Alua Turginbayeva

Alua Turginbayeva

Auto-generated profile, based on publicly available information

Alua Turginbayeva

Department of Computer and Software Engineering, Faculty of Information Technologies, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
18 April 2025 in Journal of Computational and Cognitive Engineering
Verified
Journal Article
Open access
PDF file
ABAlibek Barlybayev
Alibek Barlybayev
ATAlua Turginbayeva
Alua Turginbayeva
This research paper describes an improved fuzzy expert system for assessing information security (IS) risks. More and more organizations are facing significant IS problems. These problems arise in protecting corporate information systems from these threats. Traditional IS risk assessment methodologies often have difficulties. Difficulties arise in eliminating ambiguity and uncertainty that are characteristic of these dynamic environments. This study presents a new approach using fuzzy logic. Fuzzy logic is used to accurately identify and evaluate the subtle intricacies of each IS risk factor. Using linguistic variables and fuzzy sets, the proposed system effectively reproduces the reasoning processes. This research paper delineates the formulation of an advanced fuzzy expert system aimed at enhancing IS risk assessments amidst the evolving complexity of cyber threats. By utilizing linguistic variables and fuzzy sets, the proposed system effectively replicates human-like reasoning processes. This allows for a flexible and dynamic framework for risk assessment. This methodology is characterized by the effective integration of both qualitative and quantitative data, resulting in a comprehensive risk assessment model. The usefulness of this model is validated by its application in learning management systems. The systems evaluated include Platonus, SmartENU, Directum, MOOCENU, KPI, and a university website. Quantitative evaluations were conducted according to standards such as NIST 800-30, ISO/IEC 27001, BS 7799, and a proposed model, yielding scores that range from 0.205 to 0.998 across different criteria and systems. Correlation analysis between the standards and the expert-proposed model revealed high consistency, with correlation coefficients ranging from 0.994 to 0.996. These results underline the robustness of the proposed model in aligning closely with established IS standards and suggest its potential for broader application in IS risk assessment. Received: 30 October 2024 | Revised: 17 February 2025 | Accepted: 10 March 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Alibek Barlybayev: Conceptualization, Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Supervision, Project administration, Funding acquisition. Alua Turginbayeva: Methodology, Software, Validation, Resources, Data curation, Visualization.

20 June 2025 in International Journal of Innovative Research and Scientific Studies
Verified
Journal Article
Open access
GSGabit Shuitenov
Gabit Shuitenov
ATAlua Turginbayeva
Alua Turginbayeva
MMMussakan Muratbekov
Mussakan Muratbekov
SASerik Altynbek
Serik Altynbek
SASerik Altynbek
Serik Altynbek
This study aims to develop an integrated hybrid machine learning model that combines sensor-based environmental monitoring for the accurate prediction of aquatic ecosystem dynamics, focusing on key water quality indicators. A novel hybrid framework integrating CatBoost and XGBoost regressors was constructed, optimized through LASSO feature selection, and enhanced by SHAP analysis for interpretability. Real-time data on dissolved oxygen, hardness, transparency, and nutrient content were collected using IoT-enabled multi-parameter water sensors in lakes in Northern Kazakhstan. The hybrid model outperformed individual algorithms, achieving an RMSE of 0.362 for dissolved oxygen predictions. SHAP analysis revealed that nitrate nitrogen, total phosphorus, pH, and suspended solids were the most significant influencing factors. Additionally, the system effectively forecasted impacts on biota, indicating a potential reduction in phytoplankton and an increase in zooplankton populations in 2024. The integration of hybrid machine learning with real-time monitoring significantly improves prediction accuracy and interpretability, providing a practical decision-support tool for environmental agencies and water resource managers to proactively monitor and manage water bodies under the pressures of climate change and anthropogenic influences.

