Zhanar Lamasheva

Dr. Zhanar Lamasheva

Institute of Digital Sciences and Artificial Intelligence, L.N. Gumilyov Eurasian National University, Nur-Sultan, Astana, Kazakhstan
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 August 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
AKAislu Kassekeyeva
Aislu Kassekeyeva
SASadvakassov Arman Ashatuly
Sadvakassov Arman Ashatuly
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
Seyit KerimkhulleSeyit Kerimkhulle
Seyit Kerimkhulle
AZAbdrakhmanova Alfiya Zagievna
Abdrakhmanova Alfiya Zagievna
OOOralkhanov Berdibek Oralkhanuly
Oralkhanov Berdibek Oralkhanuly
This article presents the proper organization of the supply chain to meet consumer demand, which is crucial for modern commercial enterprises involved in the sale of various products. Studies indicate that a company's success is linked to the satisfaction of its customers. To optimize the supply chain, this study will consider the use of artificial neural network models. The results of this model will seek a balance between demand and supply, helping determine the necessary quantity of goods to satisfy demand and prevent overproduction. By using this model, the company can fully meet the needs of its customers. Additionally, the company saves its resources and labor costs and reallocates them to other tasks. The model demonstrates the optimization of production and supply business processes, as well as an increase in efficiency.

29 December 2022 in IEEE Access
Verified
Journal Article
Open access
MZMakpal Zhartybayeva
Makpal Zhartybayeva
NMNurzhan Muntayev
Nurzhan Muntayev
STSymbat Tulegenova
Symbat Tulegenova
ZOZhanar Oralbekova
Zhanar Oralbekova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
KIKazizat Iskakov
Kazizat Iskakov
As a result of anthropogenic impact, significant changes occur in the morphometric, hydrological, chemical and other characteristics of water bodies, which in turn leads to changes in the structure, productivity and condition of aquatic ecosystems. Pollution of water bodies is the result of anthropogenic activities that lead to negative consequences - deterioration of water quality, threat to water bodies, deterioration of life and health of people. In order to monitor the water ecosystems of Akmola region, the research team took water samples from water bodies (Nura, Ishim Rivers of the Republic of Kazakhstan, Akmola region and Taldykol, Maybalyk and Zhaltyrkol Lakes), collected them in a database and conducted research.We constructed a mathematical model, after which the results were compared with full-scale data.According to water samples, the level of pollution of water sources was evaluated, the obtained data was entered into the database of the water ecosystem of Akmola region, and the collected data was predicted using the ARIMA (autoregressive integrated moving average) model and the R programming language.

5 August 2025 in Technologies
Verified
Journal Article
Open access
PDF file
VRValiya Ramazanova
Valiya Ramazanova
MSMadina Sambetbayeva
Madina Sambetbayeva
SSSandugash Serikbayeva
Sandugash Serikbayeva
Aigerim YerimbetovaAigerim Yerimbetova
Aigerim Yerimbetova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
GKGulzhamal Kalman
Gulzhamal Kalman
This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals.

29 December 2025 in Frontiers in Computer Science
Verified
Journal Article
Open access
PDF file
AMAinur Mukashova
Ainur Mukashova
JTJamalbek Tussupov
Jamalbek Tussupov
SSSandugash Serikbayeva
Sandugash Serikbayeva
AMAyagoz Mukhanova
Ayagoz Mukhanova
MSMuslim Sergaziyev
Muslim Sergaziyev
VRValiya Ramazanova
Valiya Ramazanova
The rapid evolution of the labor market necessitates innovative approaches to align higher education curricula with professional standards. This study presents an AI-driven framework utilizing the GPT model to automate the formalization of professional competencies and learning outcomes from unstructured textual sources, such as professional standards and job descriptions. By transforming unstructured industry standards and job descriptions into structured competency maps, the framework ensures alignment with labor market needs. These maps are integrated into learning management systems (LMS) such as Canvas and Moodle, enabling the development of adaptive curricula. The methodology was validated using a dataset of professional standards from various industries, achieving a 30% increase in semantic accuracy compared to traditional methods. In addition, a multi-class classification task using Multinomial Naive Bayes, Gaussian Naive Bayes, and Random Forest models classified learning outcomes across college, undergraduate, graduate, and doctoral levels, achieving an accuracy score of 0.98, further confirming their applicability across qualification systems. Challenges such as technological inequalities and lack of pedagogical flexibility remain. This scalable approach enables educational institutions to bridge the gap between academia and industry, helping to produce employable graduates.

