This article takes on solving the problem of multicriteria conditional optimization. This problem is one of the most key tasks of the current time and has its application in many areas. Reuse of various existing algorithms for solving unconstrained optimization is proposed. Different methods of multicriteria unconditional optimization are reviewed. The advantages and disadvantages of each algorithm are analyzed. The algorithms modified to take into account the constraints. Additional algorithms of transition from solving an unconditional optimization problem to a conditional optimization problem are developed. A genetic algorithm SPEA2 was used to test the developed algorithms. Examples of solving the problem at hand using the aforementioned algorithms are presented. A comparative analysis of the final results was conducted.
The article is devoted to the automatic detection and recognition of traffic signs system design which processes the images received from the vehicle digital video recorder. The digital video recorder is used both for its intended purpose and to include it in the process of driving, facilitating the driver's work and, thus, significantly increasing safety and driving comfort. The analysis of the solution of the problem of detection and recognition of traffic signs based on the use of convolutional neural networks is carried out. It is shown that the greatest advantage from the point of view of the criteria of accuracy and speed of response has the single shot multibox detector method. The learning of neural network is done based on traffic signs (adopted in Ukraine) learning sample The study showed that the proposed approach for all used datasets gave both the best recognition quality and maximum performance.
The problem of forming a training set for the task of image processing is considered. It is shown that this task is of great importance in the construction of intelligent medical diagnostic systems in which convolution neural networks are used for image processing (results of ultrasound, CT and MRI). Due to the lack of elements of the training sample, it is proposed, on the one hand, to use approaches of artificial data multiplication based on the initial training sample of a fixed volume, and on the other hand, to use methods that reduce the need for large training samples, both through the use of ensemble topology (hybrid neural networks), and by applying the transfer learning approach. An algorithm for the formation of a training set for image processing tasks is developed based on the modification of the initial input information with the calculation of the confidence measure of the obtained sample.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.