The article discusses the problem of detecting sick or mechanically damaged potatoes using machine learning methods. We proposed an algorithm and developed a system for the rapid detection of damaged tubers. The system can be installed on a conveyor belt in a vegetable store, and it consists of a laptop computer and an action camera, synchronized with a flashlight system. The algorithm consists of two phases. The first phase uses the Viola-Jones algorithm, applied to the filtered action camera image, so it aims to detect separate potato tubers on the conveyor belt. The second phase is the application of a method that we choose based on video capturing conditions. To isolate potatoes infected with certain types of diseases (dry rot, for example), we use the Scale Invariant Feature Transform (SIFT)—Support Vector Machine (SVM) method. In case of inconsistent or weak lighting, the histogram of oriented gradients (HOG)—Bag-of-Visual-Words (BOVW)—neural network (BPNN) method is used. Otherwise, Otsu’s threshold binarization—a convolutional neural network (CNN) method is used. The first phase’s result depends on the conveyor’s speed, the density of tubers on the conveyor, and the accuracy of the video system. With the optimal setting, the result reaches 97%. The second phase’s outcome depends on the method and varies from 80% to 97%. When evaluating the performance of the system, it was found that it allows to detect and classify up to 100 tubers in one second, which significantly exceeds the performance of most similar systems.

This article deals with the multicriteria programming model to optimize the time of completing home assignments by school students in both in-class and online forms of teaching. To develop a solution, we defined 12 criteria influencing the school exercises’ effectiveness. In this amount, five criteria describe exercises themselves and seven others the conditions at which the exercises are completed. We used these criteria to design a neural network, which output influences target function and the search for optimal values with three optimization techniques: backtracking search optimization algorithm (BSA), particle swarm optimization algorithm (PSO), and genetic algorithm (GA). We propose to represent the findings for the optimal time to complete homework as a Pareto set.

The problem of the effectiveness of teaching can be successfully solved only if the high quality of lessons is supported by well-organized homework of students. The question of homework occupies one of the main places in educational activities since this question is directly related to the health of the child. A competent approach to minimizing the time for completing homework, taking into account the maximum efficiency obtained from the learning process, can preserve the health of students to some extent. The article describes a method for obtaining the most comfortable results of the process of completing homework, which are a Pareto set. This method is implemented using a genetic algorithm and queuing theory, and the selection of homework is carried out on the basis of intellectual analysis of the text of tasks and is a scale of a certain range. The proposed algorithm successfully obtains the solutions of the Pareto set and minimizes the efforts of school students while achieving the maximum efficiency of the educational process to preserve their health. Compared with other known algorithms, the results obtained show that the proposed algorithm demonstrates fairly accurate optimization characteristics presented in the form of a Pareto set. Furthermore, combining a genetic algorithm, queuing theory apparatus, and a neural network makes it possible to model the studied subject area more accurately.

Achieving national technological sovereignty is a complex problem that combines the tasks of social and industrial development. The article contains the results of a study on elaborating mechanisms for harmonizing the target social and economic indicators leading to technological sovereignty as a general purpose.

With the rapid growth in the use of credit cards in electronic payments, financial institutions and financial service providers are becoming vulnerable to fraud, which leads to huge losses every year. The development and implementation of an effective credit card fraud detection system is essential to reduce such losses. The presented paper analyzes current scientific work in the field of developing methods and models of artificial intelligence to ensure the security of financial transactions. The purpose of this paper is to review and compare machine learning models and methods for conducting secure financial transactions using credit cards. The above publications in this area mainly use a data set on fraudulent credit card transactions collected from European cardholders. It also mentions publications that use both synthetic and other datasets. Among the machine learning algorithms used in these publications, the effectiveness of decision trees, random forests, SVM, logistic regression and other methods on anonymized credit card fraud data, as well as algorithms using neural networks, is investigated and tested. The researchers apply these methods to preprocessed data samples. To assess the quality of the machine learning model, various special metrics are considered in classification tasks, such as accuracy, completeness, F-measure, etc. А comparative analysis of these publications has revealed several of the most preferred and effective methods for processing financial transactions.