Search

The theory of pattern recognition is used in computers, in city's video surveillance cameras, when recognizing car license plates of the violators, for unlocking of smartphones, in drones, in security systems, etc. The paper is considering the solution to the problem of using image recognition methods for detecting road's signs. The purpose of the research is to develop a mobile application for the recognizing of road signs. The methodology includes a description of the stages of the video sequence for recognizing of road signs, choosing methods for their localization, classification and data storage in recognition systems. A significant result of the research is the development of a model based on convolutional neural networks for the classification of road signs. The developed model is used in a mobile application applying the methods of the libraries of computer vision. The application can be used by car drivers with installed file on the device and an autofocus camera. Testing of the application confirms its ability to perform the assigned tasks. In conclusion, findings are drawn about the effectiveness of the application. And options are proposed for improving the model for recognizing of road signs. [ABSTRACT FROM AUTHOR]

Due to the limited reserves of natural hydrocarbons, more and more attention has been paid to the problem of saving energy resources. Reducing energy consumption improves the environmental situation by decreasing harmful emissions to the atmosphere. In our country, despite the presence of significant reserves of oil, gas and coal, the costs of their production and transportation are constantly growing. Nevertheless, insufficient attention is paid to solving the problems of energy-saving control of MIMO energy-consuming industrial and domestic facilities, although theoretical studies have shown that optimal control can reduce energy costs or fuel consumption by 15–20% or more compared to traditional systems. Such facilities include multi-zone electric furnaces, multi-section drying installations, boiler installations, multi-drive machines and other installations operating on hydrocarbon fuels or electricity. Such facilities are used in housing and communal services, industrial enterprises and in everyday life. The development of a methodology for building intelligent systems of energy-saving control of MIMO process systems on a set of operating states is a fundamental problem for the industry. The solution of this problem is connected with the development of methods for solving a whole complex of diverse and complex problems, including those associated with the creation of models, methods and algorithms that minimize the cost of energy resources in the operation of MIMO systems taking into account possible changes in the state of functioning in actual operation. The paper considers the synthesis of algorithms for energy-efficient control actions for intelligent control of MIMO technological systems. The problems of synthesis and algorithmic support for their solution are explored using the example of a five-section electric convection heater RO400FC-C. The proposed algorithms are used for different operation conditions-heating, temperature maintenance, and an emergency mode associated with failures of individual heating elements during operation of the heater. [ABSTRACT FROM AUTHOR]