Ainur Orazayeva

Ainur Orazayeva

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
30 June 2022 in Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
Verified
Journal Article
Open access
PDF file
AOAinur Orazayeva
Ainur Orazayeva
JTJamalbek Tussupov
Jamalbek Tussupov
WWWaldemar Wójcik
Waldemar Wójcik
SPSergii Pavlov
Sergii Pavlov
GAGulzira Abdikerimova
Gulzira Abdikerimova
LSLiudmyla Savytska
Liudmyla Savytska
This paper is devoted to topical issues - the development of methods for analyzing texture images of breast cancer. The main problem that is resolved in the article is that the requirements for the results of pre-processing are increasing. As a result of the task, images of magnetic resonance imaging of the breast are considered for image processing using texture image analysis methods. The main goal of the research is the development and implementation of algorithms that allow detecting and isolating a tumor in the breast in women in an image. To solve the problem, textural features, clustering, orthogonal transformations are used. The methods of analysis of texture images of breast cancer, carried out in the article, namely: Hadamard transform, oblique transform, discrete cosine transform, Daubechies transform, Legendre transform, the results of their software implementation on the example of biomedical images of oncological pathologies on the example of breast cancer, it is shown that The most informative for image segmentation is the method based on the Hadamard transform and the method based on the Haar transform. The article presents recommendations for using the results in practice, namely, it is shown that clinically important indicators that make a significant contribution to assessing the degree of pathology and the likelihood of developing diseases, there are other information parameters: diameter, curvature, etc. Therefore, increased requirements for the reliability, accuracy, speed of processing biomedical images.

1 October 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
AOAinur Orazayeva
Ainur Orazayeva
JTJamalbek Tussupov
Jamalbek Tussupov
GSGulmira Shangytbayeva
Gulmira Shangytbayeva
AGAssem Galymova
Assem Galymova
UZUlzhalgas Muratbekovna Zhunissova
Ulzhalgas Muratbekovna Zhunissova
ZKZhanat Kenzhebayeva
Zhanat Kenzhebayeva
This work is devoted to the research and development of methods for effectively identifying breast pathologies using modern machine learning technologies, such as you only look once (YOLOv8) and faster region-based convolutional neural network (R-CNN). The paper presents an analysis of existing approaches to the diagnosis of breast diseases and an assessment of their effectiveness. YOLOv8 and Faster R-CNN architectures are then applied to create pathology detection models in mammography images. The work analyzed and classified identified breast pathologies at six levels, taking into account different degrees of severity and characteristics of the diseases. This approach allows for more accurate determination of disease progression and provides additional data for more individualized treatment planning. Classification results at various levels can improve the quality of medical decisions and provide more accurate information to doctors, which in turn improves the overall efficiency of diagnosis and treatment of breast diseases. Experimental results demonstrate high accuracy and speed of image processing, providing fast and reliable detection of potential breast pathologies. The data obtained confirm the effectiveness of the use of machine learning algorithms in the field of medical diagnostics, providing prospects for the further development of automated systems for detecting breast diseases in order to improve early diagnosis and treatment efficiency.

28 July 2021 in Optoelectronic Information-Power Technologies
Verified
Journal Article
Open access
PDF file
AOAinur Orazayeva
Ainur Orazayeva
JTJamalbek Tussupov
Jamalbek Tussupov
SPSergii Pavlov
Sergii Pavlov
STS.V. Tymchyk
S.V. Tymchyk
NSN.B. Savina
N.B. Savina
OBO.S. Bezkrevnyi
O.S. Bezkrevnyi
The article analyzes the growing incidence of breast cancer, which has become particularly clear in the last two decades, requires special involvement of all specialists and researchers in this area. Identification of patients with hereditary forms of breast cancer allows to form strategies for early diagnosis, prevention and treatment. As a result of the analysis, the multiple regression equation was obtained.The statistical significance of the equation was verified using the coefficient of determination and Fisher's test. Prompt diagnosis should be combined with effective cancer treatment, which in many cases requires specialized cancer care at some level. Thanks to the creation of centralized services in oncology facilities or hospitals, which use as a model everything related to breast cancer, the treatment of breast cancer can be optimized while improving the treatment of other cancers.

