All issues

This paper investigates the effectiveness of Retrieval-Augmented Generation (RAG) combined with various Large Language Models (LLMs) for document retrieval and information access in corporate information systems. We survey typical use-cases of LLMs in enterprise environments, outline the RAG architecture, and discuss the major challenges that arise when integrating LLMs into a RAG pipeline. A system architecture is proposed that couples a text-vector encoder with an LLM. The encoder builds a vector database that indexes a library of corporate documents. For every user query, relevant contextual fragments are retrieved from this library via the FAISS engine and appended to the prompt given to the LLM. The LLM then generates an answer grounded in the supplied context. The overall structure and workflow of the proposed RAG solution are described in detail. To justify the choice of the generative component, we benchmark a set of widely used LLMs — ChatGPT, GigaChat, YandexGPT, Llama, Mistral, Qwen, and others — when employed as the answer-generation module. Using an expert-annotated test set of queries, we evaluate the accuracy, completeness, linguistic quality, and conciseness of the responses. Model-specific characteristics and average response latencies are analysed; the study highlights the significant influence of available GPU memory on the throughput of local LLM deployments. An overall ranking of the models is derived from an aggregated quality metric. The results confirm that the proposed RAG architecture provides efficient document retrieval and information delivery in corporate environments. Future research directions include richer context augmentation techniques and a transition toward agent-based LLM architectures. The paper concludes with practical recommendations on selecting an optimal RAG–LLM configuration to ensure fast and precise access to enterprise knowledge assets.

The paper presents a hybrid artificial neural network model based on an architecture that incorporates a convolutional image encoder (CNN) and an attention module (Attention-based Multiple Instance Learning, Attention MIL). This module aggregates informative features from a sequence of frames capturing the flame spraying process. Additional technological parameters—air pressure, propane pressure, and standoff distance — are integrated into the model via a tabular channel, enabling it to account for the relationship between visual data and numerical process regime characteristics. The software implementation was developed using the Streamlit platform and the PyTorch library. It features an interactive interface for model training and result visualization, analysis of attention weights across frames, and a prediction mode for output characteristics: surface roughness ($R_a$) and the mass of the deposited coating ($m$). Experimental studies were conducted on data from real-world technological processes, and a comparative analysis of the accuracy of various model configurations was performed. The results demonstrate that the hybrid neural network, which combines visual and tabular features, achieves higher prediction accuracy compared to models using only a single modality. Furthermore, when comparing different implementations of the hybrid network, it was established that using the attention mechanism to process the series of flame spray images provides a significant increase in accuracy over a simple averaging of features without attention. The application includes an attention visualization module that creates a montage of the most significant frames and displays their attention weights, allowing users to identify which frames had the greatest influence on the prediction. The model’s capability for export to the ONNX format for integration into process control systems is also demonstrated. The proposed approach showcases the effectiveness of fusing visual and tabular information for manufacturing process monitoring tasks. The model can serve as a foundation for developing a decision support system or an automated quality control system for coatings produced by flame spraying. The limitations of the implemented model and prospects for its further development are also considered.

The article deals with the problem of a distributed system operation reliability. The system core is an open integration platform that provides interaction of varied software for modeling gas transportation. Some of them provide an access through thin clients on the cloud technology “software as a service”. Mathematical models of operation, transmission and computing are to ensure the operation of an automated dispatching system for oil and gas transportation. The paper presents a system solution based on the theory of Markov random processes and considers the stable operation stage. The stationary operation mode of the Markov chain with continuous time and discrete states is described by a system of Chapman–Kolmogorov equations with respect to the average numbers (mathematical expectations) of the objects in certain states. The objects of research are both system elements that are present in a large number – thin clients and computing modules, and individual ones – a server, a network manager (message broker). Together, they are interacting Markov random processes. The interaction is determined by the fact that the transition probabilities in one group of elements depend on the average numbers of other elements groups.

The authors propose a multi-criteria dispersion model of risk assessment for such systems (both in the broad and narrow sense, in accordance with the IEC standard). The risk is the standard deviation of estimated object parameter from its average value. The dispersion risk model makes possible to define optimality criteria and whole system functioning risks. In particular, for a thin client, the following is calculated: the loss profit risk, the total risk of losses due to non-productive element states, and the total risk of all system states losses.

Finally the paper proposes compromise schemes for solving the multi-criteria problem of choosing the optimal operation strategy based on the selected set of compromise criteria.

We have investigated dynamics of synthetic genetic oscillators — repressilators — coupled through autoinducer diffusion. The model of the system with phase-repulsive coupling structure is under consideration. We have examined emergence of periodic regimes, stable inhomogeneous steady states depending on the main systems’ parameters: coupling strength and maximal transcription rate. It has been shown that autoinducer production module added to the isolated repressilator cause the limit cycle to disappear through infinite period bifurcation for sufficiently large transcription rate. We have found hysteresis of limit cycle and stable steady state the size of which is determined by ratio between mRNA and protein lifetimes. Two coupled oscillators system demonstrates stable anti-phase oscillations which can become a chaotic regime through invariant torus emergence or via Feigenbaum scenario.

