Кафедра "Інформатика та інтелектуальна власність"

Постійне посилання колекціїhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/7444

Офіційний сайт кафедри http://web.kpi.kharkov.ua/iip

Кафедра "Інформатика та інтелектуальна власність" створена 12 травня 1999 року на факультеті "Комп'ютерні та інформаційні технології".

Саме в НТУ “ХПІ” на спеціальному факультеті патентознавства Міжгалузевого інституту післядипломної освіти, у той час – підвищення кваліфікації, у 1992 році було розпочато перепідготовку спеціалістів відповідної кваліфікації, що стало початком створення національної системи підготовки кадрів для сфери інтелектуальної власності України.

Кафедра входить до складу Навчально-наукового інституту комп'ютерних наук та інформаційних технологій Національного технічного університету "Харківський політехнічний інститут".

Від 2019 року НТУ "ХПІ" та Науково-дослідний інститут інтелектуальної власності Національної академії правових наук України створтли на кафедрі "Інформатика та інтелектуальна власність" спільний Науково-освітній центр "Цифрова інтелектуальна власність".

У складі науково-педагогічного колективу кафедри працюють: 1 доктор технічних наук, 6 кандидатів технічних наук, 1 – історичних, 1 – юридичних; 1 співробітник має звання професора, 7 – доцента.

