Maxot Eleusizovich Rakhmetov

Prof. Dr. Maxot Eleusizovich Rakhmetov

Department of Computer Science, Atyrau State University named of Kh.Dosmukhamedova, Atyraū, Kazakhstan
orcid
AI in educational and Computer Science

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
13 October 2025 in Electronic Journal of e-Learning
Verified
Journal Article
Open access
PDF file
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
ASAigul Sadvakassova
Aigul Sadvakassova
GSGaliya Saltanova
Galiya Saltanova
BKBayan Kuanbayeva
Bayan Kuanbayeva
GZGaliya Zhusupkalieva
Galiya Zhusupkalieva
The development of self-regulated learning (SRL) skills, including the ability to plan, monitor and reflect, is increasingly recognised as essential for academic success in online learning environments. Despite this, most digital learning platforms continue to provide limited feedback, typically focused on task outcomes rather than learning processes. This study investigates the effectiveness of an artificial intelligence-based feedback system integrated into a standard online course platform. The system delivers adaptive, process-oriented feedback by analysing anonymised engagement summaries and short reflective inputs, aiming to promote self-regulated learning strategies without requiring additional instructor involvement or manual input for feedback generation. A quasi-experimental study was conducted with 180 undergraduate students enrolled in a fully online course. Participants were pseudo-randomly assigned by an automated allocation script to an experimental group (n = 90) receiving AI-based adaptive feedback or a control group (n = 90) with standard LMS features. The system employed behavioural indicators (e.g., time-on-task, quiz activity and content engagement) and natural language analysis of reflective entries to generate personalised prompts related to goal-setting (including time management), effort regulation and metacognitive reflection. Data sources included post-course surveys, aggregated system interaction records, academic performance data and open-ended student feedback on the system’s perceived effectiveness and usability. Students who received adaptive feedback exhibited significantly stronger engagement with SRL behaviours, including earlier task initiation, increased use of optional learning resources and greater consistency in study routines. Qualitative responses indicated that participants found the feedback clear, timely, actionable and supportive of their cognitive and motivational processes. In contrast, control group participants primarily relied on grade-based feedback and exhibited fewer strategic adjustments during the course. The findings suggest that a lightweight, AI-driven feedback mechanism can be effectively integrated into online course platforms to support SRL at scale. This study demonstrates how adaptive AI feedback can meaningfully influence academic outcomes, planning behaviour and engagement with feedback in digital learning environments.

1 January 2026 in International Journal of Information and Education Technology
Verified
Journal Article
Open access
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
EAElmira Abdykerimova
Elmira Abdykerimova
GAGadilbek Alzhanov
Gadilbek Alzhanov
BOBalaussa Orazbayeva
Balaussa Orazbayeva
BKBayan Kuanbayeva
Bayan Kuanbayeva
Artificial Intelligence (AI) opens up new perspectives for the transformation of distance learning; however, there is still no clearly structured methodological framework for the development of effective AI-based learning platforms. This study proposes the framework model “learning behavior – AI-oriented scenarios”, which aims to identify key pedagogical and technological factors that contribute to effective learning in a digital environment. Based on an analysis of the scientific literature in educational technologies and the use of AI in teaching, the main characteristics of learning behavior are identified: personalized goal setting, adaptive response to feedback, and autonomous engagement. These characteristics correspond to constructivist and experiential approaches to learning. The study examines how intelligent recommendation systems, adaptive content, and AI-based learning behavior analytics contribute to the development of these characteristics and enhance educational outcomes. As an example, a case study is presented on the development of a prototype AI platform for distance learning, whose effectiveness is supported by survey results demonstrating increased student motivation and engagement. The findings address three key research questions and contribute to the theoretical and methodological foundation for integrating AI into the design of distance education.