6 January 2026 in Electronics
Verified
Journal Article
Open access
PDF file
AZAltanbek Zulkhazhav
Altanbek Zulkhazhav
GBGulmira Bekmanova
Gulmira Bekmanova
BYBanu Zh Yergesh
Banu Zh Yergesh
ANAizhan Nazyrova
Aizhan Nazyrova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
GAGaukhar Aimicheva
Gaukhar Aimicheva
This paper presents a hybrid architecture for automatic sentiment analysis of Kazakh-language political discourse. The Kazakh language is characterized by an agglutinative structure, a complex word-formation system, and the limited availability of digital resources, which significantly complicates the application of standard neural network approaches. To account for these characteristics, a multi-level system was developed that combines morphological and syntactic analysis rules, ontological relationships between political concepts, and multilingual representations of the XLM-R model, used in zero-shot mode. A corpus of 12,000 sentences was annotated for sentiment polarity and used for training and evaluation, while Universal Dependencies annotation was applied for morpho-syntactic analysis. Rule-based components compensate for errors related to affixation variability, modality, and directive constructions. An ontology comprising over 300 domain concepts ensures the correct interpretation of set expressions, terms, and political actors. Experimental results show that the proposed hybrid architecture outperforms both neural network baseline models and purely rule-based solutions, achieving Macro-F1 = 0.81. Ablation revealed that the contribution of modules is unevenly distributed: the ontology provides +0.04 to Macro-F1, the UD syntax +0.08, and the rule-based module +0.11. The developed system forms an interpretable and robust assessment of tonality, emotions, and discursive strategies in political discourse, and also creates a basis for further expansion of the corpus, additional training of models, and the application of hybrid methods to other tasks of analyzing low-resource languages.

8 July 2026 in Frontiers in Computer Science
Verified
Journal Article
Open access
PDF file
AOAssel Omarbekova
Assel Omarbekova
ANAizhan Nazyrova
Aizhan Nazyrova
GBGulmira Bekmanova
Gulmira Bekmanova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
AGAlbina Gibadullina
Albina Gibadullina
AAAssem Abdikarim
Assem Abdikarim
Academic stress among university students represents a major public health concern due to its detrimental effects on cognitive functioning, psychological well-being, and long-term academic performance. Although machine learning has increasingly been applied to stress prediction, existing studies commonly rely on single datasets, insufficiently address class imbalance, and provide limited model interpretability. This study proposes a comparative machine learning framework that integrates explainable artificial intelligence (XAI), ablation analysis, and statistical significance testing to improve the classification of student stress. Two complementary datasets were analysed. Dataset 1 included 777 university students aged 18–22 years with three stress-type categories (Eustress, Distress, and No Stress), while Dataset 2 comprised 1,100 records with 20 psychological, physiological, environmental, and academic features labelled according to three stress severity levels (Low, Medium, and High). Five supervised learning algorithms—Logistic Regression, Random Forest, Gradient Boosting, Support Vector Machine with a radial basis function kernel, and Multilayer Perceptron—were evaluated using 10-times repeated stratified 5-fold cross-validation. Severe class imbalance in Dataset 1 (91.4% Eustress) was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), and its impact was quantified through a structured ablation study. Model performance differences were assessed using the Friedman test with post-hoc Nemenyi analysis, and SHAP was employed to provide global and class-specific model interpretability. The Friedman test demonstrated statistically significant differences among classifiers ( χ ² = 68.97, * p * < 0.001), with post-hoc analysis identifying Random Forest and Logistic Regression as the statistically superior-performing models. Random Forest achieved the highest overall classification accuracy (0.8909) and the lowest log loss (0.2057), whereas Logistic Regression produced the highest discriminative performance (AUC-ROC = 0.9853). The ablation study confirmed that SMOTE substantially improved minority-class prediction performance. SHAP analysis identified blood pressure, sleep quality, teacher–student relationship, and academic performance as the most influential predictors of overall stress severity, while self-esteem, sleep quality, bullying, and anxiety level were the strongest contributors to the High Stress class. The proposed framework provides a reproducible, interpretable, and statistically validated approach for multi-class stress classification among university students. By combining class imbalance correction, rigorous comparative evaluation, explainable artificial intelligence, and statistical validation, the framework addresses important methodological limitations of previous studies and offers a robust foundation for the development of early stress detection and intervention systems in higher education.