Saltanat Sharipova

Ms. Saltanat Sharipova

Astana IT University, Nur-Sultan, Astana, Kazakhstan
orcid

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
15 June 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SBSvitlana Biloshchytska
Svitlana Biloshchytska
Arailym TleubayevaArailym Tleubayeva
Arailym Tleubayeva
Oleksandr KuchanskyiOleksandr Kuchanskyi
Oleksandr Kuchanskyi
ABAndrii Biloshchytskyi
Andrii Biloshchytskyi
Yurii AndrashkoYurii Andrashko
Yurii Andrashko
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
This study presents an advanced hybrid approach for detecting near-duplicate texts in the Kazakh language, addressing the specific challenges posed by its agglutinative morphology. The proposed method combines statistical and semantic techniques, including N-gram analysis, TF-IDF, LSH, LSA, and LDA, and is benchmarked against the bert-base-multilingual-cased model. Experiments were conducted on the purpose-built Arailym-aitu/KazakhTextDuplicates corpus, which contains over 25,000 manually modified text fragments using typical techniques, such as paraphrasing, word order changes, synonym substitution, and morphological transformations. The results show that the hybrid model achieves a precision of 1.00, a recall of 0.73, and an F1-score of 0.84, significantly outperforming traditional N-gram and TF-IDF approaches and demonstrating comparable accuracy to the BERT model while requiring substantially lower computational resources. The hybrid model proved highly effective in detecting various types of near-duplicate texts, including paraphrased and structurally modified content, making it suitable for practical applications in academic integrity verification, plagiarism detection, and intelligent text analysis. Moreover, this study highlights the potential of lightweight hybrid architectures as a practical alternative to large transformer-based models, particularly for languages with limited annotated corpora and linguistic resources. It lays the foundation for future research in cross-lingual duplicate detection and deep model adaptation for the Kazakh language.

Verified
Journal Article
Open access
PDF file
GAGaliya Anarbekova
Galiya Anarbekova
Luis Gonzaga Baca RuizLuis Gonzaga Baca Ruiz
Luis Gonzaga Baca Ruiz
AAAkerke Akanova
Akerke Akanova
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
Nazira OspanovaNazira Ospanova
Nazira Ospanova
This study investigates the application of different ML methods for predicting pest outbreaks in Kazakhstan for grain crops. Comprehensive data spanning from 2005 to 2022, including pest population metrics, meteorological data, and geographical parameters, were employed to train the neural network for forecasting the population dynamics of Phyllotreta vittula pests in Kazakhstan. By evaluating various network configurations and hyperparameters, this research considers the application of MLP, MT-ANN, LSTM, transformer, and SVR. The transformer consistently demonstrates superior predictive accuracy in terms of MSE. Additionally, this work highlights the impact of several training hyperparameters such as epochs and batch size on predictive accuracy. Interestingly, the second season exhibits unique responses, stressing the effect of some features on model performance. By advancing our understanding of fine-tuning ANNs for accurate pest prediction in grain crops, this research contributes to the development of more precise and efficient pest control strategies. In addition, the consistent dominance of the transformer model makes it suitable for its implementation in practical applications. Finally, this work contributes to sustainable agricultural practices by promoting targeted interventions and potentially reducing reliance on chemical pesticides.

31 August 2022 in Eastern-European Journal of Enterprise Technologies
Verified
Journal Article
Open access
PDF file
AAAkerke Akanova
Akerke Akanova
Nazira OspanovaNazira Ospanova
Nazira Ospanova
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
GМGulalem Мauina
Gulalem Мauina
ZAZhanat Abdugulova
Zhanat Abdugulova
Research in the field of semantic text analysis begins with the study of the structure of natural language. The Kazakh language is unique in that it belongs to agglutinative languages and requires careful study. The object of this study is the text in the Kazakh language. Existing approaches to the study of the semantic analysis of text in the Kazakh language do not consider text analysis using the methods of thematic modeling and learning of neural networks. The purpose of this study is to determine the quality of a topic model based on the LDA (Latent Dirichlet Allocation) method with Gibbs sampling, through neural network learning. The LDA model can determine the semantic probability of the keywords of a single document and give them a rating score. To build a neural network, one of the widely used LSTM architectures was used, which has proven itself well in working with NLP (Natural Language Processing). As a result of learning, it is possible to see to what extent the text was trained and how the semantic analysis of the text in the Kazakh language went. The system, developed on the basis of the LDA model and neural network learning, combines the detected keywords into separate topics. In general, the experimental results showed that the use of deep neural networks gives the expected results of the quality of the LDA model in the processing of the Kazakh language. The developed model of the neural network contributes to the assessment of the accuracy of the semantics of the used text in the Kazakh language. The results obtained can be applied in systems for processing text data, for example, when checking the compliance of the topic and content of the proposed texts (abstracts, term papers, theses, and other works).

