Syrym Zhakypbekov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Syrym Zhakypbekov has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Artem Bykov
Международный университет информационных технологий, Алматы, Казахстан
4 shared publications С.б. Муханов
Международный университет информационных технологий, Алматы, Казахстан
3 shared publications- Daryn Amrin
International Information Technology University
2 shared publications - Samat Mukhanov
School of Cybersecurity, Astana IT University, Astana 010000, Kazakhstan
2 shared publications - Vera Yermakova
Department of Languages, International Information Technology University, 34/1 Manas Street, Almaty 050040, Kazakhstan
2 shared publications - Zhansaya Bekaulova
Международный университет информационных технологий, Алматы, Казахстан
2 shared publications
Latest Publications
- Open Access
- 27 October 2026
- Published by MDPI AG in Informatics
- Vol. 13 (11) , 179
A Criteria-Governed Human-in-the-Loop Information System Architecture for Explainable AI-Assisted Learning and Preliminary Assessment
This paper presents a criteria-governed, human-in-the-loop information system architecture integrating formative AI-assisted learning with preliminary assessment of spoken and written responses. It supports two modes: a retrieval-augmented assistant answering from course materials and an AI examiner scoring responses against a predefined rubric, criterion by criterion. The language model is confined to analysis: evidence extraction, aggregation, input-quality control, uncertainty estimation and escalation are performed by a controlled pipeline, and each result is stored as a structured decision object carrying criteria, evidence, provenance, uncertainty and teacher-verification status. Across 168 examination sessions and 1074 criterion-level decisions, every decision carried a verbatim evidence passage (100% coverage), the overall score matched the programmatic aggregation in all finalized sessions, 39.1% of responses were routed for secondary analysis and 5.4% of sessions were escalated. A survey of 52 students rated question clarity 4.81, criterion-level feedback 4.46, and allotted time 4.42, while concerns persisted about scoring reliability and recognition errors. In a preliminary blind calibration, the AI ranked 13 spoken answers like human raters (r = 0.75), but scored them 22 points lower. The contribution is the architecture and its feasibility in deployment; the study does not establish automated-scoring accuracy, and final decisions remain with the teacher.
- 27 October 2026
- Published by MDPI AG in Informatics
- Vol. 13 (11) , 179
Open AccessA Criteria-Governed Human-in-the-Loop Information System Architecture for Explainable AI-Assisted Learning and Preliminary Assessment
This paper presents a criteria-governed, human-in-the-loop information system architecture integrating formative AI-assisted learning with preliminary assessment of spoken and written responses. It supports two modes: a retrieval-augmented assistant answering from course materials and an AI examiner scoring responses against a predefined rubric, criterion by criterion. The language model is confined to analysis: evidence extraction, aggregation, input-quality control, uncertainty estimation and escalation are performed by a controlled pipeline, and each result is stored as a structured decision object carrying criteria, evidence, provenance, uncertainty and teacher-verification status. Across 168 examination sessions and 1074 criterion-level decisions, every decision carried a verbatim evidence passage (100% coverage), the overall score matched the programmatic aggregation in all finalized sessions, 39.1% of responses were routed for secondary analysis and 5.4% of sessions were escalated. A survey of 52 students rated question clarity 4.81, criterion-level feedback 4.46, and allotted time 4.42, while concerns persisted about scoring reliability and recognition errors. In a preliminary blind calibration, the AI ranked 13 spoken answers like human raters (r = 0.75), but scored them 22 points lower. The contribution is the architecture and its feasibility in deployment; the study does not establish automated-scoring accuracy, and final decisions remain with the teacher.
