The paper is devoted to the problems of creating intelligent information systems for solving various medical problems taking into account the personalized approach. The current state of personalized medicine is considered, the main requirements for a personalized medical system are formulated, and the architecture of a typical system is proposed. The actuality of creating such systems, the scientific novelty of the proposed approach and its practical value are emphasized. The software components of the system that meet the listed requirements are described. The choice of methods and tools to ensure their development and operation is substantiated. The system with the described structural components and functional capabilities will contribute to more effective interaction between doctors and patients, raising the medical care quality and improving the treatment results.

This article provides a comprehensive analysis of network traffic balancing methods in high-load networks. It examines fundamental load distribution principles, including requirements for maintaining TCP session integrity and specific aspects of network flow identification. The study offers a detailed investigation of modern load balancing algorithms – from classical ECMP to advanced solutions based on consistent hashing, HRW, and Maglev. Particular attention is given to the selection of optimal hash functions for network flow identification and comparative analysis of different methods’ characteristics. The presented results enable the development of recommendations for choosing balancing strategies in various operational scenarios of high-load network infrastructures.

This article presents a review and comparative analysis of modern methods for correcting optical distortions in astrophotography acquired under conditions of atmospheric turbulence. The study investigates the physical and theoretical foundations of distortion formation, including atmospheric turbulence, optical aberrations, and noise inherent to the image acquisition process. The objective of this work is to systematize existing approaches and identify the most effective methods applicable to both amateur and professional astrophotography. The analysis covers image resolution restoration algorithms such as classical deconvolution (including the Richardson–Lucy algorithm and Wiener filtering), blind deconvolution, multi-frame processing, and neural network-based techniques. The results of the comparative analysis demonstrate that multi-frame algorithms and neural network approaches exhibit the highest efficiency under constrained computational resources and incomplete knowledge of the point spread function.

With the rapid development of artificial intelligence and machine learning technologies, access to structured and understandable information in the field is becoming critical for both specialists and a wide range of users. Existing resources often suffer from data fragmentation, lack of systematization, and difficulty in navigation. This paper is devoted to the development of a prototype Internet resource [1] that would solve these problems and provide users with access to an extensive knowledge base on machine learning, including descriptions of algorithms, methods, tools, and examples of their application.

The possibility of improving the quality of cardiovascular disease diagnostics by using machine learning is presented. The article discusses digital equipment for obtaining audiograms. A data set for machine learning of a cardiovascular  disease classification model is described. One of the sections is devoted to the development of a web application for remote diagnostics using the obtained model.

Recent advances in machine learning have introduced a novel approach to database indexing known as learned indexes. Among these, the RadixSpline index has emerged as a particularly promising solution for efficient search in sorted key-value data. This paper presents a comprehensive analysis and performance evaluation of the RadixSpline index, which combines spline approximation with bounded error (GreedySpline) and a sparse radix table structure. We investigate the index’s behavior under different parameter configurations, focusing on two key parameters: the spline approximation error (err) and the radix prefix length (r). Our experimental study, conducted on a 25 MB subset of the MovieLens32M dataset, demonstrates that RadixSpline can achieve up to 30% faster search times compared to traditional binary search while reducing memory usage by over 80 % compared to RocksDB’s sparse index implementation. The study makes several important contributions: (1) we provide a detailed analysis of parameter sensitivity, identifying optimal configurations for various use cases; (2) we address implementation challenges not covered in the original work, including handling of non-contiguous prefixes and missing keys; (3) we demonstrate the index’s suitability for real-time applications through its single-pass construction property. Our results confirm that RadixSpline offers significant advantages over conventional indexing methods, particularly in scenarios requiring fast searches with limited memory resources. The findings suggest strong potential for integrating RadixSpline into production database systems, with RocksDB being a particularly promising candidate for such integration.

Modern high-load applications place high demands on garbage collector systems, which are used in programming languages, in particular in Golang. This article is aimed at a systematic study of the GOGC parameter and its impact on the key performance indicators of the test application. The measurement results of selected key metrics, such as the number of GC starts and duration, and the amount of allocated memory, were visualized using tables and graphs. The article analyzes the behavior of the GC mechanism and the effect of the GOGC parameter on it. The research results allow developers of high-load applications to put them into practice to manage the garbage collection mechanism, dependingon the tasks that need to be solved.