Syrym Zhakypbekov

Mr. Syrym Zhakypbekov

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 March 2025 in Herald of the Kazakh-British technical university
Verified
Journal Article
Open access
PDF file
NKN. Komarov
N. Komarov
SMSamat Mukhanov
Samat Mukhanov
IBIkram Bazarbekov
Ikram Bazarbekov
SZSyrym Zhakypbekov
Syrym Zhakypbekov
SSS. Y. Sibanbayeva
S. Y. Sibanbayeva
This article explores the methods of processing and analyzing big data in order to improve the accuracy and efficiency of machine learning (MO) models. The main focus is on classification problems, the effectiveness of algorithms such as XGBoost, the support vector machine (SVM), ensemble methods, as well as systems for working with big data, including Hadoop and Apache Spark. The key stages of working with data are described: cleaning, normalization, selection of features, which is critically important for building stable models on large amounts of data. Accuracy, completeness, F-measure, and AUC-ROC metrics were used to evaluate the effectiveness of the algorithms, which made it possible to conduct a comparative analysis and identify the most productive approaches. Special attention is paid to the application of MO in the context of organizational innovations, including the tasks of classification, forecasting the success of innovations and innovation portfolio management. Recommendations on the choice of technologies and algorithms for various data types and scales are presented, and prospects for integrating distributed computing platforms with MO algorithms to achieve scalable and efficient solutions are discussed.

18 February 2025 in Вестник КазАТК
Verified
Journal Article
Open access
PDF file
SMSamat Mukhanov
Samat Mukhanov
SASaltanat Amirgaliyeva
Saltanat Amirgaliyeva
DADaryn Amrin
Daryn Amrin
SZSyrym Zhakypbekov
Syrym Zhakypbekov
BABeibut Amirgaliyev
Beibut Amirgaliyev
Forecasting stock prices has always been a complex and challenging task due to its high volatility, noise in data, and abrupt price fluctuations caused by different factors. Traditional approaches, such as quantitative, fundamental, and technical analysis, often struggle to accurately predict stock price movements due to their difficulty in processing non-linear data. The evolution of machine learning, particularly neural network models, opened new opportunities for improving prediction accuracy by handling non-linear and multidimensional data with high effectiveness. This study focuses on evaluating and comparing three neural network architectures, in which the last is a combination of the first two - Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model, for forecasting stock prices. Using ten years of historical stock data, taken for Apple Inc. (AAPL) stocks as an example, ranging from 2015 to 2025, the models were trained and tested on key performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R². Results show that while both CNN and LSTM models show good performance individually, the hybrid CNN-LSTM model can significantly outperform them, achieving the highest accuracy with the lowest error rates. By combining the strengths of CNN for feature extraction and LSTM for temporal sequence processing, the hybrid model effectively captures complex patterns in stock price movements. By iterating over the types of layers to use, we came to the conclusion, that by combining both models into one hybrid model, some layers, like one CNN layer, and one LSTM layer should be removed. This research demonstrates the potential of hybrid neural network models in financial time-series forecasting and comprehensively analyzes their advantages over non-hybrid models.

25 May 2026 in Bulletin of Shakarim University. Technical Sciences
Verified
Journal Article
Open access
PDF file
AKA. Kenzhebay
A. Kenzhebay
ATA. Tynykulova
A. Tynykulova
GYG. Yensebayeva
G. Yensebayeva
SZSyrym Zhakypbekov
Syrym Zhakypbekov
KBK. Bakenova
K. Bakenova
ГЕГ. Енсебаева
Г. Енсебаева
The rapid development of additive manufacturing technologies imposes increasingly stringent requirements on the positioning accuracy and dynamic stability of motion systems, particularly in printers employing H-bot kinematic architectures, which are prone to torsional vibrations. Such vibrations significantly degrade print quality by inducing trajectory deviations of the print head and cannot be effectively mitigated solely through mechanical reinforcement or conventional control strategies. This study proposes a software-based torsional vibration compensation method founded on the use of filtered B-splines for motion trajectory correction at the planning stage. Unlike existing approaches that rely on rigid digital filtering or realtime adaptive control, the proposed method combines the high approximation capability of B-splines with selective attenuation of spectral components responsible for resonant torsional oscillations. A mathematical model of torsional vibrations in H-bot frame structures is developed, followed by a spectral analysis of their dynamic characteristics to justify the applicability of B-spline-based filtering for identifying and compensating critical frequency components. Numerical simulation results demonstrate a substantial reduction in vibration amplitude and a corresponding decrease in trajectory tracking error of the print head. The practical relevance of the proposed approach lies in its ability to be integrated into standard trajectory planning algorithms without hardware modification, making it applicable to a wide class of H-botbased additive manufacturing systems.

