Symbat Nurgaliyeva
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Symbat Nurgaliyeva has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Abylay Yerniyazov
Astana IT University, Astana, Kazakhstan
1 shared publication - Aivar Sakhipov
Astana IT University
1 shared publication - Aizhan Tlebaldinova
D. Serikbayev East Kazakhstan Technical University
1 shared publication - Assiya Karatay
School of AI and Data Science, Astana IT University,Astana,Kazakhstan
1 shared publication Azamat Nagumanov
School of Software Engineering, Astana IT University,Astana,Kazakhstan
1 shared publication- Bakyt Bakayeva
Astana IT University, Astana, Kazakhstan
1 shared publication
Latest Publications
- 1 December 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (6) , 5606-5616
Accurate burn severity classification via texture analysis and supervised learning
This paper presents a methodology for adapting machine learning (ML) algorithms to determine an optimal approach to burn severity classification and improving classification accuracy. The dataset for multiclass classification includes 1,500 images evenly distributed into three burn severity classes, and the dataset for binary classification includes 1,000 images evenly distributed into two classes. All images were processed with the MaZda 4.6 software package, which computed 297 texture features for each region of interest (ROI) based on different statistical descriptors. In a preprocessing step, the images were converted to 8-bit grayscale format and normalized for luminance. ROIs were manually selected with expert consultation to capture representative texture regions of burn tissue. Six feature selection methods were applied to identify the most informative descriptors. Subsequently, more than ten ML models were trained based on these features. The combination of a multilayer perceptron (MLP) classifier and recursive feature elimination (RFE) yielded the highest multiclass classification accuracy of 79% with 11 selected features. For binary classification, the MLP classifier combined with RELIEF achieved an accuracy of 96% with eight selected features. These results demonstrate the potential of feature selection combined with MLP for burn severity classification.
- 1 December 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (6) , 5606-5616
Accurate burn severity classification via texture analysis and supervised learning
This paper presents a methodology for adapting machine learning (ML) algorithms to determine an optimal approach to burn severity classification and improving classification accuracy. The dataset for multiclass classification includes 1,500 images evenly distributed into three burn severity classes, and the dataset for binary classification includes 1,000 images evenly distributed into two classes. All images were processed with the MaZda 4.6 software package, which computed 297 texture features for each region of interest (ROI) based on different statistical descriptors. In a preprocessing step, the images were converted to 8-bit grayscale format and normalized for luminance. ROIs were manually selected with expert consultation to capture representative texture regions of burn tissue. Six feature selection methods were applied to identify the most informative descriptors. Subsequently, more than ten ML models were trained based on these features. The combination of a multilayer perceptron (MLP) classifier and recursive feature elimination (RFE) yielded the highest multiclass classification accuracy of 79% with 11 selected features. For binary classification, the MLP classifier combined with RELIEF achieved an accuracy of 96% with eight selected features. These results demonstrate the potential of feature selection combined with MLP for burn severity classification.
- Open Access
- 6 August 2026
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 20 (15) , 37–50
A Mobile System for Formative Assessment and Teacher-Reviewed Feedback
Open-ended short responses can reveal more about student understanding than selectedresponse items yet scoring them during live instruction is rarely feasible. This paper presents a bring-your-own-device (BYOD) mobile classroom system that combines rubric-guided large language model (LLM) scoring of short open-ended answers, real-time teacher analytics through a classroom dashboard, and evidence-based post-quiz feedback generation. The system includes a teacher-reviewed workflow in which instructors can inspect model outputs and, when needed, adjust scores or feedback during formative classroom use. In the reported evaluation, however, teacher override was not applied or analyzed; the agreement metrics compare the system’s initial rubric-guided outputs with expert reference scores. The system was evaluated in three classroom groups (N = 60 students; 480 question-level scoring cases). Three expert raters participated, each assigned to one classroom group, so each response received one expert reference score. In this test, system scores showed strong but not complete agreement with expert reference scores (QWK = 0.887; MAE = 0.089; RMSE = 0.121). Mastery-label accuracy reached 78.3%. Expert raters gave positive scores to the generated feedback reports for groundedness (M = 4.78), specificity (M = 4.37), and actionability (M = 4.57) on a 1–5 scale. Within the limits of this small-scale classroom evaluation, the findings suggest that rubric-guided LLM scoring may support formative assessment in mobile classrooms, provided teacher oversight is maintained for borderline cases.
