be widely used in the management of a modern farm. Accuracy and performance of the proposed method has been tested with the participation of the experts.Публікація Information System for Automating Processes of Biological Objects Detection, Recognition, and Measurement(Sofia Technical University, 2021) Megel, Y. E.; Kuzenko, A. S.; Blagov, I.; Kovalenko, Sv.; Kovalenko, Ser.; Malko, M.; Rybalka, А. І.The article briefly describes the existing and proposes novel approaches to the detection, estimation of the number and measurement of physical parameters of biological objects in the frames of computer vision systems. The object detection method is based on a two-stage algorithm: at the first stage, the approximate position of the object is determined using edge detection algorithms; at the second stage, graphic models of the object are built by creating graphical primitives. An algorithm for constructing graphical primitives is developed using the color of a biological object as a parameter. The presence of the second stage can significantly reduce both false positive and false negative results. To implement the presented model theoretical studies and practical experiments are carried out. During experiments, it was revealed that the proposed approach allows increasing the accuracy of determining biological objects, since it works with a color image and, accordingly, uses the ranges of digital color channels. In addition, the construction of graphical primitives, taking into account color ranges, makes it possible to estimate the physical characteristics of a biological object. The proposed two-stage technique for the automatic determination of biological objects makes it possible to solve the problems of positioning ultraviolet and low-frequency laser devices for point irradiation. The presence in the algorithm of the stage of constructing graphical primitives on biological objects makes it possible to estimate the degree of fatness of the animal, which is one of the components of determining its state of health, and can be part of an automatic system for contactless determination of the animal's weight.Публікація Measuring multimedia content proximity via artificial intelligence methods(Technical University of Sofia, 2020) Rybalka, A. I.; Megel, Y. E.; Mikhnova, O.The paper describes existing and novel approaches to word sequence similarity measuring which uses image processing procedures to reveal proximity relations between words and their meaning. This is implemented due to the fact the each word sequence can be associated with a particular pictorial domain, and thus any textual information can be potentially presented via an image series. Theoretical results of rule based approach, genetic algorithms and neural networks application are analyzed in terms of solving the problem under study. The proposed information processing technology may be useful for automatic translation applications, known as CAT-tools by now, search engine optimization, etc.