All issues

This article presents the results of an analytical and computer study of the chaotic evolution of a regular velocity field generated by a large-scale harmonic forcing. The authors obtained an analytical solution for the flow stream function and its derivative quantities (velocity, vorticity, kinetic energy, enstrophy and palinstrophy). Numerical modeling of the flow evolution was carried out using the OpenFOAM software package based on incompressible model, as well as two inhouse implementations of CABARET and McCormack methods employing nearly incompressible formulation. Calculations were carried out on a sequence of nested meshes with 64², 128², 256², 512², 1024² cells for two characteristic (asymptotic) Reynolds numbers characterizing laminar and turbulent evolution of the flow, respectively. Simulations show that blow-up of the analytical solution takes place in both cases. The energy characteristics of the flow are discussed relying upon the energy curves as well as the dissipation rates. For the fine mesh, this quantity turns out to be several orders of magnitude less than its hydrodynamic (viscous) counterpart. Destruction of the regular flow structure is observed for any of the numerical methods, including at the late stages of laminar evolution, when numerically obtained distributions are close to analytics. It can be assumed that the prerequisite for the development of instability is the error accumulated during the calculation process. This error leads to unevenness in the distribution of vorticity and, as a consequence, to the variance vortex intensity and finally leads to chaotization of the flow. To study the processes of vorticity production, we used two integral vorticity-based quantities — integral enstrophy ($\zeta$) and palinstrophy $(P)$. The formulation of the problem with periodic boundary conditions allows us to establish a simple connection between these quantities. In addition, $\zeta$ can act as a measure of the eddy resolution of the numerical method, and palinstrophy determines the degree of production of small-scale vorticity.

Image denoising is one of the fundamental problems in digital image processing. This problem usually refers to the reconstruction of an image from an observed image degraded by noise. There are many factors that cause this degradation such as transceiver equipment, or environmental influences, etc. In order to obtain higher quality images, many methods have been proposed for image denoising problem. Most image denoising method are based on total variation (TV) regularization to develop efficient algorithms for solving the related optimization problem. TV-based models have become a standard technique in image restoration with the ability to preserve image sharpness.

In this paper, we focus on Poisson noise usually appearing in photon-counting devices. We propose an effective regularization model based on combination of first-order and fractional-order total variation for image reconstruction corrupted by Poisson noise. The proposed model allows us to eliminate noise while edge preserving. An efficient alternating minimization algorithm is employed to solve the optimization problem. Finally, provided numerical results show that our proposed model can preserve more details and get higher image visual quality than recent state-of-the-art methods.

We developed a model of honeybee colony foraging based on reaction – diffusion equations. Employed bees transmit information about their food sources using dance, and job seekers in the hive can choose any dance they like and thus join the exploitation of the corresponding source. We consider two strategies of dance selection: a targeted one, when bees analyze information on the dance floor and choose the most energetic and longest dance corresponding to the most profitable source, and a simple random choice of the first dance they encounter. Modelling showed that the greatest profit (food influx into the hive) is provided by the random choice of dance, as paradoxical as it may seem at first glance. Optimization of profit by each agent for itself (targeted choice of dances) is rather a disadvantage for the colony, and “non-optimality” in dance choice can be the result of useful evolutionary adaptation.

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.

Deep learning’s power stems from complex architectures; however, these can lead to overfitting, where models memorize training data and fail to generalize to unseen examples. This paper proposes a novel probabilistic approach to mitigate this issue. We introduce two key elements: Truncated Log-Uniform Prior and Truncated Log-Normal Variational Approximation, and Automatic Relevance Determination (ARD) with Bayesian Deep Neural Networks (BDNNs). Within the probabilistic framework, we employ a specially designed truncated log-uniform prior for noise. This prior acts as a regularizer, guiding the learning process towards simpler solutions and reducing overfitting. Additionally, a truncated log-normal variational approximation is used for efficient handling of the complex probability distributions inherent in deep learning models. ARD automatically identifies and removes irrelevant features or weights within a model. By integrating ARD with BDNNs, where weights have a probability distribution, we achieve a variational bound similar to the popular variational dropout technique. Dropout randomly drops neurons during training, encouraging the model not to rely heavily on any single feature. Our approach with ARD achieves similar benefits without the randomness of dropout, potentially leading to more stable training.

To evaluate our approach, we have tested the model on two datasets: the Canadian Institute For Advanced Research (CIFAR-10) for image classification and a dataset of Macroscopic Images of Wood, which is compiled from multiple macroscopic images of wood datasets. Our method is applied to established architectures like Visual Geometry Group (VGG) and Residual Network (ResNet). The results demonstrate significant improvements. The model reduced overfitting while maintaining, or even improving, the accuracy of the network’s predictions on classification tasks. This validates the effectiveness of our approach in enhancing the performance and generalization capabilities of deep learning models.

The article deals with the nonlinear model of population dynamics of different ages workers in the regional economy. The model is built on the principles underlying modeling in econophysics. The authors demonstrate the complex dynamics of the model regimes that impose fundamental limits on medium- and long-term forecast of employment in a region. By analogy with the biophysical approach the authors propose a classification of social interactions of the different age-group workers. The model analysis is given for the level of employment among age groups. The verification of the model performs on the statistical data of the Jewish Autonomous Region.

