Timur Kartbayev

This research paper considers methods for automatic detection of profanity and aggressive comments in Kazakh social networks. The relevance of the study is due to the increasing volume of profanity comments online and the lack of effective automated solutions for resource-limited languages. The Kazakh language is characterized by complex morphology and contextual specificity, which makes it difficult to use traditional natural language processing methods. The proposed study introduces a hybrid model based on the BERT transformer architecture, combining multihead attention and convolutional neural networks. This architecture enables the effective detection of offensive texts, including both explicit and subtle forms of comments exchanged among cadets and officers online. To train and test the model, a corpus of Kazakh-language comments annotated by experts was constructed, including opinions from cadets, commanders, and personnel. The quality of the annotation was assessed using Fleiss's Kappa coefficient, which gave 0.6649, with an overall agreement level of 91.67%, which indicates high reliability of the data. Experimental results showed that the proposed model outperforms the baseline methods (Naive Bayes, LSTM, FastText) in terms of accuracy, F1-score, and ROC-AUC. The resulting ROC-AUC value was 0.95. The research results confirm the effectiveness of transformer models with an attention mechanism for detecting profanity in the Kazakh language and can be used in the development of automated content moderation and information security monitoring systems.

Despite the extensive body of research on fiber Bragg grating (FBG) sensors, embedding FBGs into composite materials still leaves an important challenge unresolved: improving model accuracy while preserving sensitivity under coupled thermo-mechanical loading. In this work, an integrated mathematical model of an FBG-based fiber-optic sensing subsystem is developed and implemented in MATLAB/Simulink, enabling simultaneous estimation of mechanical action (pressure/strain) and temperature from the Bragg-wavelength shift while explicitly accounting for optical, mechanical, and thermal parameters of the composite host. The model combines Bragg-wavelength shift computation with strain-optic and thermo-optic contributions, a composite stress–strain transfer that maps external pressure to axial fiber strain, transient heat transfer to the grating region, and synthesis of the reflected spectrum and optical power profile for interrogation. A calibration-based decoupling stage is included to separate thermal and mechanical components, and the Simulink workflow supports parameter sweeps and uncertainty analysis. Model outputs agree with reference/experimental data, with a discrepancy not exceeding 4% across the considered operating range. Simulations indicate a pressure sensitivity of 5–15 pm/kPa, a refractive-index sensitivity of up to 500 nm/RIU, and a tunable spectral range of 1530–1570 nm, while remaining stable under simultaneous pressure and temperature variations. The proposed model serves as a practical digital prototype for embedded FBG sensing and supports design optimization, compensation-strategy development, and structural health monitoring scenario evaluation.

The paper studies the distribution of relative displacement of a composite plate with integrated fiber Bragg gratings. The analysis of the methods for manufacturing composite plates with embedded optical fibers containing FBG sensors, as well as the spectral characteristics of the gratings under various bending conditions, are performed. The effect of sensor arrangement on the accuracy of determining stresses and relative elongations of the material is experimentally studied. The features of spectral shifts that occur under non-uniform stresses are revealed, which can reduce the accuracy of measurements when using interrogators. The patterns of change in the central wavelength of Bragg gratings depending on the type and magnitude of plate bending are established. The research results confirm that the use of a network of embedded FBG sensors allows one to accurately determine the areas of maximum deformations, as well as the nature and magnitude of bending of composite structures. The data obtained can be used to develop more accurate systems for monitoring the stress–strain state of composite materials.

This paper explores Named Entity Recognition (NER) in the Kazakh language using transformer-based models. NER is a subfield of Natural Language Processing (NLP) that involves the automatic identification of named entities in textual data and their classification into predefined categories. A review of previous studies indicates that further research is needed on this topic in Kazakh texts. Scientific works in the field of information technology were taken as textual data, and in the preparation of dataset, along with named entities, such as the names of people, names of institutions, places of location, terms in the field were marked up in IBO2 format. For the recognition of named entities, the transformer model of the spacy library and the large Llama language model were considered. To solve the task, the internal structural blocks of both models were fully described, a formal description of the implementation of the NER task was given and their fine-tuning was performed. The models were trained on a prepared dataset and various tests were performed. Obtained results are compared with the indicators of other studies and a comparative analysis is presented.

The paper studies the distribution of relative displacement of a composite plate with integrated fiber Bragg gratings. The analysis of the methods for manufacturing composite plates with embedded optical fibers containing FBG sensors, as well as the spectral characteristics of the gratings under various bending conditions, is performed. The effect of sensor arrangement on the accuracy of determining stresses and relative elongations of the material is experimentally studied. The features of spectral shifts that occur under non-uniform stresses are revealed, which can reduce the accuracy of measurements when using interrogators. The patterns of change in the central wavelength of Bragg gratings depending on the type and magnitude of plate bending are established. The research results confirm that the use of a network of embedded FBG sensors allows one to accurately determine the areas of maximum deformations, as well as the nature and magnitude of bending of composite structures. The data obtained can be used to develop more accurate systems for monitoring the stress-strain state of composite materials.