By numerical simulation methods the interaction processes of oscillating soliton (breather) with a 180-degree Neel domain wall in the framework of a (2 + 1)-dimensional supersymmetric O(3) nonlinear sigma model is studied. The purpose of this paper is to investigate nonlinear evolution and stability of a system of interacting localized dynamic and topological solutions. To construct the interaction models, were used a stationary breather and domain wall solutions, where obtained in the framework of the two-dimensional sine-Gordon equation by adding specially selected perturbations to the A3-field vector in the isotopic space of the Bloch sphere. In the absence of an external magnetic field, nonlinear sigma models have formal Lorentz invariance, which allows constructing, in particular, moving solutions and analyses the experimental data of the nonlinear dynamics of an interacting solitons system. In this paper, based on the obtained moving localized solutions, models for incident and head-on collisions of breathers with a domain wall are constructed, where, depending on the dynamic parameters of the system, are observed the collisions and reflections of solitons from each other, a long-range interactions and also the decay of an oscillating soliton into linear perturbation waves. In contrast to the breather solution that has the dynamics of the internal degree of freedom, the energy integral of a topologically stable soliton in the all experiments the preserved with high accuracy. For each type of interaction, the range of values of the velocity of the colliding dynamic and topological solitons is determined as a function of the rotation frequency of the A3-field vector in the isotopic space. Numerical models are constructed on the basis of methods of the theory of finite difference schemes, using the properties of stereographic projection, taking into account the group-theoretical features of constructions of the O(N) class of nonlinear sigma models of field theory. On the perimeter of the two-dimensional modeling area, specially developed boundary conditions are established that absorb linear perturbation waves radiated by interacting soliton fields. Thus, the simulation of the interaction processes of localized solutions in an infinite two-dimensional phase space is carried out. A software module has been developed that allows to carry out a complex analysis of the evolution of interacting solutions of nonlinear sigma models of field theory, taking into account it’s group properties in a two-dimensional pseudo-Euclidean space. The analysis of isospin dynamics, as well the energy density and energy integral of a system of interacting dynamic and topological solitons is carried out.

The article presents a technology for building clinical decision support systems (CDSS) based on service containers using Docker and a web interface that runs directly in the browser without installing specialized software on workstation of a clinician. A modular architecture is proposed in which each application module is packaged as an independent service container combining a lightweight web server, a user interface, and computational components for medical image processing. Communication between the browser and the server side is implemented via a persistent bidirectional WebSocket connection with binary message serialization (MessagePack), which provides low latency and efficient transfer of large data. For local storage of images and analysis of results, browser facilities (IndexedDB with the Dexie.js wrapper) are used to speed up repeated data access. Three-dimensional visualization and basic operations with DICOM data are implemented with Three.js and AMI.js: this toolchain supports the integration of interactive elements arising from the task context (annotations, landmarks, markers, 3D models) into volumetric medical images.

Server components and functional modules are assembled as a set of interacting containers managed by Docker. The paper discusses the choice of base images, approaches to minimizing containers down to runtime-only executables without external utilities, and the organization of multi-stage builds with a dedicated build container. It describes a hub service that launches application containers on user request, performs request proxying, manages sessions, and switches a container from shared to exclusive mode at the start of computations. Examples of application modules are provided (fractional flow reserve estimation, quantitative flow ratio computation, aortic valve closure modeling), along with the integration of a React-based interface with a three-dimensional scene, a versioning policy, automated reproducibility checks, and the deployment procedure on the target platform.

It is demonstrated that containerization ensures portability and reproducibility of the software environment, dependency isolation and scalability, while the browser-based interface provides accessibility, reduced infrastructure requirements, and interactive real-time visualization of medical data. Technical limitations are noted (dependence on versions of visualization libraries and data formats) together with practical mitigation measures.

This article solves the problem of developing a technology for collecting initial data for building models for assessing the functional state of a person. This condition is assessed by the pupil response of a person to a change in illumination based on the pupillometry method. This method involves the collection and analysis of initial data (pupillograms), presented in the form of time series characterizing the dynamics of changes in the human pupils to a light impulse effect. The drawbacks of the traditional approach to the collection of initial data using the methods of computer vision and smoothing of time series are analyzed. Attention is focused on the importance of the quality of the initial data for the construction of adequate mathematical models. The need for manual marking of the iris and pupil circles is updated to improve the accuracy and quality of the initial data. The stages of the proposed technology for collecting initial data are described. An example of the obtained pupillogram is given, which has a smooth shape and does not contain outliers, noise, anomalies and missing values. Based on the presented technology, a software and hardware complex has been developed, which is a collection of special software with two main modules, and hardware implemented on the basis of a Raspberry Pi 4 Model B microcomputer, with peripheral equipment that implements the specified functionality. To evaluate the effectiveness of the developed technology, models of a single-layer perspetron and a collective of neural networks are used, for the construction of which the initial data on the functional state of intoxication of a person were used. The studies have shown that the use of manual marking of the initial data (in comparison with automatic methods of computer vision) leads to a decrease in the number of errors of the 1st and 2nd years of the kind and, accordingly, to an increase in the accuracy of assessing the functional state of a person. Thus, the presented technology for collecting initial data can be effectively used to build adequate models for assessing the functional state of a person by pupillary response to changes in illumination. The use of such models is relevant in solving individual problems of ensuring transport security, in particular, monitoring the functional state of drivers.

