AOAndrey Vladimirovich Ostroukh

Andrey Vladimirovich Ostroukh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrey Vladimirovich Ostroukh has a total of 112 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Mathematical model of on-demand route formation for public transport based on individual passenger requests in low-density population area

    by Svetlana S. Titova, Andrey V. Ostroukh

    Background. The organization of public transport routes based on individual passenger requests (on-demand routes) using small-class buses in areas with low population density has become a pressing issue due to the necessity of improving the efficiency of transport systems under limited financial and material resources. Traditional regular route schemes often prove unprofitable and insufficiently convenient for residents of such territories, leading to decreased transport accessibility and deterioration of population living standards. Modern technologies and mathematical modeling enable the development of flexible and cost-effective solutions capable of adapting to the characteristics of low-density regions and minimizing costs associated with organizing transport services. The need for optimizing transport flows acquires particular significance in light of global sustainable development and environmental trends. Developing models that reduce operational expenses and decrease the carbon footprint of transport operations corresponds to modern requirements for rational natural resource utilization and energy efficiency. Creating effective mechanisms for managing on-demand routes holds high social significance, contributing to ensuring equal opportunities for all segments of the population regardless of their geographical location and financial status. Purpose. To develop a mathematical model for organizing on-demand routes for passenger transportation using small-class buses in populated areas with low population density, ensuring maximum efficiency and economic viability of transport services. Materials and methods. This study employed a comprehensive approach to developing a mathematical model for organizing on-demand routes. The research was based on analyzing real conditions of bus service operation in regions with low population density. The model considered the following parameters: number of populated areas and their geographic location, passenger flow volume, technical specifications of small-class buses, time constraints, and financial performance indicators of transport enterprises. Route optimization was performed using dynamic programming algorithms that accounted for variable demand structure and resource limitations. Practical testing of the model was conducted using data from a specific region with low population density, enabling the collection of reliable results and drawing conclusions about the effectiveness of the proposed approach to organizing transport services. Results. A comprehensive analysis of existing approaches to organizing on-demand routes was conducted, and key factors determining their effectiveness were identified. A mathematical model was developed that accounts for the specifics of populated areas with low population density, including uneven distribution of demand, large distances between populated areas, and limited financial resources. Various route optimization algorithms were investigated, and the most suitable method was selected for solving the stated problem. Numerical simulation of the proposed model was performed using a specific regional example, and its effectiveness was evaluated compared to existing transportation schemes. Recommendations were developed for implementing the proposed model in the practical activities of transport organizations operating in conditions of low population density.

  • Open Access

    Overcoming linguistic barriers in code assistants: creating a QLoRA adapter to improve support for Russian-language code writing instructions

    by C. B. Pronin, A. V. Volosova, A. V. Ostroukh, Yu. N. Strogov

    In this paper, an approach to training and evaluating an adapter model for the popular language model "zephyr-7b-beta" is described. The adapter was developed to improve the performance of the base model in tasks related to programming and understanding the Russian language. Considering the high quality of the original model in tasks in the English language, the goal of the research was to expand its linguistic and technical spectrum. The proposed adapter was trained using a large and diverse dataset, including question-answer pairs related to programming, as well code-related texts in Russian language. The applied training methodology ensures an improvement in the model's quality of answers in understanding and generating Python code based on Russian instructions. We evaluated the performance of the base model with the installed adapter using various metrics, comparing it to the base model as well as other state-of-the-art models in this field. The obtained results showed significant improvement, both in tasks related to writing Python code and in processing the Russian language, confirming the effectiveness of the proposed adapter.

  • Overcoming linguistic barriers in code assistants: creating a Qlora adapter to improve support for russian-language code writing instructions