3 March 2026 in Frontiers in Education
Verified
Journal Article
Open access
PDF file
ZZZhandos Zulpykhar
Zhandos Zulpykhar
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
BJBakytgul Jugembayeva
Bakytgul Jugembayeva
DKDameli Kapanova
Dameli Kapanova
RZRaushan Zhilmagambetova
Raushan Zhilmagambetova
Scientific research on the assessment of educational outcomes using artificial intelligence technologies in higher education is still fragmented, especially in the context of Ibero-American countries and the transforming educational systems, which include Kazakhstan. Despite the active introduction of digital platforms, analytical tools, and automated assessment systems, comprehensive research revealing innovative approaches, methodological foundations, and ethical aspects of AI-based assessment remains limited. In this regard, this mini-review is aimed at filling the identified research gap by analyzing key theoretical works and modern empirical studies that determine the prospects for further development of this field. The methodological basis of the review is a conceptual model that considers assessment using artificial intelligence as a multi-level system that includes automated analysis of educational data, personalized feedback, predictive evaluation mechanisms, and algorithmic support for pedagogical decisions. Within the framework of this model, assessment is interpreted not as an isolated control tool, but as an integrated component of the educational environment that influences individual learning trajectories, academic success and student engagement. It should be noted that this mini-review is one of the first studies in which this conceptual framework is applied to a comparative analysis of assessment practices using artificial intelligence in the Ibero-American and Kazakh contexts of higher education. The review included 12 peer-reviewed scientific publications published since 2020, which addressed the issues of automated assessment, learning analytics, adaptive feedback systems and ethical aspects of the introduction of artificial intelligence in the university environment of these regions. The paper analyzes the main innovations in the field of AI-based assessment, including the use of behavioral and cognitive analytics, automated formative assessment, forecasting academic risks and personalized assessment support for students. Special attention is paid to contextual factors such as the level of digital readiness of students, the institutional features of universities, as well as differences in assessment practices between public and private educational organizations. Along with technological innovations, the mini-review examines the key ethical challenges associated with the use of artificial intelligence in assessing educational achievements. Such challenges include algorithmic bias, limited transparency of assessment decisions, issues of protecting students’ personal data, and the risks of increasing educational inequality. The analysis shows that the manifestation of these ethical issues varies in Ibero-American countries and Kazakhstan, reflecting differences in educational policies, the level of digital infrastructure, and socio-economic conditions. Based on research using a variety of methodological approaches, including quantitative, qualitative, and mixed designs, this mini-review demonstrates the multiplicity of interpretations and practices of applying artificial intelligence in higher education assessment. At the same time, the need to expand interdisciplinary research aimed at analyzing poorly studied categories of students and alternative educational trajectories in the digital environment is emphasized. In conclusion, the educational and ethical implications of further implementation of AI-based assessment in higher education are considered. Given the increasing role of automated assessment systems and the desire of universities to improve the objectivity and fairness of assessment, the development of methodologically sound and ethically responsible models for the use of artificial intelligence is of particular relevance. At the same time, taking into account the regional characteristics of educational systems makes the comparative analysis of the Ibero-American and Kazakh experience an important area of modern research in the field of digital education.

14 January 2026 in Computation
Verified
Journal Article
Open access
PDF file
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
AAAinagul Adiyeva
Ainagul Adiyeva
BOBalaussa Orazbayeva
Balaussa Orazbayeva
Shynar YelezhanovaShynar Yelezhanova
Shynar Yelezhanova
RTRaigul Tuleuova
Raigul Tuleuova
RMRaushan Moldasheva
Raushan Moldasheva
Nonlinear single-input single-output (SISO) systems operating under parametric uncertainty often exhibit bifurcations, multistability, and deterministic chaos, which significantly limit the effectiveness of classical linear, adaptive, and switching control methods. This paper proposes a novel synthesis framework for self-organizing control systems based on catastrophe theory, specifically within the class of elliptic catastrophes. Unlike conventional approaches that stabilize a predefined system structure, the proposed method embeds the control law directly into a structurally stable catastrophe model, enabling autonomous bifurcation-driven transitions between stable equilibria. The synthesis procedure is formulated using a Lyapunov vector-function gradient–velocity method, which guarantees aperiodic robust stability under parametric uncertainty. The definiteness of the Lyapunov functions is established using Morse’s lemma, providing a rigorous stability foundation. To support practical implementation, a data-driven parameter tuning mechanism based on self-organizing maps (SOM) is integrated, allowing adaptive adjustment of controller coefficients while preserving Lyapunov stability conditions. Simulation results demonstrate suppression of chaotic regimes, smooth bifurcation-induced transitions between stable operating modes, and improved transient performance compared to benchmark adaptive control schemes. The proposed framework provides a structurally robust alternative for controlling nonlinear systems in uncertain and dynamically changing environments.

