These days, a lot of crime-related events take place all over the world. Most of them are reported in news portals and social media. Crime-related event extraction from the published texts can allow monitoring, analysis, and comparison of police or criminal activities in different countries or regions. Existing approaches to event extraction mainly suggest processing texts in English, French, Chinese, and some other resource-rich and well-annotated languages. This paper presents a parallel corpus-based approach that follows a closed-domain event extraction methodology to event extraction from web news articles in low-resource languages. To identify the event, its arguments, and the arguments’ roles in the source-language part of the corpus we utilize an enhanced pattern-based method that involves the multilingual synonyms dictionary with knowledge about crime-related concepts and logic-linguistic equations. The event extraction from the target-language part of the corpus uses a cross-lingual crime-related event extraction transfer technique that is based on supplementary knowledge about the semantic similarity patterns of the considered pair of languages. The presented approach does not require a preliminarily annotated corpus for training making it more attractive to low-resource languages and allows extracting TRANSFER, CRIME, and POLICE types of events and their seven subtypes from various topics of news articles simultaneously. Implementation of our approach for the Russian-Kazakh parallel corpus of news portals articles allowed obtaining the F1-measure of crime-related event extraction of over 82% for the source language and 63% for the target language.

This study presents the analysis and modeling of the thermal regime of a furnace lining at an industrial copper smelting facility using a combined approach based on neural network (NN) technologies and the finite element method (FEM). Experimental temperature data were collected from a laboratory setup equipped with three thermocouples (TP-2488/1 and TCRosemount 0065), with a sampling frequency of 1 Hz over a total duration of 5 hours, resulting in 18,000 measurement points. The measurement uncertainty of the thermocouples did not exceed ±1.5 °C. These data were used both for model development and for validating the numerical FEM simulations. A feedforward neural network was trained using 70% of the dataset, while 15% and 15% were used for validation and testing, respectively. The prediction error of the neural network remained within 3% with a 95% confidence interval of [2.6%, 3.4%]. The results show that the proposed hybrid approach improves temperature prediction accuracy and reduces static control error by 15% when combined with a proportional-integral controller. The methodology demonstrates significant potential for improving thermal process stability and reducing energy consumption in high-temperature metallurgical systems.

In the rapidly evolving real estate market, the application of machine learning (ML) is crucial for understanding and predicting price trends. This study evaluates and compares seven ML models, including multiple linear regression, random forest regression, support vector regression (SVR), decision tree regression, and XGBoost, to determine the most effective predictor of real estate prices in Astana, Kazakhstan. The study focuses on the Yesil district, a key area in the city, utilizing a dataset of over 9,000 records extracted from a broader collection of more than 30,000 real estate transactions across Kazakhstan. Through rigorous experimentation, model performance was assessed using statistical metrics such as mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R-squared). The results indicate that the Random Forest Regressor and XGBRegressor models outperformed others, achieving the highest R-squared values (99.55% and 99.18%, respectively) and the lowest MAE and RMSE values. These findings highlight their robustness in predicting housing prices with high accuracy. The primary objective of this study was to develop a precise ML model capable of accurately forecasting real estate prices in Astana based on key market attributes. The superior predictive performance of the Random Forest and XGBRegressor models justifies their selection for deployment in real-world applications. Their high predictive accuracy suggests their potential utility for real estate professionals, policymakers, and investors seeking data-driven insights into market dynamics. This research expands knowledge on the applications of ML in the real estate sector, reinforcing the importance of evidence-based decision-making within the industry.

Pyrometallurgical processes, such as copper concentrate smelting, are pivotal to the metallurgical industry. Effectively managing these processes necessitates a comprehensive understanding of thermal and material flow dynamics. This paper outlines the development of a mathematical model and control algorithm for the Vanyukov smelting process. The proposed solution aims to optimize operational regimes and improve production efficiency. The study explores the synthesis of models and algorithms for a hybrid system grounded in the analysis and processing of extensive data collected at the Balkhash Copper Smelter. Mathematical modeling techniques and research findings are presented, including transfer function construction and simulations utilizing various controllers.

Emotion recognition plays an important role in a wide range of application domains. Although previous studies have made progress in this domain, they often fall short in achieving a better understanding of emotions and inferring their underlying causes. To address these limitations, we propose an emotion recognition framework that integrates visual, audio, and textual modalities within a unified architecture. The proposed framework integrates an adaptive cross-modal attention module to capture inter-modal interactions. This module dynamically adjusts the contribution of each modality based on contextual relevance, enhancing recognition accuracy. Additionally, an emotion causality inference module uses a fine-tuned, trainable LLaMA2-Chat (7B) model to jointly process image and text data. This identifies word clues associated with the expressed emotions. Furthermore, a real-time emotion feedback module delivers instantaneous assessments of emotional states during conversations, supporting timely and context-aware interventions. The experimental results on four datasets, SEMAINE, AESI, ECF, and MER-2024, demonstrate that our method achieves improvements in F1-scores compared to baselines.

The article is based on the synthesis of domestic and foreign data, shows the main sources and ways of radon in buildings, formulated the basic principles of their anti-radon protection, classifies methods and means of protection, outlines recommendations for their practical implementation in the design and construction of buildings. Today in Kazakhstan there are several laws aimed at ensuring radiation safety of the population, at the request of which epidemiological services conduct constant monitoring of facilities under construction and existing ones. According to current standards, the concentration of radon in existing buildings should not exceed 200 Bq/m3, and during design – 100 Bq/m3. When solving problems of anti-radon protection of buildings, the sources of radon are objects from which radon directly enters the premises, regardless of the nature of its appearance in these objects. It is necessary to understand that measures for anti-radon protection of a building, carried out at the stages of its design and construction, are more effective and require lower costs than measures to reduce radon in an already constructed building. Currently, there are no standardized methods for calculating the necessary parameters and determining the optimal type of radon protection. The procedure for this selection is heuristic and in each case is based on an analysis and qualitative assessment of a number of circumstances.