- 6 August 2026
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 20 (15) , 37–50
Open AccessA Mobile System for Formative Assessment and Teacher-Reviewed Feedback
Open-ended short responses can reveal more about student understanding than selectedresponse items yet scoring them during live instruction is rarely feasible. This paper presents a bring-your-own-device (BYOD) mobile classroom system that combines rubric-guided large language model (LLM) scoring of short open-ended answers, real-time teacher analytics through a classroom dashboard, and evidence-based post-quiz feedback generation. The system includes a teacher-reviewed workflow in which instructors can inspect model outputs and, when needed, adjust scores or feedback during formative classroom use. In the reported evaluation, however, teacher override was not applied or analyzed; the agreement metrics compare the system’s initial rubric-guided outputs with expert reference scores. The system was evaluated in three classroom groups (N = 60 students; 480 question-level scoring cases). Three expert raters participated, each assigned to one classroom group, so each response received one expert reference score. In this test, system scores showed strong but not complete agreement with expert reference scores (QWK = 0.887; MAE = 0.089; RMSE = 0.121). Mastery-label accuracy reached 78.3%. Expert raters gave positive scores to the generated feedback reports for groundedness (M = 4.78), specificity (M = 4.37), and actionability (M = 4.57) on a 1–5 scale. Within the limits of this small-scale classroom evaluation, the findings suggest that rubric-guided LLM scoring may support formative assessment in mobile classrooms, provided teacher oversight is maintained for borderline cases.
- Open Access
- 29 August 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 4 (9 (136)) , 70-78
Design and evaluation of an intelligent waste monitoring system based on RGIS integration for smart cities
The object of this study is the municipal solid waste management system within a modern urban environment, where rapid urbanization and population growth pose significant challenges to ecological sustainability. The key problem addressed is the inefficiency of waste collection due to overflowing containers, poor route planning, and suboptimal resource allocation. To tackle these issues, an intelligent waste monitoring system has been developed that integrates Internet of Things (IoT) technologies, computer vision, data analytics, and a Regional Geographic Information System (RGIS). The system includes a computer vision model that analyzes images of waste containers to determine their fill level. Fine-tuning the model on locally collected image data, reflecting regional characteristics such as lighting, container types, and weather conditions, significantly improved detection accuracy and adaptability. Route optimization for waste collection is implemented using a mathematical formulation of the Traveling Salesman Problem (TSP), solved via Mixed Integer Linear Programming (MILP), which helped reduce fuel consumption, travel time, and staff workload. Integration with RGIS and GPS enables dynamic routing and real-time geospatial visualization of operational data. The proposed system forms a closed-loop control cycle that links automated detection, spatial analysis, and decision-making. Experimental results demonstrate high efficiency, adaptability to regional conditions, and scalability, confirming the system’s practical applicability to other urban areas. In the future, the system may be expanded to include environmental monitoring modules such as air quality, noise, and soil conditions and predictive modeling of waste generation, thereby supporting the sustainable development of smart city infrastructure
- 29 August 2025
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 4 (9 (136)) , 70-78
Open AccessDesign and evaluation of an intelligent waste monitoring system based on RGIS integration for smart cities
The object of this study is the municipal solid waste management system within a modern urban environment, where rapid urbanization and population growth pose significant challenges to ecological sustainability. The key problem addressed is the inefficiency of waste collection due to overflowing containers, poor route planning, and suboptimal resource allocation. To tackle these issues, an intelligent waste monitoring system has been developed that integrates Internet of Things (IoT) technologies, computer vision, data analytics, and a Regional Geographic Information System (RGIS). The system includes a computer vision model that analyzes images of waste containers to determine their fill level. Fine-tuning the model on locally collected image data, reflecting regional characteristics such as lighting, container types, and weather conditions, significantly improved detection accuracy and adaptability. Route optimization for waste collection is implemented using a mathematical formulation of the Traveling Salesman Problem (TSP), solved via Mixed Integer Linear Programming (MILP), which helped reduce fuel consumption, travel time, and staff workload. Integration with RGIS and GPS enables dynamic routing and real-time geospatial visualization of operational data. The proposed system forms a closed-loop control cycle that links automated detection, spatial analysis, and decision-making. Experimental results demonstrate high efficiency, adaptability to regional conditions, and scalability, confirming the system’s practical applicability to other urban areas. In the future, the system may be expanded to include environmental monitoring modules such as air quality, noise, and soil conditions and predictive modeling of waste generation, thereby supporting the sustainable development of smart city infrastructure