2 August 2025 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
The purpose of the research is purpose of the study. The analysis of modern solutions aimed at supporting decision-making on optimal driving within the framework of the Connected Car concept, as well as systematize the main methods of using telematics data and architecture of similar systems. Methods. Methods. The study is based on an analysis of domestic and foreign publications, patents and practical implementations in the field of Connected Cars, as well as examples of the introduction of telematics platforms in the automotive industry. Classical statistical methods, machine learning algorithms, and big data streaming tools are considered. Special attention is paid to scalability, standardization and quality of telematics information. Results. It has been established that most modern systems rely on basic statistical and machine learning methods (classification, clustering, regression models) to analyze large amounts of data on vehicle movement. However, unified approaches to the integration of these methods into the integrated architecture of decision support systems have not yet been formed. Hybrid approaches combining statistical methods, ML algorithms, and Big Data technologies demonstrate the greatest effectiveness. Their widespread adoption is hampered by the lack of uniform standards for telematics data exchange, the difficulties of reliable data storage, and the need to filter noise and omissions. Based on the review, the advantages and disadvantages of various methods are identified, as well as the requirements for the architecture of the DSS for the Connected Car are formulated. Conclusion. The review confirms the high demand for flexible, scalable solutions capable of processing telematics data in real time and taking into account individual driving characteristics. The further development of such systems is closely related to the unification of telematics information formats, increased security (both in terms of data protection and in the field of traffic), as well as expanding the range of analyzed sources (road infrastructure, weather conditions, smart city ecosystems, etc.) to improve the accuracy of recommendations and optimize driving.
1 January 2016 in Vulkanologiâ i sejsmologiâ
В работе изложена методика оценки прогнозируемости сейсмического потока на вулканических объектах. В качестве математической модели используется нелинейное дифференциальное уравнение второго порядка, а алгоритмы оптимизации и оценки прогнозируемости представлены авторскими разработками. Методика иллюстрируется на примере извержения вулкана Шивелуч в 1964 г. Расчеты показывают, что сейсмический поток может успешно прогнозироваться в будущее на интервал времени от нескольких суток до нескольких десятков суток на стадии активизации и от нескольких десятков суток до нескольких сотен суток на стадии затухания. Уровень прогнозируемости довольно высок – прогнозная дистанция превышает величину средней ошибки на два–четыре десятичных порядка. Нелинейность как активизации процесса, так и его затухания близка к закону равнобокой гиперболы. Разработанная методика делает возможным реалистичный подход к прогнозу той части вулканического процесса, которая соответствует развитию хрупких деформаций и/или быстрых перемещений вещества по образующимся...
1 January 2018 in Rossijskij fiziologičeskij žurnal im. I.M. Sečenova
22 November 2025 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
The purpose of the research is to develop a software and information system for automating the assessment of cognitive abilities of employees and candidates using scientifically validated testing methodologies in HR departments. Methods . To implement the software system, the C# programming language was used with the ASP.NET Core framework, along with JavaScript and the React library. For storing data on users, testing results, and reports, the MSSQL database was utilized. The following scientifically validated methodologies were employed: "Schulte Tables" (G. Schulte) to measure attention concentration, "Pair Word Memorization Method" (H. Ebbinghaus) to assess shortterm memory, "Raven's Progressive Matrices" (J. Raven) to analyze logical thinking, "Holmes and Rahe Stress Scale" (T. Holmes, R. Rahe) to evaluate stress resilience, and "Belbin's Methodology" (R. M. Belbin) to determine team roles. The system uses test results as input data, which are subsequently analyzed to generate reports and provide recommendations. Results . During the development, a software and information system was created to automate the process of assessing cognitive abilities of employees and candidates. Interfaces for users and HR specialists were implemented, providing access to tests, results, and analytics. Testing on a sample of company employees demonstrated a diagnostic accuracy level of 93%. The system offers personalized and group analysis capabilities, including generating recommendations for skill development and building summary reports, making it an effective tool for HR departments. The testing results showed that the developed software fully meets functional requirements and is ready for use. Conclusion. The developed software and information system enables the automation of cognitive testing processes for employees and candidates, providing HR departments with a convenient tool for evaluating key skills and developing development plans. The system ensures high diagnostic accuracy and saves specialists’ time through automated data processing. Future development prospects include expanding functionality, adding new testing methodologies, implementing adaptive algorithms for dynamically adjusting task complexity, and integrating with HRM systems to optimize personnel management processes.
7 May 2026 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
The purpose of the research is to develop and formalize a hybrid model for forecasting stock prices on the Moscow Exchange, which takes into account the specifics of linguistic analysis of Russian-language news and the integration of time series signals with semantic text analysis. The model is aimed at improving prediction accuracy in the conditions of high volatility of the Russian financial market and structural changes after 2022. Methods . A three-level model for stock price prediction has been developed. Each level implies the use of a more suitable tool considering the forecasting horizon. Thus, the short-term level is based on a GRU recurrent network and uses a sliding window, which shows high efficiency during periods of low volatility. The medium-frequency level uses a regression model with a Huber loss function and modified CIS tone metrics to translate news influence into a monetary equivalent, which allows combining short-term and fundamental indicators; the use of the latter increases the model's adaptability during periods of high volatility. The low-frequency level combines the ARIMAX statistical model, the LSTM neural network, as well as medium-frequency level indicators to assess long-term trends and correct errors of the lower levels. The integration of the levels is implemented through a mechanism of dynamic weight redistribution and inter-level adjustment of confidence coefficients. Results . A software complex for stock market forecasting was developed based on the Python programming language, implementing a hybrid architecture that integrates time series analysis, fundamental indicators, and news context. The simulation demonstrated sustained forecasting accuracy: under market turbulence conditions, levels L2 and L3 showed a mean absolute error not exceeding 0.5 rubles, which is significantly lower than the metrics of the technical level L1. The dynamic weight redistribution mechanism between levels ensured the model's adaptation to sharp changes in market conditions. Conclusion . The proposed hybrid forecasting architecture combines machine learning, NLP, and econometric methods, ensuring a balance between sensitivity to short-term changes and the robustness of long-term forecasts. The integration of news analysis, time series, and macroeconomic factors allows for considering the specifics of the Russian market and reduces the impact of market shocks. The system is suitable for use in investment analytics and automated trading solutions, opening prospects for further adaptation to other emerging markets