This study investigates the effectiveness of machine learning methods in identifying earthquake-prone areas in Kazakhstan and its neighboring regions. By leveraging a comprehensive dataset encompassing significant earthquake data from 1900 to 2023, various machine learning algorithms were employed, including RandomForest, GradientBoosting, Logistic Regression, Support Vector Classification (SVC), K-Nearest Neighbors (KNeighbors), Decision Tree, XGBoost, LightGBM, AdaBoost, and MLPClassifier. The primary objective was to analyze and compare the performance of these models in predicting earthquake magnitudes and frequencies. The results reveal that certain algorithms significantly outperformed others in terms of accuracy, underscoring the potential of machine learning techniques to enhance earthquake prediction capabilities. Notably, XGBoost and RandomForest demonstrated the highest predictive accuracy, suggesting their suitability for application in seismic risk assessment. These findings offer valuable insights for governmental agencies engaged in disaster management and prevention planning, highlighting the practical implications of integrating advanced analytical techniques in their strategies. In addition to model performance analysis, a visual heatmap was generated to illustrate the geographical distribution of earthquake occurrences across the studied regions. This visual representation effectively identifies high-risk areas, serving as a crucial tool for local authorities and researchers in making informed decisions regarding safety measures and emergency preparedness. This research contributes to the expanding body of knowledge on earthquake prediction utilizing machine learning, emphasizing the necessity for continuous improvement in predictive models by incorporating additional environmental and geological factors. The implications of these findings extend beyond academic discourse, holding significant potential for enhancing public safety in regions vulnerable to seismic activity. As such, this study advocates for the integration of machine learning methodologies in disaster management frameworks to mitigate risks and enhance preparedness in earthquake-prone regions.

This scientific article examines the design and optimization of an automated irrigation system for an intelligent greenhouse using IoT (Internet of Things) technologies in the agricultural sector. The main objective of the study is to increase crop productivity by implementing a personalized and efficient irrigation process based on environmental and soil moisture parameters. The hardware component of the system is built on Arduino Uno and ESP8266 microcontrollers, utilizing DHT11, LDR, HC-SR04, and soil moisture sensors to collect real-time data. The obtained information is processed and visualized through the Blynk IoT platform, allowing for remote monitoring and control. Experimental results demonstrate that the system contributes to significant water conservation, improved energy efficiency, reduced human intervention, and stable crop growth conditions. The findings highlight the potential of IoT-based smart irrigation technologies to support agricultural digitalization, optimize greenhouse management, and enhance sustainable farming practices. This study provides a scientific foundation for further research on scalable intelligent irrigation architectures and their integration into modern agrotechnological systems.

После реформы образовательных программ 2022 года ИТ-направления в вузах Казахстана столкнулись с ситуацией, которая сначала выглядела как локальная, но со временем стала повторяться. Учебные планы формально обновляются, однако их внутренняя логика не всегда успевает за усложнением дисциплин, особенно в области ИИ. В МКТУ им. Ясави на специальности «Информационные системы» это проявилось достаточно заметно: часть студентов, которые уверенно проходили базовые курсы, на старших курсах начинают терять стабильность в результатах. Не сразу, но довольно системно. Возник вопрос — где именно происходит этот «разрыв». Анализ начался с выгрузки данных из системы Platonus. На этом этапе стало понятно, что сами данные далеки от идеальных: присутствует шум, пропуски и несогласованности между семестрами. Очистка заняла отдельное время, и в какой-то момент стало ясно, что без предварительной стандартизации любые выводы будут сомнительными. После применения Z-score нормализации и расчета KPI по ключевым дисциплинам картина стала более определённой. В разных потоках от 14% до 18% студентов стабильно попадают в зону повышенного риска. Это не разовые отклонения, а повторяющийся паттерн, который указывает на проблемы в образовательной траектории. Чтобы сократить задержку между возникновением проблемы и её обнаружением, был разработан инструмент на базе Streamlit. В отличие от статических отчетов, он позволяет отслеживать изменения в динамике и видеть отклонения на ранних этапах. По сути, это рабочий интерфейс, а не просто визуализация. Практическое применение показало, что такой подход помогает эдвайзерам кафедры «Компьютерная инженерия» реагировать раньше — до того, как студент доходит до пересдачи. Это не устраняет проблему полностью, но меняет момент её обнаружения, а значит и возможности вмешательства. Полученные результаты показывают, что предиктивная аналитика в образовательной среде работает не как дополнение, а как необходимый слой. Простая фиксация среднего балла в конце семестра в этом контексте уже не даёт достаточной информации.

Instagram Facebook, Twitter, the impact of publications in social networks of the International Kazakh‑Turkish university named after Khoja Ahmed Yasawi in the period from the beginning of 2022 to the beginning of 2025 on the formation of the image of the university is analyzed in detail using artificial intelligence (AI) tools. In the course of the study, such aspects as the influence of language and visual content on the image, the emotional coloring of publications (sentiment analysis), topic modeling and visual recognition (image recognition) are considered. The content on social networks is systematically analyzed using AI-based Natural Language Processing (NLP), thematic modeling, sensory analysis and image recognition methods. As a result of the study, the image of the University in the digital information space, methods of communication with the audience and the effectiveness of content were determined. Based on the results obtained in the article, specific recommendations are given to improve the digital communication strategy of the University. This work is a practical basis aimed at strengthening the image of universities in social networks and the effective use of AI tools. In addition, the data obtained during the study were visualized and the dynamics of the content and the reaction of the audience were analyzed over time. The proposed methods form an innovative model for evaluating social network content and provide effective mechanisms for promoting the university brand.

The relevance of the research is determined by the need to simulate wave propagation in heterogeneous media based on phononic crystals. These studies are necessary for the tasks of flaw detection, the development of non-destructive testing methods, geophysics, engineering geophysics and other methods of acoustic research. During the study, it was determined that the fragmentation of the components of two-component phononic crystals into 2, 3, … N equal parts in the unit cell leads to a catastrophic rearrangement of the dispersion relations and the appearance of new elementary wave packets for acoustic waves. Using numerical-analytical methods, it is shown that in two-component phononic crystals, the polydispersity of the components can significantly affect the average characteristics of the propagation of long acoustic waves when the polydisperse crystal is close to monodisperse with a smaller unit cell size. For polydisperse crystals close to monodisperse with the same period (unit cell size), their averaged characteristics for long waves coincide.