Khuralay Moldamurat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Khuralay Moldamurat has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Makhabbat Bakyt
L.N. Gumilyov Eurasian National University
12 shared publications - Sabyrzhan Atanov
L. N. Gumilyov Eurasian National University,Department of Computer and Software Engineering,Astana,Kazakhstan
8 shared publications - Dinara Kalmanova
L.N. Gumilyov Eurasian National University
5 shared publications - Luigi La Spada
Edinburgh Napier University
4 shared publications - Niyaz Belgibekov
JSC Center for Military-Strategic Research
4 shared publications - Kairat Akhmetov
L.N. Gumilyov Eurasian National University
3 shared publications
Latest Publications
- Open Access
- 31 March 2026
- Published by L. N. Gumilyov Eurasian National University in BULLETIN of the L.N. Gumilyov Eurasian National University. Chemistry. Geography Series
- Vol. 154 (1) , 100-117
Comparison and synthesis of image analysis algorithms: processing NDVI and RGB for UAV-based environmental monitoring
The assessment of vegetation health stands as a fundamental operation which precision agriculture and ecology and environmental risk management require. The Normalized Difference Vegetation Index (NDVI) uses red and near-infrared (NIR) reflectance data to function as the primary index which enables vegetation health assessment and stress detection. The implementation of these systems faces challenges when trying to deploy them in budget-friendly operations because they need multispectral sensors which include NIR channels. The research evaluates three algorithmic approaches through a complete analysis which includes (i) NDVI method and (ii) RGB-only channel transformation method and (iii) a synthesized hybrid algorithm that applies NDVI normalization to green-dominance for standard RGB cameras. The research includes mathematical derivations together with radiometric interpretation methods and calibration needs and error propagation calculations for all investigated approaches. The research develops a system which performs UAV image data preprocessing through geometric correction and radiometric normalization and noise filtering and illumination compensation. The system becomes more useful through discussions about UAV implementation scenarios and flight planning constraints and geospatial post-processing workflows. The text includes forest-fire-related use-cases as examples of fast assessment situations which vegetation stress maps help with post-event choices yet these examples do not represent the main focus. The research findings show that NDVI based on classical methods delivers better results for quantitative biophysical analysis but RGB-based methods work well for qualitative segmentation when using limited hardware resources. The developed algorithm delivers superior vegetation identification results than RGB transformation methods and functions as a useful solution for organizations which lack NIR-equipped systems. The document presents recommendations which help users choose methods based on their specific requirements regarding accuracy levels and budget constraints and time needs for deployment and system operational difficulties.
- 31 March 2026
- Published by L. N. Gumilyov Eurasian National University in BULLETIN of the L.N. Gumilyov Eurasian National University. Chemistry. Geography Series
- Vol. 154 (1) , 100-117
Open AccessComparison and synthesis of image analysis algorithms: processing NDVI and RGB for UAV-based environmental monitoring
The assessment of vegetation health stands as a fundamental operation which precision agriculture and ecology and environmental risk management require. The Normalized Difference Vegetation Index (NDVI) uses red and near-infrared (NIR) reflectance data to function as the primary index which enables vegetation health assessment and stress detection. The implementation of these systems faces challenges when trying to deploy them in budget-friendly operations because they need multispectral sensors which include NIR channels. The research evaluates three algorithmic approaches through a complete analysis which includes (i) NDVI method and (ii) RGB-only channel transformation method and (iii) a synthesized hybrid algorithm that applies NDVI normalization to green-dominance for standard RGB cameras. The research includes mathematical derivations together with radiometric interpretation methods and calibration needs and error propagation calculations for all investigated approaches. The research develops a system which performs UAV image data preprocessing through geometric correction and radiometric normalization and noise filtering and illumination compensation. The system becomes more useful through discussions about UAV implementation scenarios and flight planning constraints and geospatial post-processing workflows. The text includes forest-fire-related use-cases as examples of fast assessment situations which vegetation stress maps help with post-event choices yet these examples do not represent the main focus. The research findings show that NDVI based on classical methods delivers better results for quantitative biophysical analysis but RGB-based methods work well for qualitative segmentation when using limited hardware resources. The developed algorithm delivers superior vegetation identification results than RGB transformation methods and functions as a useful solution for organizations which lack NIR-equipped systems. The document presents recommendations which help users choose methods based on their specific requirements regarding accuracy levels and budget constraints and time needs for deployment and system operational difficulties.