30 September 2025 in Bulletin of Shakarim University. Technical Sciences
Verified
Journal Article
Open access
PDF file
GSGabit Shuitenov
Gabit Shuitenov
ATA. Turginbayeva
A. Turginbayeva
SASerik Altynbek
Serik Altynbek
MMM. Muratbekov
M. Muratbekov
ZYZh. Yessenzholov
Zh. Yessenzholov
This paper presents a secure, transparent, and tamper-resistant web-based voting application. Designed specifically for university-level elections, the system leverages a private blockchain network to ensure the integrity and immutability of each vote. Built using a modern technology stack – TypeScript and React on the frontend, Axios for communication, and a Fastify-based Node.js backend with a MySQL database - the platform prioritizes both usability and security.The voting process is authenticated and validated through cryptographic hashing and blockchain consensus, preventing unauthorized alterations or vote duplication. Each vote is recorded as a transaction on a private blockchain, where nodes verify its legitimacy before it becomes part of the permanent ledger. This system-level integration of blockchain offers auditability, transparency, and trust, eliminating the need for manual verification and reducing the risk of election fraud.The solution is tailored for institutional adoption, ensuring that only authenticated university users can participate. Through this approach, the project demonstrates how blockchain technologies can be practically applied to enhance the credibility and efficiency of digital democratic processes.

30 December 2024 in Bulletin of the National Engineering Academy of the Republic of Kazakhstan
Verified
Journal Article
Closed access
EUEsil University
Esil University
GSGabit Shuitenov
Gabit Shuitenov
SASerik Altynbek
Serik Altynbek
KBKazakh University of Technology and Business
Kazakh University of Technology and Business
ATA. Turginbayeva
A. Turginbayeva
LUL.N. Gumilyov Eurasian National University
L.N. Gumilyov Eurasian National University
This article discusses the process of building a language entropy model, which is an important tool for analyzing and evaluating the information structure of a language. The paper also describes the installation and use of the Apache Spark distributed framework for unstructured data storage and parallel computing. Apache Spark provides high performance and scalability, which is especially important when processing large amounts of data. The authors offer useful recommendations and practical solutions for developers and researchers working with language analysis and processing of unstructured data.