- 4 October 2026
- Published by Springer Nature
- p. 357-370
Video-Based Anomaly Detection in Monitoring Systems Using Deep Learning
- 4 October 2026
- Published by Springer Nature
- p. 357-370
Video-Based Anomaly Detection in Monitoring Systems Using Deep Learning
- Open Access
- 30 September 2026
- Published by Astana IT University in Scientific Journal of Astana IT University
- Vol. 27 (3) , 208-227
CRITERION-GUIDED AI ARCHITECTURE FOR LEARNING SUPPORT AND PRELIMINARY STUDENT ASSESSMENT
This paper presents a pilot evaluation of a criterion-guided human-in-the-loop architecture for an intelligent educational system that supports learning and preliminary assessment of students’ written and oral responses. Instead of assigning a final score directly, the system combines relevant context, formalized criteria, interpretable response features, supporting evidence, uncertainty estimates, and instructor verification. The architecture separates probabilistic components, including retrieval, automatic speech recognition, natural language processing, and a language model, from deterministic assessment and governance mechanisms such as rubric weights, aggregation rules, thresholds, audit logging, and referral rules. Two modes were implemented: a retrieval-augmented generation assistant for formative learning support and an AI examiner for preliminary criterion-based assessment. In the assistant pilot, 336 of 347 queries were processed without recorded technical errors, giving a completion rate of 96.8%; source citations were included in 89.0% of responses, and median response time was 980 ms. Student perceptions of the examiner were evaluated using 52 questionnaires on a five-point Likert scale. Mean ratings were highest for question clarity at 4.81, usefulness of criterion-level feedback at 4.46, and sufficiency of response time at 4.42. Students also reported notable uncertainty about the grade, with a mean rating of 3.79, and concern about speech-recognition errors, with a mean rating of 3.31. Among 45 oral responses, 12 (26.7%) lacked usable word-level timestamps and were referred for review. A worked case demonstrated traceability from response features and evidence to criterion scores, uncertainty handling, aggregation, and instructor verification. A preliminary comparison of 23 paired AI and instructor-released scores was treated as diagnostic because of a severe ceiling effect. The results support technical feasibility and procedural acceptability, but not yet the validity or reliability of automated assessment.
- 30 September 2026
- Published by Astana IT University in Scientific Journal of Astana IT University
- Vol. 27 (3) , 208-227
Open AccessCRITERION-GUIDED AI ARCHITECTURE FOR LEARNING SUPPORT AND PRELIMINARY STUDENT ASSESSMENT
This paper presents a pilot evaluation of a criterion-guided human-in-the-loop architecture for an intelligent educational system that supports learning and preliminary assessment of students’ written and oral responses. Instead of assigning a final score directly, the system combines relevant context, formalized criteria, interpretable response features, supporting evidence, uncertainty estimates, and instructor verification. The architecture separates probabilistic components, including retrieval, automatic speech recognition, natural language processing, and a language model, from deterministic assessment and governance mechanisms such as rubric weights, aggregation rules, thresholds, audit logging, and referral rules. Two modes were implemented: a retrieval-augmented generation assistant for formative learning support and an AI examiner for preliminary criterion-based assessment. In the assistant pilot, 336 of 347 queries were processed without recorded technical errors, giving a completion rate of 96.8%; source citations were included in 89.0% of responses, and median response time was 980 ms. Student perceptions of the examiner were evaluated using 52 questionnaires on a five-point Likert scale. Mean ratings were highest for question clarity at 4.81, usefulness of criterion-level feedback at 4.46, and sufficiency of response time at 4.42. Students also reported notable uncertainty about the grade, with a mean rating of 3.79, and concern about speech-recognition errors, with a mean rating of 3.31. Among 45 oral responses, 12 (26.7%) lacked usable word-level timestamps and were referred for review. A worked case demonstrated traceability from response features and evidence to criterion scores, uncertainty handling, aggregation, and instructor verification. A preliminary comparison of 23 paired AI and instructor-released scores was treated as diagnostic because of a severe ceiling effect. The results support technical feasibility and procedural acceptability, but not yet the validity or reliability of automated assessment.
- Open Access
Quantum-Assisted Deep Learning for Fault Detection and Diagnosis in Distributed Sensor Networks
Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks.
Open AccessQuantum-Assisted Deep Learning for Fault Detection and Diagnosis in Distributed Sensor Networks
Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks.