В данной работе рассматривается методика измерения распределения деформаций в композитной пластине из углеродного волокна с использованием волоконно-оптических датчиков Брэгга. Представлен экспериментальный анализ влияния растяжения на центральную длину волны отраженного сигнала ВБР. Исследования проводились на композитных образцах с встроенными оптическими волокнами, размещенными на разных уровнях структуры. Полученные результаты подтверждают возможность использования ВБР для контроля деформаций и напряжений в композитных материалах. Представленные данные могут быть полезны при разработке интеллектуальных конструкций с встроенной системой мониторинга.

In this paper, the types and principles of operation of fiber sensors based on fiber Bragg gratings (FBGs) are investigated. The influence of strain and temperature on the characteristics of FBGs is considered, and a method for the simultaneous measurement of these parameters is presented. Laboratory studies were carried out in the temperature range from +18 °C to +135 °C with an incremental step of 5 °C, with the actual temperature not deviating by more than ±0.5 °C. From the data obtained, the Bragg wavelength–temperature relationships were plotted, which showed a linear increase in wavelength with increasing temperature. This study shows that the use of two FBGs with a different sensitivity to temperature and strain allowed for the simultaneous measurement of both parameters. Numerical models created in the MATLAB R2022b environment confirmed the high accuracy and precision of the measurements. The FBG-based sensors demonstrated a robust performance in harsh environments, withstanding temperatures of up to 160 °C and high humidity, making them applicable in various industries and sciences. This work confirms that FBGs are a promising tool for accurate temperature and strain measurements, providing reliable results in harsh environments.

Road infrastructure is a key public asset because it benefits the social and economic development of any country. It plays an important role in the development of the industrial complex and the production sector, and the surfaces of transport roads should be of high quality and have a long service life. Road infrastructure, like all infrastructure, requires preservation, maintenance and repair. There are special requirements for roadways that must be observed during construction or repair. The uncertainty of the composition, temperature sensitivity and viscoelastic characteristics of road materials make the structural analysis of pavement very difficult compared to other civil structures, such as bridges, tunnels and buildings. For this reason, the question of how to improve fiber sensors based on fiber Bragg grating (FBG) arose. The novelty of this study is to modernize fiber sensors based on FBG so that they display deformation, stress and displacement, temperature and other parameters with much greater accuracy, which would provide a reliable scientific basis for modifying the theory, as well as the use of a fiber sensor based on FBG for simultaneous measurement of deformation and temperature when monitoring the road surface. This article is devoted to a detailed study of the use of fiber-optic sensors (FOS) based on fiber Bragg grating for road surface monitoring. Such a fiber sensor, consisting of a fiber Bragg grating and a pair of grids, can offer the possibility of simultaneous measurement of deformation and temperature for monitoring the pavement. Temperature and deformation measurements were carried out by installing a sensor on the surface of a made asphalt sample. The built-in fiber sensor based on FBG provides important information about how the pavement structure can withstand the load and subsidence of soil and implement road safety and stability measures in a timely manner to evaluate and predict the service life of the pavement. The results of the study showed that the synchronicity, repeatability and linearity of the characteristics of the fiber sensor are excellent. The difference between the experimental and theoretical results was about 7%. Thus, based on the results of the obtained data, the fiber sensor on the FBG can be used for monitoring and designing road surfaces and in general transport infrastructure.

Road infrastructure is a key public asset because it benefits the social and economic development of any country. It plays an important role for the development of the industrial complex, the production sector and the road surfaces of transport roads should be of high quality, have a long service life. Road infrastructure, as well as all infrastructure, requires preservation, maintenance and repair. There are special requirements for the roadway that must be observed during construction or repair. This article is devoted to a detailed study of the use of fiber optics sensors (FOS) based on the fiber Bragg grating (FBG) for road surface monitoring. Such a fiber sensor consisting of a fiber Bragg grid and a pair of grids can offer the possibility of simultaneous measurement of deformation and temperature for monitoring the pavement. Temperature and deformation measurements were carried out by installing a sensor on the surface of a made asphalt sample. The built-in fiber sensor based on FBG provides important information about how the pavement structure can withstand the load, subsidence of soil, timely implement road safety and stability measures evaluate and predict the service life of the pavement. The results of the study showed that the synchronicity, repeatability and linearity of the characteristics of the fiber sensor are excellent. The difference between the experimental and theoretical results is about 7%. Thus, based on the results of the obtained data, the fiber sensor on the FBG can be used for monitoring, designing road surfaces and in general transport infrastructure.

Мақалада алғаш рет сызықтық көп сатылы ойындардың жаңа класын қолдану ұсынылды. Бұл класс ақылды қала жобаларында ойыншылардың қаржылық ресурстарын орналастыру бойынша динамикалық жоспарлау мысалында инвестицияларды жоғалту тәуекелдерін бағалау үдерісін сипаттауға мүмкіндік берді. Қарастырылған тәсілдің ерекшелігі-бірнеше терминалды беттері бар сапалы бейсызықты көп сатылы ойынды шешуге негізделген құралдарды қолдану және аралас стратегиялар класында шешілетін дәреже ойыны.