16 September 2020 in Journal of Mathematics, Mechanics and Computer Science
Verified
Journal Article
Open access
PDF file
UTU. K. Turusbekova
U. K. Turusbekova
ATA. S. Turginbayeva
A. S. Turginbayeva
Hash functions are easy-to-compute compression functions that take a variable-length input and convert it to a fixed-length output. Hash functions are used as compact representations, or digital fingerprints, of data and to provide message integrity. In modern cryptography, various hash functions are widely used. The main problem with using hash functions is that the existence of irreversible functions that exclude the possibility of collisions has not been proven. In addition, there are no universal hashing methods, and they should be selected depending on their area of application. A special role is played by complexity-theoretical problems, namely, algebraic number theory. One of these problems is the search for irreducible polynomials of a given degree over a finite field, which can be used to search for message hash codes.The relevance of the study of irreducible polynomials over simple and extended Galois fields is due to their diverse application in various fields of science and technology. Irreducible polynomials have found their application in various fields of mathematics, information technology and information security. Using the properties of irreducible polynomials allows you to maximize the effective computer implementation of arithmetic in finite fields, which is of particular importance for cryptography and coding theory. Finding irreducible polynomials is difficult to compute, especially over large fields. The procedure for finding irreducible polynomials requires efficient algorithms and large computational resources, as in the case of finding prime numbers, which is the main problem for constructing effective hashing algorithms based on them. This article describes a method for constructing hash functions based on calculating the remainder of a division by irreducible polynomials. In addition, the problem of searching for irreducible polynomials is considered. Computer modeling of hash functions using irreducible polynomials over finite fields has been performed. The results of using various irreducible polynomials and their analysis are presented. The results of the article can be used in cryptographic applications and coding theory. Қазіргі заманғы криптографияда әр түрлі хеш-функциялары кеңінен қолданылады. Хэш - функциялар - бұл өзгермелі ұзындықтағы кіріс қорын қабылдап, оларды тұрақты ұзындықтағы шығыс қорына түрлендіретін, есептеуге оңай сығымдау функциялары. Олар хабарламаның тұтастығын қамтамасыз ету үшін ықшам көріністер немесе сандық саусақ іздері ретінде қолданылады. Хеш-функцияларын қолданудағы негізгі мәселе соқтығысулар мүмкіндігін жоққа шығаратын қайтымсыз функциялардың болуының дәлелденбенуі болып табылады. Сонымен қатар, хештеудің әмбебап әдістері жоқ және оларды қолдану саласына қарай таңдаған жөн. Ерекше рөлді теориялық-күрделілік проблемалары, атап айтқанда алгебралық сандар теориясы атқарады. Осындай проблемалардың бірі ақырлы өрісте дәрежесі берілген келтірілмейтін көпмүшеліктерді іздеу болып табылады, оларды хабарламалардың хеш-кодтарын іздеуде қолдануға болады. қарапайым және кеңейтілген Галуа өрістерінде келтірілмейтін көпмүшеліктерді зерттеудің өзектілігі олардың ғылым мен техниканың әр түрлі салаларында түрлі қолданылуымен байланысты. Келтірілмейтін көпмүшеліктер математиканың, ақпараттық технологияның және ақпараттық қауіпсіздіктің әр түрлі салаларында қолданыс тапты. Келтірілмейтін көпмүшеліктердің қасиеттерін қолдану арифметиканың ақырлы өрістерде компьютерлік тиімді іске асырылуын арттыруға мүмкіндік береді, ал бұл, өз кезегінде, криптография мен кодтау теориясы үшін ерекше маңызды. Келтірілмейтін көпмүшеліктерді табу есептеу үшін, әсіресе өлшемі үлкен өрістер үшін күрделі мәселе болып табылады. Келтірілмейтін көпмүшеліктерді іздеу процедурасы жай сандар жағдайындағы сияқты тиімді алгоритмдер мен үлкен есептеу қорларын қажет етеді, ал бұл, өз кезегінде, олардың негізінде тиімді хештеу алгоритмдерін құру үшін негізгі мәселелердің бірі болып табылады. ұсынылған мақалада хеш-функцияларды құрудың келтірілмейтін көпмүшелікке бөлгендегі қалдықты есептеуге негізделген әдісі сипатталған. Сонымен қатар, келтірілмейтін көпмүшеліктерді іздеу мәселесі қарастырылады. Ақырлы өрістерде келтірілмейтін...

8 May 2026 in IEEE Access
Verified
Journal Article
Open access
GSGabit Shuitenov
Gabit Shuitenov
SASerik Altynbek
Serik Altynbek
MMMadi Muratbekov
Madi Muratbekov
ATAlua Turginbayeva
Alua Turginbayeva
AAAkbota Abylayeva
Akbota Abylayeva
NTNurlan Tashatov
Nurlan Tashatov
Ensuring reproducibility and trustworthiness in intelligent systems has become a cornerstone of applied systems innovation. This study introduces HyCoSS++, a deterministic machine learning framework with simulated ledger-based audit anchoring that formalizes verifiable reproducibility and auditability within AI-driven architectures. The proposed approach integrates cryptographic provenance mechanisms - SHA-256 hashing and Merkle root aggregation into a calibrated ensemble learning pipeline designed for consistent, transparent, and tamper-resistant computation. By embedding deterministic execution and version-controlled environments, HyCoSS++ guarantees identical outputs under identical conditions, addressing the reproducibility crisis across computational sciences. Beyond algorithmic performance, the framework represents a system-level innovation, combining reproducible computing, trustworthy AI, and cryptographically verifiable auditability to create verifiable intelligent infrastructures. Experimental evaluation demonstrates stable calibration, traceable model lineage, and high reproducibility without compromising accuracy. The proposed methodology provides a transferable foundation for auditable, explainable, and reproducible intelligent systems, aligning with the core mission of applied system innovation research.