Today, achieving high accuracy in real-time object recognition is an urgent problem in many fields, such as computer vision, autonomous vehicles, medical diagnostics, and many others. The rapid development of technology and the increasing amount of available data have made it possible to use machine learning and neural networks to achieve this goal.
In this thesis, we have developed an automated photometric system for object recognition. In the first part of the work, different types of automated systems for object recognition are considered and analyzed. Different approaches to the implementation of computer vision are analyzed. Neural networks, including various types of neural networks and convolutional networks, are discussed in detail. Particular attention was paid to the overview of frameworks used in this area, as well as applications for data collection and data markup.
In the practical part of the work, the system's block diagram and algorithm were developed, and the selection of hardware and software components was made. The data collection process was also reviewed. Mathematical modeling of neural network training was performed and the results were analyzed.

Hits: 57

The aim of the project is to develop and implement an automated meter capable of effectively measuring the residual magnetic field in ferromagnetic products. During the project development, the task of designing the meter was successfully addressed, including calculations for the number of turns in the measurement winding and the total active and reactive power required for fluxgate excitation. The graphic part of the project presents the structural diagram of the device, functional diagram, assembly drawing of the meter, and electrical schematic.
Key aspects of the project include the development of a fluxgate transducer, which is the main component of the meter, and the study of methods and means for accurate measurement of the residual magnetic field in ferromagnetic materials.

Hits: 79

This bachelor thesis is devoted to the study of heating systems of private houses and pump automation in these systems.
The work reviewed various heating systems, focusing on solid fuel single-circuit boilers, and also investigated the principles of operation of pumps and existing heating systems. The work also includes conclusions and an overview of the problem.
The paper describes the presented version of pump automation. The principle of operation of the device is considered, as well as an overview of the elements used in the subsystem. The electrical schematic diagram and calculated elements in the diagram are described. The principle of operation of the Arduino Uno microcontroller board in the subsystem is also explained in detail.

Hits: 74

This thesis is devoted to the development of software for analyzing ultrasound images for the purpose of diagnosing polycystic ovaries. In this work, the research of computer vision tools was carried out and the peculiarities of ovarian polycystic disease diagnosis were studied. An experimental system has been developed that uses a convolutional self-designed neural network and the Grad-Cam visualization method for classifying and detecting polycystic ovaries on ultrasound images. The results of the study showed the effectiveness of the developed system, which allows to automate the diagnostic process and facilitate the rapid and accurate identification of polycystic ovaries from ultrasound data.

Hits: 63

The work is devoted to the development of an optical device for controlling the humidity of fabrics in the textile industry. At the current stage of technical development, the automation of technological process management and quality control is of great importance, particularly in the textile industry, where it has a significant economic effect. An optical device for monitoring the humidity of fabrics is necessary in the textile industry.
In the course of the research, the spectral characteristics of wet materials were studied. We were able to see the principle of operation of optoelectronic moisture meters. Also, the principles of construction of well-known IR hygrometers were highlighted. Structural, optical, functional and electrical schematics of the device were developed. The reliability indicators of the device were also calculated and an error analysis was carried out.

Hits: 61

  1. Ovsianikov О. Improving efficiency of neural networks by augmentation methods
  2. Zemliakov O. Automated control system for laser engraving and cutting process
  3. Hryshyn D. Contact-measuring system of coordinate measuring machine
  4. Charnosh A. Automated eddy current system for thickness measurement of aluminum coating during mirror production

Page 5 of 18

АСНК КПІ ім. Ігоря Сікорського, 2021