- Open Access
- 25 May 2026
- Published by Shakarim University in Bulletin of Shakarim University. Technical Sciences
- Vol. 1 (1(21)) , 214-225
ALGORITHMS FOR SOFTWARE COMPENSATION OF TORSIONAL VIBRATIONS IN H-BOT 3D PRINTERS BASED ON FILTERED B-SPLINES
The rapid development of additive manufacturing technologies imposes increasingly stringent requirements on the positioning accuracy and dynamic stability of motion systems, particularly in printers employing H-bot kinematic architectures, which are prone to torsional vibrations. Such vibrations significantly degrade print quality by inducing trajectory deviations of the print head and cannot be effectively mitigated solely through mechanical reinforcement or conventional control strategies. This study proposes a software-based torsional vibration compensation method founded on the use of filtered B-splines for motion trajectory correction at the planning stage. Unlike existing approaches that rely on rigid digital filtering or realtime adaptive control, the proposed method combines the high approximation capability of B-splines with selective attenuation of spectral components responsible for resonant torsional oscillations. A mathematical model of torsional vibrations in H-bot frame structures is developed, followed by a spectral analysis of their dynamic characteristics to justify the applicability of B-spline-based filtering for identifying and compensating critical frequency components. Numerical simulation results demonstrate a substantial reduction in vibration amplitude and a corresponding decrease in trajectory tracking error of the print head. The practical relevance of the proposed approach lies in its ability to be integrated into standard trajectory planning algorithms without hardware modification, making it applicable to a wide class of H-botbased additive manufacturing systems.
- 25 May 2026
- Published by Shakarim University in Bulletin of Shakarim University. Technical Sciences
- Vol. 1 (1(21)) , 214-225
Open AccessALGORITHMS FOR SOFTWARE COMPENSATION OF TORSIONAL VIBRATIONS IN H-BOT 3D PRINTERS BASED ON FILTERED B-SPLINES
The rapid development of additive manufacturing technologies imposes increasingly stringent requirements on the positioning accuracy and dynamic stability of motion systems, particularly in printers employing H-bot kinematic architectures, which are prone to torsional vibrations. Such vibrations significantly degrade print quality by inducing trajectory deviations of the print head and cannot be effectively mitigated solely through mechanical reinforcement or conventional control strategies. This study proposes a software-based torsional vibration compensation method founded on the use of filtered B-splines for motion trajectory correction at the planning stage. Unlike existing approaches that rely on rigid digital filtering or realtime adaptive control, the proposed method combines the high approximation capability of B-splines with selective attenuation of spectral components responsible for resonant torsional oscillations. A mathematical model of torsional vibrations in H-bot frame structures is developed, followed by a spectral analysis of their dynamic characteristics to justify the applicability of B-spline-based filtering for identifying and compensating critical frequency components. Numerical simulation results demonstrate a substantial reduction in vibration amplitude and a corresponding decrease in trajectory tracking error of the print head. The practical relevance of the proposed approach lies in its ability to be integrated into standard trajectory planning algorithms without hardware modification, making it applicable to a wide class of H-botbased additive manufacturing systems.
- 16 June 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 6 (2(22)) , 130-141
СРАВНЕНИЕ МОДЕЛЕЙ НЕЙРОННЫХ СЕТЕЙ ДЛЯ ПРОГНОЗИРОВАНИЯ ВОЛАТИЛЬНОСТИ ЦЕН КРИПТОВАЛЮТ В ТОРГОВЫХ ПАРАХ
Увеличение цифровизации финансовых рынков и рост торговых пар We b3 существенно повлияли на торговлю активами, создавая но-вые вызовы в прогнозировании волатильности цен. Традиционные стратегии управления рисками зачастую не справляются с непредсказуемой природой криптовалютных рынков. В данном исследовании рассматривается примене-ние передовых моделей машинного обучения для прогнозирования волатиль-ности цен в криптовалютных торговых парах. Мысравниваемэффективностьмоделей Temporal Fusion Transformer (TFT), Temporal Convolutional Network (TCN), XGBoost, Random Forest игибридноймодели CNN-LSTM. Наши результаты показывают, что модели TFT и гибридная CNN-LSTM превосходят традиционные рекуррентные нейронные сети в улавливании сложных рыночных динамик, способствуя улучшению стратегий управления рисками в высокочастотной торговле криптовалютами.