29 December 2025 in Eastern-European Journal of Enterprise Technologies
Verified
Journal Article
Open access
PDF file
ASAivar Sakhipov
Aivar Sakhipov
AMAruzhan Mektepbayeva
Aruzhan Mektepbayeva
ATAmangul Talgat
Amangul Talgat
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
AAAinagul Adiyeva
Ainagul Adiyeva
Shynar YelezhanovaShynar Yelezhanova
Shynar Yelezhanova
The object of the study is the adaptive machine learning systems that are able to process large amounts of rapidly changing streaming data in real time. The problem of maintaining prediction accuracy and computational efficiency in the presence of concept drift is treated. Concept drift refers to the overweighting of static models when stationary models are tried, and the nature of the underlying distributions changes. The adaptive architecture includes revision divergence-oriented concept drift detection, incremental model updating via hyper-dimensional statistical clustering of segments. Results from experiments using simulated and real-world datasets demonstrate that the adaptive architecture maintains predictive accuracy above 0.83 across abrupt, gradual, recurrent, and continuous drift scenarios. Compared with non-adaptive models, adaptation latency is reduced by approximately 2.6×, while unnecessary retraining operations are decreased by up to 40%. These results are possible due to the fact that proposed framework is able to retrain solutions if, and only if, distributional changes are determined to be statistically significant and meaningful to the model. This leads to the avoidance of processors being given redundant computations and providing a steady-state model during non-drift conditions. A principal contribution is that feature engineering is accomplished in a drift-aware manner, thresholding is made adaptive to the distributions indicated, and update mechanisms are employed which efficiently utilize resources in a unified high-performance streaming pipeline. The architecture performs well under abrupt, gradual, recurrent, and continuous drift and effective for real-time applications which include smart-city analytics, cyber security monitoring, roadways system works, and IoT for industrial systems

11 June 2025 in International Journal of Innovative Research and Scientific Studies
Verified
Journal Article
Open access
SNSaniya Nariman
Saniya Nariman
Maxot Eleusizovich RakhmetovMaxot Eleusizovich Rakhmetov
Maxot Eleusizovich Rakhmetov
GNGulmira Nurbekova
Gulmira Nurbekova
GIGulnur Issakova
Gulnur Issakova
BOBalaussa Orazbayeva
Balaussa Orazbayeva
This article presents a comparative analysis of the capabilities of the Creo Parametric graphics system in comparison with other popular software products. Special attention is paid to the specifics of working with assemblies in the full-featured NX CAD system, as well as the process of creating a three-dimensional model of a part in SolidWorks. The application areas of graphics systems such as NX and CATIA are also considered. The principle of building a 3D model in the T-FLEX CAD system is investigated. In addition, the possibilities, approaches, and principles of operation of applications of the Creo Parametric graphics system are analyzed. To improve the performance and quality of work in graphics systems, it is recommended to use each of them in those areas of industry where they demonstrate clear advantages. In the engineering industry, the use of the Creo Parametric CAD system is especially advantageous, as it allows you to combine two approaches — parametric and direct modeling. Furthermore, it is convenient to work with small applications and supports the import of formats from computer-aided design (CAD) systems from other manufacturers.