- 30 March 2026
- Published by Ministry of Defense of the Republic of Kazakhstan S. Nurmagambetov Military Institute of Land Forces in The Proceeding "Bulletin MILF"
- Vol. 65 (1)
STUDY OF THE GEOMETRIC CHARACTERISTICS OF A UAV WING WITH A PAYLOAD FROM 70 TO 150 KG
This paper presents the results of a study on the geometric parameters of a UAV wing depending on the payload weight. It has been theoretically established that the wingspan and wing area increase in direct proportion to the growth of the total load, which includes the mass of the aircraft and the payload, within the range of 70 to 150 kg. As the wing area increases from 19 to 23 m², calculated on the basis of a trapezoidal planform, the root and tip chord lengths change accordingly: their values vary within 4.9-5.4 m and 2.5-2.7 m, respectively. The wingspan, in this case, varies from 11.5 to 12.7 m. The obtained relationships made it possible to determine the range of the wing’s geometric characteristics – from minimum to maximum values—thus providing well-founded initial data for UAV design.
- 30 March 2026
- Published by Ministry of Defense of the Republic of Kazakhstan S. Nurmagambetov Military Institute of Land Forces in The Proceeding "Bulletin MILF"
- Vol. 65 (1)
STUDY OF THE GEOMETRIC CHARACTERISTICS OF A UAV WING WITH A PAYLOAD FROM 70 TO 150 KG
This paper presents the results of a study on the geometric parameters of a UAV wing depending on the payload weight. It has been theoretically established that the wingspan and wing area increase in direct proportion to the growth of the total load, which includes the mass of the aircraft and the payload, within the range of 70 to 150 kg. As the wing area increases from 19 to 23 m², calculated on the basis of a trapezoidal planform, the root and tip chord lengths change accordingly: their values vary within 4.9-5.4 m and 2.5-2.7 m, respectively. The wingspan, in this case, varies from 11.5 to 12.7 m. The obtained relationships made it possible to determine the range of the wing’s geometric characteristics – from minimum to maximum values—thus providing well-founded initial data for UAV design.
- Open Access
- 1 February 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (1) , 860-874
Optimizing the implementation of the Saber post-quantum cryptography scheme with a hybrid architecture
This paper presents a hardware–software hybrid implementation of the Saber key encapsulation mechanism (KEM) on a Terasic DE10-Nano board, which combines an ARM Cortex-A9 processor and an Intel Cyclone V field programmable gate array (FPGA). By offloading computationally intensive polynomial multiplication to a dedicated FPGA module, the hybrid design significantly reduces execution time. Experimental results show that compared to a software-only approach, the hybrid design decreases execution time by 40% for key generation, 35% for encapsulation, and 50% for decapsulation. The consistent performance gains were confirmed across the LightSaber, Saber, and FireSaber parameter sets, demonstrating that CPU-FPGA co-design offers significant efficiency improvements for post quantum cryptography (PQC), especially on platforms with limited resources.
- 1 February 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (1) , 860-874
Open AccessOptimizing the implementation of the Saber post-quantum cryptography scheme with a hybrid architecture
This paper presents a hardware–software hybrid implementation of the Saber key encapsulation mechanism (KEM) on a Terasic DE10-Nano board, which combines an ARM Cortex-A9 processor and an Intel Cyclone V field programmable gate array (FPGA). By offloading computationally intensive polynomial multiplication to a dedicated FPGA module, the hybrid design significantly reduces execution time. Experimental results show that compared to a software-only approach, the hybrid design decreases execution time by 40% for key generation, 35% for encapsulation, and 50% for decapsulation. The consistent performance gains were confirmed across the LightSaber, Saber, and FireSaber parameter sets, demonstrating that CPU-FPGA co-design offers significant efficiency improvements for post quantum cryptography (PQC), especially on platforms with limited resources.