- 16 June 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 6 (2(22)) , 130-141
СРАВНЕНИЕ МОДЕЛЕЙ НЕЙРОННЫХ СЕТЕЙ ДЛЯ ПРОГНОЗИРОВАНИЯ ВОЛАТИЛЬНОСТИ ЦЕН КРИПТОВАЛЮТ В ТОРГОВЫХ ПАРАХ
Увеличение цифровизации финансовых рынков и рост торговых пар We b3 существенно повлияли на торговлю активами, создавая но-вые вызовы в прогнозировании волатильности цен. Традиционные стратегии управления рисками зачастую не справляются с непредсказуемой природой криптовалютных рынков. В данном исследовании рассматривается примене-ние передовых моделей машинного обучения для прогнозирования волатиль-ности цен в криптовалютных торговых парах. Мысравниваемэффективностьмоделей Temporal Fusion Transformer (TFT), Temporal Convolutional Network (TCN), XGBoost, Random Forest игибридноймодели CNN-LSTM. Наши результаты показывают, что модели TFT и гибридная CNN-LSTM превосходят традиционные рекуррентные нейронные сети в улавливании сложных рыночных динамик, способствуя улучшению стратегий управления рисками в высокочастотной торговле криптовалютами.
- Open Access
- 22 March 2025
- Published by Kazakh-British Technical University in Herald of the Kazakh-British technical university
- Vol. 22 (1) , 25-35
METHODS OF PROCESSING AND ANALYZING BIG DATA IN MACHINE LEARNING TASKS: APPROACHES AND PROSPECTS
This article explores the methods of processing and analyzing big data in order to improve the accuracy and efficiency of machine learning (MO) models. The main focus is on classification problems, the effectiveness of algorithms such as XGBoost, the support vector machine (SVM), ensemble methods, as well as systems for working with big data, including Hadoop and Apache Spark. The key stages of working with data are described: cleaning, normalization, selection of features, which is critically important for building stable models on large amounts of data. Accuracy, completeness, F-measure, and AUC-ROC metrics were used to evaluate the effectiveness of the algorithms, which made it possible to conduct a comparative analysis and identify the most productive approaches. Special attention is paid to the application of MO in the context of organizational innovations, including the tasks of classification, forecasting the success of innovations and innovation portfolio management. Recommendations on the choice of technologies and algorithms for various data types and scales are presented, and prospects for integrating distributed computing platforms with MO algorithms to achieve scalable and efficient solutions are discussed.
- 22 March 2025
- Published by Kazakh-British Technical University in Herald of the Kazakh-British technical university
- Vol. 22 (1) , 25-35
Open AccessMETHODS OF PROCESSING AND ANALYZING BIG DATA IN MACHINE LEARNING TASKS: APPROACHES AND PROSPECTS
This article explores the methods of processing and analyzing big data in order to improve the accuracy and efficiency of machine learning (MO) models. The main focus is on classification problems, the effectiveness of algorithms such as XGBoost, the support vector machine (SVM), ensemble methods, as well as systems for working with big data, including Hadoop and Apache Spark. The key stages of working with data are described: cleaning, normalization, selection of features, which is critically important for building stable models on large amounts of data. Accuracy, completeness, F-measure, and AUC-ROC metrics were used to evaluate the effectiveness of the algorithms, which made it possible to conduct a comparative analysis and identify the most productive approaches. Special attention is paid to the application of MO in the context of organizational innovations, including the tasks of classification, forecasting the success of innovations and innovation portfolio management. Recommendations on the choice of technologies and algorithms for various data types and scales are presented, and prospects for integrating distributed computing platforms with MO algorithms to achieve scalable and efficient solutions are discussed.