30 June 2024 in Scientific Journal of Astana IT University
Verified
Journal Article
Open access
PDF file
STSapar Toxanov
Sapar Toxanov
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
ABAndrii Biloshchytskyi
Andrii Biloshchytskyi
DADilara Abzhanova
Dilara Abzhanova
BBBatyrbek Bakytkereiuly
Batyrbek Bakytkereiuly
This study examines the impact of sharding on the scalability and efficiency of blockchain systems, specifically in the development of a complex of intelligent information and communication systems for environmental monitoring of emissions into the environment for decision-making in the context of carbon neutrality. Utilizing the Ikarus Network infrastructure, sharding was implemented on masternodes as a key technology to optimize transaction processing. Sharding enables the blockchain to be divided into multiple parallel chains, significantly increasing throughput and reducing the load on individual nodes. The results demonstrate a 70% increase in transaction processing speed, allowing the system to handle up to 5000 transactions per second, compared to the previous 3000 transactions per second. Network throughput increased by 50%, ensuring more efficient load distribution and stable operation even with high data volumes. Statistical analysis using ANOVA confirmed significant improvements in transaction processing speed, confirmation time, and resource usage post-sharding implementation. The F-value for transaction processing speed was 4567 with a P-value of 0.0001, indicating substantial improvements. Visual data analysis further confirmed these results, showing noticeable performance enhancements in the blockchain system. Distribution charts and histograms of transaction processing speed and confirmation time revealed an increase in the average number of transactions per second and greater system stability post-sharding. Sharding not only increased throughput but also enhanced system security by decentralizing data among shards, complicating potential cyberattacks. The study aimed to determine how sharding can improve the scalability and efficiency of blockchain systems. These improvements position the Ikarus Network as a promising solution for scalable and secure blockchain-based applications, especially for tasks related to carbon emission monitoring and management. These findings can underpin further study and the development of more efficient blockchain technologies.

30 October 2025 in Scientific Journal of Astana IT University
Verified
Journal Article
Open access
PDF file
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
DADilara Abzhanova
Dilara Abzhanova
STSapar Toxanov
Sapar Toxanov
ABAndrii Biloshchytskyi
Andrii Biloshchytskyi
The prediction of emissions to air is a crucial and complex task for environmental monitoring and air quality management. Accurate forecasting is essential for the timely adoption of mitigation measures and for ensuring regulatory compliance. However, traditional statistical methods often perform inadequately because they poorly capture non-linear dependencies, intricate interactions between variables, and long-term temporal patterns, all of which ultimately decrease forecasting accuracy. The work presents an emission prediction software module based on a neural network with LSTM architecture. The input factors used were the concentrations of the main pollutants (NO, NO2, SO2, CO, solid particles) as well as meteorological indicators including air temperature, humidity and flow rate. Data provided by the operating enterprises, including 39,803 lines with increments of 20 minutes, were pre-processed: cleared from skips, normalized parameters and forming training sequences of 72 steps, corresponding to the daily interval. Additional exploration analysis was performed, which revealed the presence of expressed daily and weekly cycles, as well as correlations between weather conditions and concentrations of pollutants. The built model showed the ability to reproduce emission dynamics with acceptable accuracy, which is confirmed by MSE 0.87 and R2 0.86 values. The developed module is integrated into the current monitoring system and provides a user-friendly interface for building real-time forecasts. The results are consistent with current research, but the work is applied as a tool used in practical activities. In the future, it is planned to expand the set of factors and explore the possibilities of using ensemble architecture to improve the accuracy and robustness of forecasts.

26 July 2025
Verified
Book Chapter
Closed access
PDF file
GAGaliya Anarbekova
Galiya Anarbekova
AAA. S. Akanova
A. S. Akanova
NON. N. Ospanova
N. N. Ospanova
Saltanat SharipovaSaltanat Sharipova
Saltanat Sharipova
ESE. T. Seksenbayev
E. T. Seksenbayev