- Open Access
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (6)
Large language models for pattern recognition in text data
Large language models (LLMs) are widely deployed in settings where both reliability and efficiency matter. We present a calibrated, seed‑robust empirical comparison of an encoder fine‑tuned model (bidirectional encoder representations from transformers (BERT)‑base) and a decoder in‑context model (generative pre-trained transformer (GPT)‑2 small) across Stanford question answering dataset v2.0 (SQuAD v2.0) and general language understanding evaluation (GLUE)-multi-genre natural language inference (MNLI), Stanford sentiment treebank 2 (SST‑2). Beyond accuracy, we assess reliability (expected calibration error with reliability diagrams and confidence–coverage analysis) and efficiency (latency, memory, throughput) under matched conditions and three fixed seeds. BERT‑base yields higher accuracy and lower calibration error, while GPT‑2 narrows gaps under few‑shot prompting but remains more sensitive to prompt design and context length. Efficiency benchmarks show that decoder‑only prompting incurs near‑linear latency/memory growth with k‑shot exemplars, whereas fine‑tuned encoders maintain stable per‑example cost. These findings offer practical guidance on when to prefer fine‑tuning versus prompting and demonstrate that reliability must be evaluated alongside accuracy for risk‑aware deployment.
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (6)
Open AccessLarge language models for pattern recognition in text data
Large language models (LLMs) are widely deployed in settings where both reliability and efficiency matter. We present a calibrated, seed‑robust empirical comparison of an encoder fine‑tuned model (bidirectional encoder representations from transformers (BERT)‑base) and a decoder in‑context model (generative pre-trained transformer (GPT)‑2 small) across Stanford question answering dataset v2.0 (SQuAD v2.0) and general language understanding evaluation (GLUE)-multi-genre natural language inference (MNLI), Stanford sentiment treebank 2 (SST‑2). Beyond accuracy, we assess reliability (expected calibration error with reliability diagrams and confidence–coverage analysis) and efficiency (latency, memory, throughput) under matched conditions and three fixed seeds. BERT‑base yields higher accuracy and lower calibration error, while GPT‑2 narrows gaps under few‑shot prompting but remains more sensitive to prompt design and context length. Efficiency benchmarks show that decoder‑only prompting incurs near‑linear latency/memory growth with k‑shot exemplars, whereas fine‑tuned encoders maintain stable per‑example cost. These findings offer practical guidance on when to prefer fine‑tuning versus prompting and demonstrate that reliability must be evaluated alongside accuracy for risk‑aware deployment.
- 8 October 2025
- Published by Springer Nature
- p. 175-193
Quantum Encryption for Low-Orbit Vehicles
- Open Access
- 30 September 2025
- Published by Shakarim University in Bulletin of Shakarim University. Technical Sciences
- No. 3(19),p. 21-31
MODIFICATION OF THE LIGHTWEIGHT STREAM CIPHER ALGORITHM CHACHA20
Providing secure and high-speed data transmission for low-orbit aircraft (LOA) is a priority in today's world. The objective of this study is to modify existing encryption methods for LOA to overcome the disadvantages in speed and vulnerability to emerging cyber-attacks, including quantum ones. The main idea is to develop a hybrid approach combining an optimized lightweight stream cipher ChaCha20 with a quantum key distribution protocol BB84. This will provide high encryption speed and information-theoretic key exchange security, which is invulnerable to quantum attacks. The research methodology includes the analysis of existing cryptographic solutions, performance modeling of the proposed hybrid algorithm, and the integration of machine learning-based anomaly detection mechanisms (LSTM) to improve the robustness of the system. The main results show that the proposed method significantly improves throughput, reduces latency and power consumption compared to traditional approaches, while providing resilience to current and future threats. The value of the work lies in contributing to the development of post-quantum cryptography for the aerospace industry and creating a basis for the development of more secure and efficient NOLA communication systems, which has direct practical implications for environmental monitoring, precision agriculture and national security.