- 15 March 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 6 (1(21)) , 113-126
CROSS-SYSTEM ANALYSIS OF QUEUEING SYSTEMS INTERACTIONS IN DISTRIBUTED NETWORKS
Растущая зависимость от облачных вычислений принесла как замечательные возможности, так и сложные проблемы. Распределенные сети, такие как среды облачных вычислений, по своей сути динамичны и требуют надежных систем для эффективной обработки изменяющихся рабочих нагрузок. В данномисследовании изучаются сложные взаимодействия между несколькими моделями массового обслуживания в изучаемыхсистемах, что дает свежий взгляд на их влияние на производительность. Используя теорию массового обслуживания, авторыуглубляются в ключевые показатели, такие как время отклика и стратегии распределения ресурсов. Проведенный анализ подчеркивает преимущества горизонтального масштабирования, вертикального масштабирования и критическую роль пропускной способности сети в оптимизации производительности облачной инфраструктуры. Результаты не только демонстрируют практическое применение теории массового обслуживания, но и под-черкивают ее ценность в решении реальных проблем в распределенных сетях. Это ис-следование закладывает основу для будущих исследований в области прогностических моделей и гибридных подходов, прокладывая путь для более умных, более масштаби-руемых облачных решений.
- 15 March 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 6 (1(21)) , 113-126
CROSS-SYSTEM ANALYSIS OF QUEUEING SYSTEMS INTERACTIONS IN DISTRIBUTED NETWORKS
Растущая зависимость от облачных вычислений принесла как замечательные возможности, так и сложные проблемы. Распределенные сети, такие как среды облачных вычислений, по своей сути динамичны и требуют надежных систем для эффективной обработки изменяющихся рабочих нагрузок. В данномисследовании изучаются сложные взаимодействия между несколькими моделями массового обслуживания в изучаемыхсистемах, что дает свежий взгляд на их влияние на производительность. Используя теорию массового обслуживания, авторыуглубляются в ключевые показатели, такие как время отклика и стратегии распределения ресурсов. Проведенный анализ подчеркивает преимущества горизонтального масштабирования, вертикального масштабирования и критическую роль пропускной способности сети в оптимизации производительности облачной инфраструктуры. Результаты не только демонстрируют практическое применение теории массового обслуживания, но и под-черкивают ее ценность в решении реальных проблем в распределенных сетях. Это ис-следование закладывает основу для будущих исследований в области прогностических моделей и гибридных подходов, прокладывая путь для более умных, более масштаби-руемых облачных решений.
- Open Access
- 18 February 2025
- Published by JSC Academy of Logistics and Transport in Вестник КазАТК
- Vol. 136 (1) , 402-418
COMPARISON OF SINGLE AND HYBRID NEURAL NETWORK MODELS FOR STOCK PRICE FORECASTING
Forecasting stock prices has always been a complex and challenging task due to its high volatility, noise in data, and abrupt price fluctuations caused by different factors. Traditional approaches, such as quantitative, fundamental, and technical analysis, often struggle to accurately predict stock price movements due to their difficulty in processing non-linear data. The evolution of machine learning, particularly neural network models, opened new opportunities for improving prediction accuracy by handling non-linear and multidimensional data with high effectiveness. This study focuses on evaluating and comparing three neural network architectures, in which the last is a combination of the first two - Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model, for forecasting stock prices. Using ten years of historical stock data, taken for Apple Inc. (AAPL) stocks as an example, ranging from 2015 to 2025, the models were trained and tested on key performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R². Results show that while both CNN and LSTM models show good performance individually, the hybrid CNN-LSTM model can significantly outperform them, achieving the highest accuracy with the lowest error rates. By combining the strengths of CNN for feature extraction and LSTM for temporal sequence processing, the hybrid model effectively captures complex patterns in stock price movements. By iterating over the types of layers to use, we came to the conclusion, that by combining both models into one hybrid model, some layers, like one CNN layer, and one LSTM layer should be removed. This research demonstrates the potential of hybrid neural network models in financial time-series forecasting and comprehensively analyzes their advantages over non-hybrid models.
- 18 February 2025
- Published by JSC Academy of Logistics and Transport in Вестник КазАТК
- Vol. 136 (1) , 402-418
Open AccessCOMPARISON OF SINGLE AND HYBRID NEURAL NETWORK MODELS FOR STOCK PRICE FORECASTING
Forecasting stock prices has always been a complex and challenging task due to its high volatility, noise in data, and abrupt price fluctuations caused by different factors. Traditional approaches, such as quantitative, fundamental, and technical analysis, often struggle to accurately predict stock price movements due to their difficulty in processing non-linear data. The evolution of machine learning, particularly neural network models, opened new opportunities for improving prediction accuracy by handling non-linear and multidimensional data with high effectiveness. This study focuses on evaluating and comparing three neural network architectures, in which the last is a combination of the first two - Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model, for forecasting stock prices. Using ten years of historical stock data, taken for Apple Inc. (AAPL) stocks as an example, ranging from 2015 to 2025, the models were trained and tested on key performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R². Results show that while both CNN and LSTM models show good performance individually, the hybrid CNN-LSTM model can significantly outperform them, achieving the highest accuracy with the lowest error rates. By combining the strengths of CNN for feature extraction and LSTM for temporal sequence processing, the hybrid model effectively captures complex patterns in stock price movements. By iterating over the types of layers to use, we came to the conclusion, that by combining both models into one hybrid model, some layers, like one CNN layer, and one LSTM layer should be removed. This research demonstrates the potential of hybrid neural network models in financial time-series forecasting and comprehensively analyzes their advantages over non-hybrid models.
- 10 January 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 5 (4(20)) , 68-82
СБОР ДАННЫХ И ПРИМЕНЕНИЕ МОДЕЛЕЙ НЕЙРОННЫХ СЕТЕЙ ДЛЯ КЛАССИФИКАЦИИ ЯЗЫКА ЖЕСТОВ В ЗАДАЧАХ РАСПОЗНАВАНИЯ ОБРАЗОВ
В данной работе рассматривается сбор данных и применение моделей нейронных сетей для классификации языка жестов в задачах распознавания образов. Язык жестов, как важный способ коммуникации для людей с нарушениями слуха, требует эффективных технологий для его автоматического распознавания. В ходе исследования был проведён сбор разнообразных видеоданных, охватывающих различные жесты и контексты их использования. Для анализа этих данных применялись современные архитектуры нейронных сетей, включая сверточные и рекуррентные сети, что позволило достичь высокой точности классификации. Результаты показывают перспективность использования глубокого обучения для распознавания языка жестов, что открывает новые возможности для разработки вспомогательных технологий и улучшения качества жизни людей с ограниченными возможностями. Работа подчеркивает важность интеграции методов машинного обучения и компьютерного зрения для создания более интуитивно понятных интерфейсов взаимодействия.
- 10 January 2025
- Published by International Information Technology University in INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES
- Vol. 5 (4(20)) , 68-82
СБОР ДАННЫХ И ПРИМЕНЕНИЕ МОДЕЛЕЙ НЕЙРОННЫХ СЕТЕЙ ДЛЯ КЛАССИФИКАЦИИ ЯЗЫКА ЖЕСТОВ В ЗАДАЧАХ РАСПОЗНАВАНИЯ ОБРАЗОВ
В данной работе рассматривается сбор данных и применение моделей нейронных сетей для классификации языка жестов в задачах распознавания образов. Язык жестов, как важный способ коммуникации для людей с нарушениями слуха, требует эффективных технологий для его автоматического распознавания. В ходе исследования был проведён сбор разнообразных видеоданных, охватывающих различные жесты и контексты их использования. Для анализа этих данных применялись современные архитектуры нейронных сетей, включая сверточные и рекуррентные сети, что позволило достичь высокой точности классификации. Результаты показывают перспективность использования глубокого обучения для распознавания языка жестов, что открывает новые возможности для разработки вспомогательных технологий и улучшения качества жизни людей с ограниченными возможностями. Работа подчеркивает важность интеграции методов машинного обучения и компьютерного зрения для создания более интуитивно понятных интерфейсов взаимодействия.