Muscle contraction is controlled by Ca2+ ions via regulatory proteins, troponin and tropomyosin, associated with thin actin filaments in sarcomeres. Depending on the Ca2+ concentration, the thin filament rearranges so that tropomyosin moves along its surface, opening or closing access to actin for the motor domains of myosin molecules, and causing contraction or relaxation, respectively. Numerous point amino acid substitutions in tropomyosin are known, leading to genetic pathologies — myo- and cardiomyopathies caused by changes in the structural and functional properties of the thin filament. The results of molecular dynamics modeling of a fragment of a thin filament of cardiac muscle sarcomeres formed by fibrillar actin and wildtype tropomyosin or with amino acid substitutions: the double stabilizing substitution D137L/G126R and the cardiomyopathic substitution S215L are presented. For numerical calculations, we used a new model of a thin filament fragment containing 26 actin monomers and 4 tropomyosin dimers, with a refined structure of the region of overlap of neighboring tropomyosin molecules in each of the two tropomyosin strands. The simulation results showed that tropomyosin significantly increases the bending stiffness of the thin filament, as previously found experimentally. The double stabilizing replacement D137L/G126R leads to a further increase in this rigidity, and the replacement S215L, on the contrary, leads to its decrease, which also corresponds to experimental data. At the same time, these substitutions have different effects on the angular mobility of the actin helix and only slightly modulate the angular mobility of tropomyosin cables relative to the actin helix and the population of hydrogen bonds between negatively charged tropomyosin residues and positively charged actin residues. The results of the verification of the new model demonstrate that its quality is sufficient for the numerical study of the effect of single amino acid substitutions on the structure and dynamics of thin filaments and study the effects leading to dysregulation of muscle contraction. This model can be used as a useful tool for elucidating the molecular mechanisms of some genetic diseases and assessing the pathogenicity of newly discovered genetic variants.

Getting a qualified medical examination can be difficult for people in remote areas because medical staff available can either be inaccessible or it might lack expert knowledge at proper level. Telemedicine technologies can help in such situations. On one hand, such technologies allow highly qualified doctors to consult remotely, thereby increasing the quality of diagnosis and plan treatment. On the other hand, computer-aided analysis of the research results, anamnesis and information on similar cases assist medical staff in their routine activities and decision-making.

Creating telemedicine system for a particular domain is a laborious process. It’s not sufficient to pick proper medical experts and to fill the knowledge base of the analytical module. It’s also necessary to organize the entire infrastructure of the system to meet the requirements in terms of reliability, fault tolerance, protection of personal data and so on. Tools with reusable infrastructure elements, which are common to such systems, are able to decrease the amount of work needed for the development of telemedicine systems.

An interactive tool for creating distributed telemedicine systems is described in the article. A list of requirements for the systems is presented; structural solutions for meeting the requirements are suggested. A composition of such elements applicable for distributed systems is described in the article. A cardiac telemedicine system is described as a foundation of the tool

One of the most widely used storage solutions in WLCG is a Disk Pool Manager (DPM) developed and supported by SDC/ID group at CERN. Recently DPM went through a massive overhaul to address scalability and extensibility issues of the old code.

New system was called DMLite. Unlike the old DPM that was based on daemons, DMLite is arranged as a library that can be loaded directly by an application. This approach greatly improves performance and transaction rate by avoiding unnecessary inter-process communication via network as well as threading bottlenecks.

DMLite has a modular architecture with its core library providing only the very basic functionality. Backends (storage engines) and frontends (data access protocols) are implemented as plug-in modules. Doubtlessly DMLite wouldn't be able to completely replace DPM without GridFTP as it is used for most of the data transfers in WLCG.

In DPM GridFTP support was implemented in a Data Storage Interface (DSI) module for Globus’ GridFTP server. In DMLite an effort was made to rewrite a GridFTP module from scratch in order to take advantage of new DMLite features and also implement new functionality. The most important improvement over the old version is a redirection capability.

With old GridFTP frontend a client needed to contact SRM on the head node in order to obtain a transfer URL (TURL) before reading or writing a file. With new GridFTP frontend this is no longer necessary: a client may connect directly to the GridFTP server on the head node and perform file I/O using only logical file names (LFNs). Data channel is then automatically redirected to a proper disk node.

This renders the most often used part of SRM unnecessary, simplifies file access and improves performance. It also makes DMLite a more appealing choice for non-LHC VOs that were never much interested in SRM.

With new GridFTP frontend it's also possible to access data on various DMLite-supported backends like HDFS, S3 and legacy DPM.