25 May 2026 in Bulletin of Shakarim University. Technical Sciences
Verified
Journal Article
Open access
PDF file
MYM. Zh. Yergesh
M. Zh. Yergesh
BYBanu Zh Yergesh
Banu Zh Yergesh
AOAinur Orazayeva
Ainur Orazayeva
АTА. Talgat
А. Talgat
АОА. Р. Оразаева
А. Р. Оразаева
The digitalization of secondary education in Kazakhstan increases the need for specialized Kazakhlanguage resources that support intelligent question-and-answer systems for school subjects. However, existing QA datasets are mainly focused on high-resource languages and do not cover the content of academic disciplines, particularly the history of Kazakhstan. This paper presents and analyzes in detail the Kazakh HistoryQA corpus, the first specialized question-and-answer resource in the Kazakh language, which is based on six official textbooks on the history of Kazakhstan for grades 5-10. The corpus includes 208 thematic sections, about 180 thousand tokens, and 661 QA-pairs with exact coordinates of the response span, which ensures compatibility with standard machine reading model training pipelines, including the HuggingFace library. A multi-level analysis of the corpus has been conducted: statistics on the length of contexts, questions, and answers, distribution of materials by classes and textbooks, and typology.

30 June 2026 in Scientific Journal of Astana IT University
Verified
Journal Article
Open access
PDF file
MYManas Yergesh
Manas Yergesh
KMKundyz Maxutova
Kundyz Maxutova
ABAlibek Barlybayev
Alibek Barlybayev
Arailym TleubayevaArailym Tleubayeva
Arailym Tleubayeva
AOAinur Orazayeva
Ainur Orazayeva
AAAigul Abildina
Aigul Abildina
Reproducibility and comparability remain important methodological concerns in domain-specific question answering, particularly in low-resource educational settings. This study examines the impact of ontology-guided context filtering on extractive question answering in the Kazakh language under controlled and reproducible conditions. A benchmark corpus on the History of Kazakhstan was constructed from 11 school textbooks for grades 5–10 and canonically indexed using deterministic section identifiers. Fixed train–test splits, standardized chunking, and unified preprocessing and evaluation scripts ensured consistency across experiments. Three question answering systems were evaluated under identical constraints: a neural extractive baseline operating on unfiltered context, an ontology-only system relying on structured knowledge representations, and a hybrid system applying ontology-guided context filtering prior to neural answer extraction. Filtering was conducted under an inference setting that excludes access to gold document or section identifiers, preventing the use of privileged metadata. The hybrid system demonstrates modest improvements over the neural-only baseline. Exact Match accuracy increases from 68.87% to 70.45%, while the token-level F1 score improves from 80.02% to 81.68%. Ranking-based retrieval metrics also show small gains, with Mean Reciprocal Rank increasing from 0.870 to 0.892 and Recall@10 from 95.1% to 96.9%. Inference latency is reduced from 20.01 ms to 6.83 ms per question. Paired statistical testing confirms that the improvement in F1 is statistically significant, whereas improvements in Exact Match are less conclusive. Ablation experiments suggest that these differences are not attributable to context length reduction alone, but are associated with the interaction between ontology-guided context selection and neural reader training. Overall, ontology-guided filtering can provide incremental benefits for extractive question answering in a domain-specific, low-resource educational setting under transparent and reproducible experimental conditions.

29 July 2026 in Bulletin of Shakarim University. Technical Sciences
Verified
Journal Article
Open access
PDF file
AOAinur Orazayeva
Ainur Orazayeva
NSNurgul S. Smakova
Nurgul S. Smakova
KMK. Maksutova
K. Maksutova
AAA. Abildina
A. Abildina
ATA. Turebayeva
A. Turebayeva
This study aims to explore and develop advanced methods for the effective detection of breast pathologies using state-of-the-art machine learning techniques, specifically YOLOv8 and Faster R-CNN. Traditional approaches to breast disease diagnosis are critically reviewed, and their effectiveness is evaluated in comparison to modern automated methods. The proposed models are applied to mammographic images to identify and categorize pathological patterns into six distinct levels, considering variations in severity and disease characteristics. This multi-level classification allows for a more precise assessment of disease progression and provides critical information for personalized treatment planning. Experimental results demonstrate that the proposed approach achieves high accuracy and fast image processing, enabling reliable and rapid detection of potential breast abnormalities. These findings suggest that machine learning algorithms can significantly enhance the diagnostic process, providing clinicians with more accurate and timely information. Furthermore, the study highlights the potential of automated detection systems to improve early diagnosis, optimize treatment strategies, and ultimately enhance patient outcomes. The results emphasize the growing role of artificial intelligence in medical imaging and its transformative impact on the future of breast disease management.