15 March 2025 in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
Verified
Journal Article
Closed access
СМС.б. Муханов
С.б. Муханов
ДАД.м. Амрин
Д.м. Амрин
SZSyrym Zhakypbekov
Syrym Zhakypbekov
Растущая зависимость от облачных вычислений принесла как замечательные возможности, так и сложные проблемы. Распределенные сети, такие как среды облачных вычислений, по своей сути динамичны и требуют надежных систем для эффективной обработки изменяющихся рабочих нагрузок. В данномисследовании изучаются сложные взаимодействия между несколькими моделями массового обслуживания в изучаемыхсистемах, что дает свежий взгляд на их влияние на производительность. Используя теорию массового обслуживания, авторыуглубляются в ключевые показатели, такие как время отклика и стратегии распределения ресурсов. Проведенный анализ подчеркивает преимущества горизонтального масштабирования, вертикального масштабирования и критическую роль пропускной способности сети в оптимизации производительности облачной инфраструктуры. Результаты не только демонстрируют практическое применение теории массового обслуживания, но и под-черкивают ее ценность в решении реальных проблем в распределенных сетях. Это ис-следование закладывает основу для будущих исследований в области прогностических моделей и гибридных подходов, прокладывая путь для более умных, более масштаби-руемых облачных решений.

10 January 2025 in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
Verified
Journal Article
Closed access
СМС.б. Муханов
С.б. Муханов
ААА.р. Абдул
А.р. Абдул
ZBZhansaya Mukhamedikyzy Bekaulova
Zhansaya Mukhamedikyzy Bekaulova
SZSyrym Zhakypbekov
Syrym Zhakypbekov
В данной работе рассматривается сбор данных и применение моделей нейронных сетей для классификации языка жестов в задачах распознавания образов. Язык жестов, как важный способ коммуникации для людей с нарушениями слуха, требует эффективных технологий для его автоматического распознавания. В ходе исследования был проведён сбор разнообразных видеоданных, охватывающих различные жесты и контексты их использования. Для анализа этих данных применялись современные архитектуры нейронных сетей, включая сверточные и рекуррентные сети, что позволило достичь высокой точности классификации. Результаты показывают перспективность использования глубокого обучения для распознавания языка жестов, что открывает новые возможности для разработки вспомогательных технологий и улучшения качества жизни людей с ограниченными возможностями. Работа подчеркивает важность интеграции методов машинного обучения и компьютерного зрения для создания более интуитивно понятных интерфейсов взаимодействия.

27 October 2026 in Informatics
Verified
Journal Article
Open access
PDF file
SZSyrym Zhakypbekov
Syrym Zhakypbekov
ABArtem Bykov
Artem Bykov
VYVera Alexandrovna Yermakova
Vera Alexandrovna Yermakova
AZAliya Zhuginissova
Aliya Zhuginissova
MVMarco Angelo Vasquez
Marco Angelo Vasquez
This paper presents a criteria-governed, human-in-the-loop information system architecture integrating formative AI-assisted learning with preliminary assessment of spoken and written responses. It supports two modes: a retrieval-augmented assistant answering from course materials and an AI examiner scoring responses against a predefined rubric, criterion by criterion. The language model is confined to analysis: evidence extraction, aggregation, input-quality control, uncertainty estimation and escalation are performed by a controlled pipeline, and each result is stored as a structured decision object carrying criteria, evidence, provenance, uncertainty and teacher-verification status. Across 168 examination sessions and 1074 criterion-level decisions, every decision carried a verbatim evidence passage (100% coverage), the overall score matched the programmatic aggregation in all finalized sessions, 39.1% of responses were routed for secondary analysis and 5.4% of sessions were escalated. A survey of 52 students rated question clarity 4.81, criterion-level feedback 4.46, and allotted time 4.42, while concerns persisted about scoring reliability and recognition errors. In a preliminary blind calibration, the AI ranked 13 spoken answers like human raters (r = 0.75), but scored them 22 points lower. The contribution is the architecture and its feasibility in deployment; the study does not establish automated-scoring accuracy, and final decisions remain with the teacher.