    by C.B. Pronin, A.V. Volosova, A.V. Ostroukh, Yu.N. Strogov

    This article describes an approach to learning and evaluating an adapter model for the popular zephyr-7b-beta language model. The adapter was designed to improve the performance of the basic model in tasks related to programming and understanding the Russian language. Taking into account the high quality of the original model's work in problems in English, the purpose of the study was to expand its linguistic and technical spectrum. The proposed adapter was trained using a large and diverse dataset, including question-answer pairs related to programming, as well as a text with a discussion of the code in Russian. The applied training methodology ensures an improvement in the quality of the model's responses in understanding and generating Python code based on Russian-language instructions. The authors evaluated the performance of the basic model with the adapter installed using various metrics, comparing it with the basic model, as well as with other advanced models in this area. The results obtained by the authors showed significant improvement both in tasks related to writing Python code and in processing the Russian language, confirming the effectiveness of the proposed adapter. The analysis of the experiment results showed that the adapter not only adds new functionality to the model but also significantly changes the priority of the model's output in favor of the instructions that were included during the retraining stage. To eliminate the fact of changing the model's output priority mentioned above, the following methods are proposed: 1) Using a different format for writing the query (prompt) when formatting the dataset for training the model, different from the original format in Zephyr. 2) Including instructions from the first stage of fine-tuning (retraining) in the instruction set. 3) Creating a "mixture of experts" from several different models, where each model will specialize in the most accurate solution to one or several tasks from the overall range of solvable tasks. The methods of retraining the model without losing the original characteristics are promising directions for future research in the field of resource-efficient modification of large language models. In the conducted experiment, a large language model "HuggingFaceH4/zephyr-7b-beta" was successfully fine-tuned (using the QLoRA adapter creation method) to improve its capabilities in writing Python code based on Russian instructions and providing explanations in Russian. The testing results showed that when the created adapter is installed, the model's text generation priority shifts towards generating code with explanations. Synthetic tests also demonstrated significant improvements in the model's ability to solve programming and mathematical problems. Therefore, it is advisable to consider the possibility of changing adapters depending on the type of task being solved. Changing the adapter installed on the model (loaded into memory) does not take a significant amount of time, which allows for the creation of a set of adapters tailored to specific tasks and their interchange based on the type of tasks being solved. Changing adapters instead of models eliminates the need to load multiple full versions of the model into the memory of the computational accelerator, which, depending on the implementation method, either significantly reduces the use of memory or the model loading time. Thus, the use of adapters speeds up training and optimizes the utilization of computational resources during model operation. This presented research contributes to the current efforts in the field of machine learning and natural language processing towards creating more versatile AI models. The observed potential of adapter models in improving the quality of responses in specific domains without the need for extensive retraining helps meet the growing demand for models for multilingual natural language processing and code generation. In the conducted experiment, an assessment was made of the possibility of retraining a model that had already been trained on a set of instructions. The methods of additional training of a language model with new instructions without losing the ability to perform original instructions are not well-studied, which is why a decision was made to test the feasibility and effectiveness of such retraining. Based on the description of the LoRA method, this approach is possible because during such training, the original weights of the model remain unchanged and are only supplemented with new coefficients from the adapter model (the total number of weights equals that of the base model), which was trained on new instructions. The experiment determined that multilingual adaptation of language models is viable, and that it also could be implemented using parametrically efficient methods on comparatively low-end hardware.


  • Open Access

    Synthesis of Quantum Vector Databases Based on Grovers Algorithm

    by Cesar Borisovich Pronin, Andrey Vladimirovich Ostroukh

    This paper describes a method for using Grovers algorithm to create a quantum vector database, the database stores embeddings based on Controlled-S gates, which represent a binary numerical value. This value represents the embeddings value. The process of creating meaningful embeddings is handled by a classical computer and the search process is handled by the quantum computer. This search approach might be beneficial for a large enough database, or it could be seen as a very qubit-efficient (super dense) way for storing data on a quantum computer, since the proposed circuit stores many embeddings inside one quantum register simultaneously.


  • Predictive Diagnostics and Maintenance of Industrial Equipment

    by N. G. Kuftinova, A. V. Ostroukh, O. I. Maksimychev, Yu. E. Vasil’EV, M. G. Pletnev

    Digitization of industrial enterprises is proposed, permitting the collection, analysis, and visualization of data regarding products, systems, machines, a


  • Digital Twins in Smart Data Management at a Manufacturing Enterprise

    by N. G. Kuftinova, A. V. Ostroukh, O. I. Maksimychev, Yu. E. Vasil’EV, V. A. Klimenko

    The basic principles and stages employed in the creation of digital twins are investigated. At manufacturing enterprises, digital twins permit increase in


  • Open Access

    Developing Mathematical Oracle Functions for Grover Quantum Search Algorithm

    by Cesar Borisovich Pronin, Andrey Vladimirovich Ostroukh

    This article highlights some of the key operating principles of Grover algorithm. These principles were used to develop a new oracle function, that illustrates the possibility of using Grover algorithm for solving more realistic and specific search problems, like searching for a solution to a simple mathematical equation.

  • Hyperautomation in the Auto Industry

    by A. V. Ostroukh, Ts. B. Pronin, A. V. Volosova, A. O. Volkov, D. A. Ptitsyn

    Hyperautomation of the auto industry is considered, including multitask machine learning, batch software, and automation tools. Hyperautomation is associat


  • Open Access

    Railroad cement warehouse digital system

    by Y E Vasiliev, A V Ostroukh, C B Pronin, I Y Sarychev, I.E. Kotlarsky

    In the article the concept of Railroad Cement Warehouse Digital System (RCWDS) with two silos. The article briefly analyzes the ways of unloading hopper, as well as basic equipment for mechanical and pneumatic conveying of cement hopper in the cement silos. The system is a set of hardware maintenance, information, mathematical and software for management of technological objects of railroad warehouse of cement. The system allows you to track trends in cement consumption and accumulation and manage its stocks rationally. The system also allows remote calibration of all silos, further reducing costs and staff time on site. The system is using technological equipment and industrial controllers that allow monitoring silo filling, the occurrence of excess pressure and reduce the risk of dust release into the atmosphere. The system is scalable and can be further modified to control a large number of silos. In accordance with the proposed concept, RCWDS provides the optimum level of automation in the collection and processing of information for generating control signals and transmit them without loss and distortion to the actuators in order to achieve the most efficient warehouse operation cement.