- 30 September 2025
- Published by Shakarim University in Bulletin of Shakarim University. Technical Sciences
- No. 3(19),p. 21-31
Open AccessMODIFICATION OF THE LIGHTWEIGHT STREAM CIPHER ALGORITHM CHACHA20
Providing secure and high-speed data transmission for low-orbit aircraft (LOA) is a priority in today's world. The objective of this study is to modify existing encryption methods for LOA to overcome the disadvantages in speed and vulnerability to emerging cyber-attacks, including quantum ones. The main idea is to develop a hybrid approach combining an optimized lightweight stream cipher ChaCha20 with a quantum key distribution protocol BB84. This will provide high encryption speed and information-theoretic key exchange security, which is invulnerable to quantum attacks. The research methodology includes the analysis of existing cryptographic solutions, performance modeling of the proposed hybrid algorithm, and the integration of machine learning-based anomaly detection mechanisms (LSTM) to improve the robustness of the system. The main results show that the proposed method significantly improves throughput, reduces latency and power consumption compared to traditional approaches, while providing resilience to current and future threats. The value of the work lies in contributing to the development of post-quantum cryptography for the aerospace industry and creating a basis for the development of more secure and efficient NOLA communication systems, which has direct practical implications for environmental monitoring, precision agriculture and national security.
- Open Access
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Evaluation and Research in Education (IJERE)
- Vol. 14 (3) , 2346-2357
Active online learning with remote sensing data in higher education
The increasing popularity of online learning has created a need for effective methods to enhance educational quality. This study addresses this need by developing and evaluating an active online learning model incorporating remote sensing data (RSD). The study included a pedagogical experiment with 181 students divided into control and experimental groups. The model included an interactive database, a web portal with tools for processing and visualizing RSD, and the implementation of active learning methods. Data were collected through testing, analysis of completed projects, and questionnaires. Quantitative and qualitative analysis methods were used to process the data. The pedagogical experiment showed that the model improved students’ average scores, increased the number of students with high levels of knowledge acquisition, and enhanced motivation. Thus, the use of RSD and active learning methods in online education is a promising approach to improve the quality of the educational process and foster students’ digital competence.
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Evaluation and Research in Education (IJERE)
- Vol. 14 (3) , 2346-2357
Open AccessActive online learning with remote sensing data in higher education
The increasing popularity of online learning has created a need for effective methods to enhance educational quality. This study addresses this need by developing and evaluating an active online learning model incorporating remote sensing data (RSD). The study included a pedagogical experiment with 181 students divided into control and experimental groups. The model included an interactive database, a web portal with tools for processing and visualizing RSD, and the implementation of active learning methods. Data were collected through testing, analysis of completed projects, and questionnaires. Quantitative and qualitative analysis methods were used to process the data. The pedagogical experiment showed that the model improved students’ average scores, increased the number of students with high levels of knowledge acquisition, and enhanced motivation. Thus, the use of RSD and active learning methods in online education is a promising approach to improve the quality of the educational process and foster students’ digital competence.
- Open Access
- 1 May 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (2) , 1061-1072
Intelligent voice control system for UAV with mobile robot
The article presents a voice control system for unmanned aerial vehicles (UAVs) and an integrated mobile robot, based on artificial intelligence (AI). The system recognizes voice commands in the Kazakh language, converted into Latin transliteration, providing intuitive control of the UAV and robot. The performance of the system in various scenarios including agriculture, environmental monitoring and search and rescue operations is investigated. The system showed high accuracy of command recognition (95%) and efficient control of the UAV and robot. The proposed system opens up new possibilities for the use of UAVs and robots in various fields, increasing their autonomy, flexibility and ease of use.
- 1 May 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (2) , 1061-1072
Open AccessIntelligent voice control system for UAV with mobile robot
The article presents a voice control system for unmanned aerial vehicles (UAVs) and an integrated mobile robot, based on artificial intelligence (AI). The system recognizes voice commands in the Kazakh language, converted into Latin transliteration, providing intuitive control of the UAV and robot. The performance of the system in various scenarios including agriculture, environmental monitoring and search and rescue operations is investigated. The system showed high accuracy of command recognition (95%) and efficient control of the UAV and robot. The proposed system opens up new possibilities for the use of UAVs and robots in various fields, increasing their autonomy, flexibility and ease of use.
