The subject of this article is the development of a behavior pattern with AI elements for an opponent bot in the single-player game Steal Tower. The essence of which is to collect resources to build a tower faster than opponents. To create the illusion that the same people are playing against the player, an imitation stochastic model based on the Monte Carlo method for Markov chains has been developed. Based on the results of its tests, balanced system parameters were determined, which are embedded in the behavioral pattern of the bot, which is implemented using the Enum AIStates enumeration consisting of five states: Idle (inactivity), GoTo (movement) and GoToWarehouse (return to the warehouse), Win (victory), Loose (scoring). Each of them has developed functions for the optimal behavior of the bot given in the article. So for the GoTo state, functions have been created that analyze the benefits of different types of behavior: steal or collect, or walk to the warehouse or to the tower.

Keywords: game intelligence, behavioral pattern, live world emulation, bot behavior scenario, state structure, Markov chains, Monte Carlo method, simulation model, Unity environment, C# language

The article discusses methods for optimizing floating point calculations on microcontroller devices. Hardware and software methods for accelerating calculations are considered. Algorithms of Karatsuba and Schönhage-Strassen for the multiplication operation are given. A method for replacing floating-point calculations with integer calculations is proposed. Describes how to use fixed point instead of floating point. The option of using hash memory and code optimization is considered. The results of measuring calculations on the AVR microcontroller are presented.

Keywords: floating point calculations, fixed point calculations, microcontroller, AVR, ARM

The article discusses the application of machine vision methods for embedded systems using modern microcontrollers. Machine learning methods that are used in embedded systems to solve recognition problems, as well as neural network models, are described. The use of trained models for solving image recognition problems in embedded systems is proposed. The architectures of YOLOv3 and R-CN neural networks are compared. The Jetson TX2 hardware platform is considered. The results of comparing the calculation speed for different modes of the device are presented.

Keywords: machine vision, neural networks, artificial intelligence, embedded systems, pattern recognition, YOLO, RCN, Jetson, Tensorflow

The article describes the architectural techniques used in the process of developing case studies for assessing the professional skills of students, implemented as part of the educational process of the RSTU. The decision to use the interface as the center of architecture is justified. Possible problems in the process of developing the interface of the specified software are described, and ways of solving them are also presented. Thanks to the presented methods of building the project architecture, you can get rid of the main drawbacks associated with the dependence of the program code of the implemented product on the user interface. Increase the scalability and reliability of the application, while maintaining the overall quality and functionality.

Keywords: interface, user interface, architectural solution, loaded interface, software, pattern, messagebroker, coroutine, pseudo-stream, case

A description of the new assessment tools in the form of case tasks is given, which most fully reflect the level of mastering the professional competencies laid down in the study of the discipline. Case-meters include special problematic tasks, for the solution of which it is necessary to analyze the situation that requires updating the complex of professional knowledge. The results of this type of testing give a fairly complete picture of the professional and personal qualities of a specialist. The description of the developed special software for automatic checking of case tasks for assessing the professional skills of students in the discipline of the database is given.

Keywords: situational case, assessment tools, tests, assessment, case tasks, software application, design