Переглянути

Зараз показуємо 1 - 6 з 6

Improving a neural network model for semantic segmentation of images of monitored objects in aerial photographs
(PC Technology Center, 2021) Slyusar, V.; Protsenko, M.; Chernukha, A.; Melkin, V.; Petrova, O.; Kravtsov, M.; Velma, S.; Kosenko, N.; Sydorenko, O.; Sobol, Maksym
This paper considers a model of the neural network for semantically segmenting the images of monitored objects on aerial photographs. Unmanned aerial vehicles monitor objects by analyzing (processing) aerial photographs and video streams. The results of aerial photography are processed by the operator in a manual mode; however, there are objective difficulties associated with the operator's handling a large number of aerial photographs, which is why it is advisable to automate this process. Analysis of the models showed that to perform the task of semantic segmentation of images of monitored objects on aerial photographs, the U-Net model (Germany), which is a convolutional neural network, is most suitable as a basic model. This model has been improved by using a wavelet layer and the optimal values of the model training parameters: speed (step) ‒ 0.001, the number of epochs ‒ 60, the optimization algorithm ‒ Adam. The training was conducted by a set of segmented images acquired from aerial photographs (with a resolution of 6,000×4,000 pixels) by the Image Labeler software in the mathematical programming environment MATLAB R2020b (USA). As a result, a new model for semantically segmenting the images of monitored objects on aerial photographs with the proposed name U-NetWavelet was built. The effectiveness of the improved model was investigated using an example of processing 80 aerial photographs. The accuracy, sensitivity, and segmentation error were selected as the main indicators of the model's efficiency. The use of a modified wavelet layer has made it possible to adapt the size of an aerial photograph to the parameters of the input layer of the neural network, to improve the efficiency of image segmentation in aerial photographs; the application of a convolutional neural network has allowed this process to be automatic.
The Input Material Flow Model of the Transport Conveyor
(Institute of Electrical and Electronics Engineers, Inc., 2022) Pihnastyi, O. M.; Sobol, Maksym
This paper discusses the problem of forming a data set for training a neural network used to build a model of a multi-section conveyor. The analysis of the models, which are used by designing the flow parameters control system of the transport system, is given. The conditions of applying a neural network in the transport conveyer model are justified and determined. Methods for generating a data set for training a neural network are discussed. As the main approach, the use of production data obtained from functioning transport conveyors is considered. Statistically processed data can be used to build generators of stochastic processes that model the incoming material flow for the transport system. The development of these generators to form the input flow of the material of the transport system opens up the possibility of analyzing and monitoring conveyor models in various modes of its configuration. A statistical analysis of the incoming material flow of the transport system was carried out and its number characteristics were determined. The correlation function characterizing the input flow of material for the transport system is considered. The introduction of dimensionless parameters to describe the input material flow made it possible to scale the results of work for a wide class of conveyor-type transport systems.
Method for binary contour images vectorization of handwritten characters for recognition by detector neural networks
(Institute of Electrical and Electronics Engineers, Inc., 2022) Parzhin, Yu. V.; Galkyn, Sergii; Sobol, Maksym
This paper describes the developed method for binary contour images vectorization of handwritten characters for recognition by detector neural networks. A description of the software that implements the developed method is given.
On the Characteristics of the Input Material Flow of the Transport Conveyor
(Vasyl Stefanyk Precarpathian National University, 2022) Pihnastyi, O. M.; Sobol, Maksym; Yelchaninov, D. B.
In this paper, the statistical characteristics of the flow of material entering the input of a conveyor-type transport system are studied. For a set of data obtained as a result of experimental measurements of the input flow of material, the law of distribution of a random variable and the correlation function is investigated. Theoretical assumptions about the law of change of the correlation function for the input flow of material are confirmed.
Usage of Mask R-CNN for automatic license plate recognition
(Національний технічний університет "Харківський політехнічний інститут", 2023) Podorozhniak, A. O.; Liubchenko, N. Yu.; Sobol, Maksym; Onishchenko, D. P.
The subject of study is the creation process of an artificial intelligence system for automatic license plate detection. The goal is to achieve high license plate recognition accuracy on large camera angles with character extraction. The tasks are to study existing license plate recognition technics and to create an artificial intelligence system that works on big shooting camera angles with the help of modern machine learning solution – deep learning. As part of the research, both hardware and software-based solutions were studied and developed. For testing purposes, different datasets and competing systems were used. Main research methods are experiment, literature analysis and case study for hardware systems. As a result of analysis of modern methods, Mask R-CNN algorithm was chosen due to high accuracy. Conclusions. Problem statement was declared; solution methods were listed and characterized; main algorithm was chosen and mathematical background was presented. As part of the development procedure, accurate automatic license plate system was presented and implemented in different hardware environments. Comparison of the network with existing competitive systems was made. Different object detection characteristics, such as Recall, Precision and F1-Score, were calculated. The acquired results show that developed system on Mask R-CNN algorithm process images with high accuracy on large camera shooting angles.
Use of analytical model for synthesis of algorithms for control of transport conveyor parameters
(Khmelnytskyi national university, 2022) Pihnastyi, O. M.; Sobol, Maksym
This study presents a methodology for synthesizing optimal control algorithms for the flow parameters of a conveyor-type transport system with a variable transport delay. A multi-section transport conveyor is a complex dynamic system with a variable transport delay. The transport conveyor is an important element of the production system, used to synchronize technological operations and move material. The Analytical PiKh-model of the conveyor section was used as a model for designing a control system for flow parameters. The characteristic dimensionless parameters of the conveyor section are introduced and the similarity criteria for the conveyor sections are determined. The model of a conveyor section in a dimensionless form is used to develop a methodology for synthesizing algorithms for optimal control of the flow parameters of a transport conveyor section. The dependencies between the value of the input and output material flow of the section are determined, taking into account the initial distribution of the material along the conveyor section, variable transport delay, restrictions on the specific density of the material, and restrictions on the speed of the belt. The dependencies between the value of the input and output material flow for the case of a constant transport delay are analyzed. A technique for synthesizing algorithms for optimal belt speed control based on the PiKh-model of a conveyor section is presented. As a simplification, a two-stage belt speed control is considered. Particular attention is paid to the methodology for synthesizing optimal control algorithms based on the energy management methodology (TOU-Tariffs). The criteria of control quality are introduced and problems of optimal control of flow parameters of the transport system are formulated. Taking into account differential connections and restrictions on phase variables and admissible controls, which are typical for the conveyor section, the Pontryagin function and the adjoint system of equations are written. As examples demonstrating the design of optimal control, algorithms for optimal control of the flow parameters of the transport system are synthesized and analysis of optimal controls is performed.