- Open Access
- 1 April 2025
- Published by Republican State Enterprise "National Nuclear Center of the Republic of Kazakhstan" in NNC RK Bulletin
- No. 1,p. 28-37
OPTICAL AND THERMAL MODELS AGAINST FOREST FIRES: INTEGRATION OF UAVS AND TELEMETRY
This article discusses the current problems of forest and steppe fires in the Republic of Kazakhstan, their increasing frequency, impact on ecosystems and the economy, as well as on human safety. The necessity of using modern technologies in fire control and management, including unmanned aerial vehicles (UAVs), is discussed. In computer programming, the mathematical formula of the Stefan-Boltzmann law was used to model a thermal process as a physical phenomenon. As a result of calculations in the Python program, the dependence of heat flow on distance and smoke coefficient was confirmed. In the course of the study, the results of calculating thermal radiation based on the methodology for evaluating optical and thermal indicators for early fire prevention were obtained. It has been shown that the integration of UAVs and telemetry improves control over fire conditions, increases the accuracy of fire forecasting by promptly obtaining information in real time. This approach is proposed as an important way to protect ecosystems and human life.
- 1 April 2025
- Published by Republican State Enterprise "National Nuclear Center of the Republic of Kazakhstan" in NNC RK Bulletin
- No. 1,p. 28-37
Open AccessOPTICAL AND THERMAL MODELS AGAINST FOREST FIRES: INTEGRATION OF UAVS AND TELEMETRY
This article discusses the current problems of forest and steppe fires in the Republic of Kazakhstan, their increasing frequency, impact on ecosystems and the economy, as well as on human safety. The necessity of using modern technologies in fire control and management, including unmanned aerial vehicles (UAVs), is discussed. In computer programming, the mathematical formula of the Stefan-Boltzmann law was used to model a thermal process as a physical phenomenon. As a result of calculations in the Python program, the dependence of heat flow on distance and smoke coefficient was confirmed. In the course of the study, the results of calculating thermal radiation based on the methodology for evaluating optical and thermal indicators for early fire prevention were obtained. It has been shown that the integration of UAVs and telemetry improves control over fire conditions, increases the accuracy of fire forecasting by promptly obtaining information in real time. This approach is proposed as an important way to protect ecosystems and human life.
- Open Access
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in Computer Science and Information Technologies
- Vol. 6 (1)
Geoinformation system for monitoring forest fires and data encryption for low-orbit vehicles
This article discusses two important aspects of unmanned aerial vehicles (UAVs): forest fire monitoring and data security for low-orbit vehicles. The first part of the article is devoted to the development of a geographic information system (GIS) for monitoring and forecasting the spread of forest fires. The system uses intelligent processing of aerospace data obtained from UAVs to timely detect fires, determine their characteristics and forecast the dynamics of development. The second part of the article focuses on the problem of high-speed encryption of data transmitted from low-orbit aircraft. An effective encryption algorithm is proposed that ensures high data processing speed and reliable protection of information from unauthorized access. The article presents the results of modeling and analysis of the effectiveness of the proposed solutions.
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in Computer Science and Information Technologies
- Vol. 6 (1)
Open AccessGeoinformation system for monitoring forest fires and data encryption for low-orbit vehicles
This article discusses two important aspects of unmanned aerial vehicles (UAVs): forest fire monitoring and data security for low-orbit vehicles. The first part of the article is devoted to the development of a geographic information system (GIS) for monitoring and forecasting the spread of forest fires. The system uses intelligent processing of aerospace data obtained from UAVs to timely detect fires, determine their characteristics and forecast the dynamics of development. The second part of the article focuses on the problem of high-speed encryption of data transmitted from low-orbit aircraft. An effective encryption algorithm is proposed that ensures high data processing speed and reliable protection of information from unauthorized access. The article presents the results of modeling and analysis of the effectiveness of the proposed solutions.