This work was carried out as part of research on the development of methods for the intelligent analysis of medical thermometric data. These methods are designed to create a consultative intelligent system for the diagnosis of breast cancer. In this work, an artificial neural network has been obtained, which allows localization of a tumor according to microwave thermometry data. The network uses the architecture of deep belief networks. In cases where the tumor does not coincide and is not near the hottest point of the breast, the neural network can reach an accuracy of over 56% on test samples. This result exceeds the previous one by 13%.

Keywords: microwave thermometry, breast cancer, mammology, tumor localization, fidelity, data mining, artificial neural networks, deep learning, thermometric diagnostic features, cross-validation

This work was carried out as part of research on the development of methods for the intelligent analysis of medical thermometric data. These methods are designed to create a consultative intelligent system for the diagnosis of breast cancer. We propose a new approach to the formation of a feature space based on microwave radiothermometry data that are designed to detect malignant tumors. In the process, about 200 new signs were obtained and tested. Based on them, we created an algorithm for the localization of tumors in the mammary gland. This algorithm is a weighted voting algorithm that is configured using a genetic algorithm. The resulting localization algorithm can achieve an accuracy over 70% in test samples.

Keywords: microwave thermometry, breast cancer, mammology, tumor localization, accuracy, data mining, genetic algorithm, weighted voting algorithm, thermometric diagnostic features, cross-validation

This paper presents two methods of computer simulation (quantum chemical analysis and molecular dynamics) of the interaction of additives with the iron surface. Quantum chemical interaction of silicate and phosphate additives with iron surface was carried out. The plate model was used for quantum chemical analysis, calculations were carried out in the DFT approximation. The method of molecular dynamics is based on the calculation of the evolution of the system of interacting particles of atoms and molecules by integrating the equations of their motion. It is shown that the oxidation of the surface leads to a decrease in the adhesion energy of both individual additives and their combinations, allowing to find the influencing factors on the behavior of tribosystems.

Keywords: lubricant, method, quantum chemical analysis, molecular dynamics, tribology, friction, computer simulation

A theoretical study of the mechanism of mixed (semifluid) the interaction of the solid lubricant lubricants shell rods with contact "wheel-rail." Methods for determination of the average standard resource shell lubricating grease solid rods and medium wear hard shell shell lubricants rods in various combinations shells at different ranges of temperatures. A fundamentally new way of tribology hard shell lubricants rods "shell holder - movie." Determined on the basis of laboratory tests the new composition of lubricating rods having good lubricity and increased resource consumption less lubrication at elevated temperatures of contact compared to a typical sample of lubricating rods.
Keywords: Mixed lubrication, solid lubricants shell cores, contact "wheel-rail", the average standard resource lubricant, the average wear of the shell, a new way of tribology "shell holder - movie."

Keywords: