Alibek Bissembayev

Dr. Alibek Bissembayev

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
25 August 2025 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
DKDina Koishiyeva
Dina Koishiyeva
JKJeong-won Kang
Jeong-won Kang
Teodor IlievTeodor Iliev
Teodor Iliev
ABAlibek Bissembayev
Alibek Bissembayev
Assel MukashevaAssel Mukasheva
Assel Mukasheva
Class imbalance is a persistent limitation in polyp segmentation, commonly resulting in biased predictions and reduced accuracy in identifying clinically relevant structures. This study systematically evaluated 12 loss functions, including standard, weighted, and compound formulas, applied to colon polyp segmentation using the UNet-VGG16 fixed architecture on the Kvasir-SEG dataset. The encoder was frozen to isolate the effect of loss functions under the same training conditions. A fixed random seed was used in all experiments to ensure reproducibility and control variance during training. The results reveal that the combined loss functions, namely WBCE combined with Dice and Tversky combined with Focal, achieved the top Dice scores of 0.8916 and 0.8917, respectively. Tversky plus Focal also provided the highest sensitivity of 0.8885, and WBCE obtained the best average IoU of 0.8120. Tversky loss showed the lowest error rate of 4.99, indicating stable optimization. These results clarify the influence of loss function selection on segmentation performance in scenarios characterized by considerable class imbalance.

30 June 2024 in Herald of the Kazakh-British technical university
Verified
Journal Article
Open access
PDF file
ИАИ. С. Амангельды
И. С. Амангельды
ABAlibek Bissembayev
Alibek Bissembayev
Advancements of Industry 4.0 has revolutionized manufacturing operations, among them predictive maintenance (PdM) acts as one of the most demanding approaches. It effectively optimizes maintenance schedules and ensures efficient and uninterrupted work. Article provides a comprehensive literature review, offering insights into theoretical foundations, historical developments, and practical applications of predictive maintenance. The methodology section explains the research approach in detail, focusing on the development of a MATLAB-based code to generate the predictive model in accordance with the remaining useful life of the machine. Exploration into the application of PdM is made through the establishment of Bayesian Inference model informed by Pearson correlation analysis. This study underscores the possibilities of predictive analytics in enhancing operational accuracy and effectivity across various industries. As the demand for reliable manufacturing processes continues to grow, the findings of this research offer insights into the development of advanced PdM strategies and achievement of operational excellence in terms of smart manufacturing.

22 January 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
RZRuslan Zhulduzbayev
Ruslan Zhulduzbayev
AAArian Ashourvan
Arian Ashourvan
DADiana Arman
Diana Arman
ABAlibek Bissembayev
Alibek Bissembayev
AKAlmira M Kustubayeva
Almira M Kustubayeva
The determination of brain age based on electroencephalography (EEG) data has become widely developed with the spread of machine learning in recent years. In this research paper, we analyzed 21 articles published no earlier than 2015, focusing particularly on features, machine learning and deep learning models, and the validation process. The studies reviewed presented model performance on EEG data using machine learning or deep learning techniques. Deep convolutional and transformer-based models trained on well-curated features forecasted chronological age most precisely. In newborns, time–frequency and entropy-based characteristics showed good predictive power for the brain age index (BAI) and functional brain age (FBA). Consistently, spectral and nonlinear descriptors ranked among the most informative characteristics. Methodological rigor, meanwhile, differed: only a small number of studies used bias correction techniques, addressed statistical assumptions, or reported external validation. Preprocessing techniques also showed significant variation. Although EEG-based models have good accuracy, problems of interpretability and generalizability restrict their clinical and developmental use. Advancing this discipline will call for biologically based outcome definitions, uniform evaluation systems, and open source processing pipelines.

9 February 2026 in IEEE Access
Verified
Journal Article
Open access
ANAlfiya Nurpeissova
Alfiya Nurpeissova
JKJeong Won Kang
Jeong Won Kang
AMAssel Mukasheva
Assel Mukasheva
ABAlibek Bissembayev
Alibek Bissembayev
Teodor IlievTeodor Iliev
Teodor Iliev
Energy-constrained Internet of Things (IoT) networks require adaptive modulation schemes that simultaneously optimize multiple conflicting objectives, such as energy efficiency, throughput, latency, and reliability, under severe hardware limitations. Traditional approaches either optimize single objectives or fail to effectively explore multi-dimensional solution spaces, thereby limiting their performance in resource-constrained environments. This study introduces a quantum-inspired Multi-Dimensional Adaptive Modulation (QI-MDAM) algorithm that leverages quantum superposition principles to represent modulation selection as probabilistic amplitude states, enabling the simultaneous probability-weighted evaluation of multiple modulation candidates through quantum amplitude representation and maintaining computational efficiency for IoT devices. QI-MDAM demonstrated exceptional performance through a comprehensive evaluation of 11 state-of-the-art approaches across four representative IoT deployment scenarios: a 12.4% improvement in energy efficiency (0.2119 vs. 0.2418 mJ/bit baseline) and a 78.8% throughput enhancement (0.685 vs. 0.383 Mbps baseline). Statistical validation using Monte Carlo simulation with 100 independent instances confirmed highly significant performance differences (Analysis of Variance (ANOVA): $F_{(11,1188)}=47.23$ , $p=2.47 \times 10^{-7}$ ) with large effect sizes (Cohen’s $d=2.47$ ). A real-time feasibility analysis using STM32L4 microcontroller constraints validated the sub-10 ms processing requirement across all scenarios. The quantum-inspired approach achieves superior Pareto frontier positioning while optimizing conflicting objectives that classical methods cannot reconcile. These results establish quantum-inspired optimization as a paradigm-shifting approach for resource-constrained wireless communications, enabling previously unattainable performance combinations that are critical for scaling sustainable IoT ecosystems.

25 August 2025 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
DSDanial Serekov
Danial Serekov
ABAlibek Bissembayev
Alibek Bissembayev
Teodor IlievTeodor Iliev
Teodor Iliev
Assel MukashevaAssel Mukasheva
Assel Mukasheva
JKJeong-won Kang
Jeong-won Kang
Swiftly advancing low-code development platforms (LCDPs) have created a new branch in software development, allowing for the rapid creation of applications with minimal knowledge of coding. However, in spite of the great opportunities gained, problems related to choosing the most appropriate platform from a wide range of alternatives that differ in features, usage scenarios, and performance metrics make it difficult to determine the most suitable solution. The use of the MULTIMOORA method can greatly facilitate the selection process, along with a strong evaluation and weighting system, which has a positive impact on the results. The evaluation system provides ten global criteria with internal sub-criteria of different factors. The list of tested platforms includes the seven most popular ones: Kissflow, Salesforce App Cloud, Zoho Creator, OutSystems, MS Power App, Mendix, and Appian. The results show the genuine value of this method, by accentuating the strengths of the proven platforms and the method itself. This study offers a multifaceted and sustainable approach to platform validation that allows the use of LCDPs for various applications and helps to make rational decisions.

16 September 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
YRYasfirbek Rozmetov
Yasfirbek Rozmetov
AAAnel Aidos
Anel Aidos
Murat OzerMurat Ozer
Murat Ozer
ABAlibek Bissembayev
Alibek Bissembayev
ABAigul Bissarinova
Aigul Bissarinova
Assel MukashevaAssel Mukasheva
Assel Mukasheva
SQL and NoSQL databases are at risk from injection attacks, which is one of the most serious threats to the security of today’s data-centric systems. To address this issue, this research proposes an architecture for evaluating a new hybrid technique for detecting vulnerabilities by using a mixture of lightweight statistical machine learning techniques and a semantically verified locally installed large language model (LLM). Specifically, the proposed detection architecture consists of three major parts: (1) an initial filtering phase that uses rapid filtering through TF-IDF vectorization and logistic regression; (2) a second phase that implements a confidence-based hybrid decision logic model; and (3) a third phase using a deterministic LLM to process semantically ambiguous queries. In our experimental evaluation of a balanced benchmark of 1000 queries (500 SQL and 500 NoSQL), our proposed hybrid method achieved the highest overall performance, yielding a precision of 0.998, recall of 0.986, and F1-score of 0.992. The individual ML model obtained a lower recall of 0.964 than the standalone LLM but had F1-scores (0.981) much higher than that of standalone LLM (0.667). The hybrid architecture reduced the number of false negatives (generated by the standalone ML models) from 18 to 7 and the number of false negatives generated by the standalone LLMs from 228 to 7. The hybrid architecture achieved very few false positives. Therefore, the use of hybrid ML-LLM detection pipelines will provide both greater robustness and practical effectiveness when doing database security monitoring.