The short-term prediction of road traffic condition is one of the main tasks of transportation modelling. The main purpose of which are traffic control, reporting of accidents, avoiding traffic jams due to knowledge of traffic flow and subsequent transportation planning. A number of solutions exist — both model-driven and data driven had proven to be successful in capturing the dynamics of traffic flow. Nevertheless, most space-time models suffer from high mathematical complexity and low efficiency. Artificial Neural Networks, one of the prominent datadriven approaches, show promising performance in modelling the complexity of traffic flow. We present a neural network architecture for traffic flow prediction on a real-world road network graph. The model is based on the combination of a recurrent neural network and graph convolutional neural network. Where a recurrent neural network is used to model temporal dependencies, and a convolutional neural network is responsible for extracting spatial features from traffic. To make multiple few steps ahead predictions, the encoder-decoder architecture is used, which allows to reduce noise propagation due to inexact predictions. To model the complexity of traffic flow, we employ multilayered architecture. Deeper neural networks are more difficult to train. To speed up the training process, we use skip-connections between each layer, so that each layer teaches only the residual function with respect to the previous layer outputs. The resulting neural network was trained on raw data from traffic flow detectors from the US highway system with a resolution of 5 minutes. 3 metrics: mean absolute error, mean relative error, mean-square error were used to estimate the quality of the prediction. It was found that for all metrics the proposed model achieved lower prediction error than previously published models, such as Vector Auto Regression, LSTM and Graph Convolution GRU.

Rugose spiraling whitefly (RSW) is one of the major pests which affects the coconut trees. It feeds on the tree by sucking up the water content as well as the essential nutrients from leaves. It also forms sooty mold in leaves due to which the process of photosynthesis is inhibited. Biocontrol of pest is harmless for trees and crops. The experimental results in literature reveal that Pseudomallada astur is a potential predator for this pest. We investigate the dynamics of predator, Pseudomallada astur’s interaction with rugose spiralling whitefly, Aleurodicus rugioperculatus in coconut trees using a mathematical model. In this system of ordinary differential equation, the pest-predator interaction is modeled using Holling type III functional response. The parametric values are calculated from the experimental results and are tabulated. An approximate analytical solution for the system has been derived. The homotopy analysis method proves to be a suitable method for creating solutions that are valid even for moderate to large parameter values, hence we employ the same to solve this nonlinear model. The $\hbar$-curves, which give the admissible region of $\hbar$, are provided to validate the region of convergence. We have derived the approximate solution at fifth order and stopped at this order since we obtain a more approximate solution in this iteration. Numerical simulation is obtained through MATLAB. The analytical results are compared with numerical simulation and are found to be in good agreement. The biological interpretation of figures implies that the use of a predator reduces the whitefly’s growth to a greater extent.

The functioning of DNA regulatory regions rely primarily on their physicochemical and structural properties but not on nucleotide sequences, i.e. ‘genetic text’. The formers are responsible for coding of DNA-protein interactions that govern various regulatory events. One of the characteristics is SIDD (Stress-Induced Duplex Destabilization) that quantify DNA duplex region propensity to melt under the imposed superhelical stress. The duplex property has been shown to participate in activity of various regulatory regions. Here we employ the SIDD model to calculate melting probability profiles for T7 bacteriophage promoter sequences. The genome is characterized by small size (approximately 40 thousand nucleotides) and temporal organization of expression: at the first stage of infection early T7 DNA region is transcribed by the host cell RNA polymerase, later on in life cycle phage-specific RNA polymerase performs transcription of class II and class III genes regions. Differential recognition of a particular group of promoters by the enzyme cannot be solely explained by their nucleotide sequences, because of, among other reasons, it is fairly similar among most the promoters. At the same time SIDD profiles obtained vary significantly and are clearly separated into groups corresponding to functional promoter classes of T7 DNA. For example, early promoters are affected by the same maximally destabilized DNA duplex region located at the varying region of a particular promoter. class II promoters lack substantially destabilized regions close to transcription start sites. Class III promoters, in contrast, demonstrate characteristic melting probability maxima located in the near-downstream region in all cases. Therefore, the apparent differences among the promoter groups with exceptional textual similarity (class II and class III differ by only few singular substitutions) were established. This confirms the major impact of DNA primary structure on the duplex parameter as well as a need for a broad genetic context consideration. The differences in melting probability profiles obtained using SIDD model alongside with other DNA physicochemical properties appears to be involved in differential promoter recognition by RNA polymerases.

In this article we propose a new approach to the analysis of econometric industry parameters for the industry consolidation level. The research is based on the simple industry automatic control model. The state of the industry is measured by quarterly obtained econometric parameters from each industry’s company provided by the tax control regulator. An approach to analysis of the industry, which does not provide for tracking the economy of each company, but explores the parameters of the set of all companies as a whole, is proposed. Quarterly obtained econometric parameters from each industry’s company are Income, Quantity of employers, Taxes, and Income from Software Licenses. The ABC analysis method was modified by ABCD analysis (D — companies with zero-level impact to industry metrics) and used to make the results obtained for different indicators comparable. Pareto charts were formed for the set of econometric indicators.

To estimate the industry monopolization, the Herfindahl – Hirschman index was calculated for the most sensitive companies metrics. Using the HHI approach, it was proved that COVID-19 does not lead to changes in the monopolization of the Russian IT industry.

As the most visually obvious approach to the industry visualization, scattering diagrams in combination with the Pareto graph colors were proposed. The affect of the accreditation procedure is clearly observed by scattering diagram in combination with red/black dots for accredited and nonaccredited companies respectively.

The last reported result is the proposal to use the Licenses End-to-End Product Identification as the market structure control instrument. It is the basis to avoid the multiple accounting of the licenses reselling within the chain of software distribution.

The results of research could be the basis for future IT industry analysis and simulation on the agent based approach.