Dinargul Mukhammejanova

Ms. Dinargul Mukhammejanova

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
16 January 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
MKMarlen Kossakov
Marlen Kossakov
Assel MukashevaAssel Mukasheva
Assel Mukasheva
Gani SergazinGani Sergazin
Gani Sergazin
SSSyrym Seidazimov
Syrym Seidazimov
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
MSMadina Sydybayeva
Madina Sydybayeva
In many fields, data-driven decision making has become essential due to machine learning (ML), which provides insights that improve productivity and quality of life. A basic machine learning approach called clustering helps find comparable data points. Clustering plays a critical role in the identification of patient subgroups and the customisation of treatment in the context of tuberculosis (TB) research. While prior studies have recognized its utility, a comprehensive comparative analysis of multiple clustering methods applied to TB data is lacking. Using TB data, this study thoroughly assesses and contrasts four well-known machine learning clustering algorithms: spectral clustering, DBSCAN, hierarchical clustering, and k-means. To evaluate the quality of a cluster, quantitative measures such as the silhouette score, Davies–Bouldin index, and Calinski–Harabasz index are utilised. The results provide quantitative insights that enhance comprehension of clustering and guide future research.

31 July 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
Assel MukashevaAssel Mukasheva
Assel Mukasheva
DKDina Koishiyeva
Dina Koishiyeva
Gani SergazinGani Sergazin
Gani Sergazin
MSMadina Sydybayeva
Madina Sydybayeva
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
SSSyrym Seidazimov
Syrym Seidazimov
Colorectal cancer is the third most prevalent type of cancer globally, and it typically progresses unnoticed, making early detection via effective screening methods crucial. This study presents the TASPP-UNet, an advanced deep learning model that integrates Atrous Spatial Pyramid Pooling (ASPP) blocks and a ResNet-50 encoder to enhance polyp boundary delineation accuracy in colonoscopy images. We utilized augmented datasets from Kvasir-SEG and CVC Clinic-DB, which included up to 2000 images, to enrich the training examples’ variability. The TASPP-UNet achieved a superior IOU of 0.9276, compared to 0.9128 by the ResNet50-UNet and 0.8607 by the standard U-Net, demonstrating its efficacy in precise segmentation tasks. Notably, this model exhibited impressive computational efficiency with a processing speed of 151.1 frames per second (FPS), underscoring its potential for real-time clinical applications aimed at early and accurate colorectal cancer detection. This performance highlights the model’s capability not only to improve diagnostic accuracy but also to enhance clinical workflows, potentially leading to better patient outcomes.

29 November 2025 in Bioengineering
Verified
Journal Article
Open access
PDF file
DKDina Koishiyeva
Dina Koishiyeva
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
JKJeong-won Kang
Jeong-won Kang
Assel MukashevaAssel Mukasheva
Assel Mukasheva
Medical image segmentation has undergone significant changes in recent years, mainly due to the development of base models. The introduction of the Segment Anything Model (SAM) represents a major shift from task-specific architectures to universal architectures. This review discusses the adaptation of SAM in medical visualisation, focusing on three primary domains. Firstly, multimodal fusion frameworks implement semantic alignment of heterogeneous visual methods. Secondly, volumetric extensions transition from slice-based processing to native 3D spatial reasoning with architectures such as SAM3D, ProtoSAM-3D, and VISTA3D. Thirdly, uncertainty-aware architectures integrate probabilistic calibration for clinical interpretability, as illustrated by the SAM-U and E-Bayes SAM models. A comparative analysis reveals that SAM derivatives with effective parameters achieve Dice coefficients of 81–95%, while concomitantly reducing annotation requirements by 56–73%. Future research directions include incorporating adaptive domain hints, Bayesian self-correction mechanisms, and unified volumetric frameworks to enable autonomous generalisation across diverse medical imaging contexts.

15 May 2025 in Journal of Electrical Engineering & Technology
Verified
Journal Article
Closed access
PDF file
ATAnel Tolkynbekova
Anel Tolkynbekova
DKDina Koishiyeva
Dina Koishiyeva
ABAlibek Bissembayev
Alibek Bissembayev
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
Assel MukashevaAssel Mukasheva
Assel Mukasheva
JKJeong-won Kang
Jeong-won Kang

2 May 2024 in Вестник КазАТК
Verified
Journal Article
Open access
PDF file
ДВДенис Валяев
Денис Валяев
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
Assel MukashevaAssel Mukasheva
Assel Mukasheva
ЖСЖанна Суйменбаева
Жанна Суйменбаева
Бұл мақалада әртүрлі уақыт кезеңдері бар деректер жиынтығында бағдарламалық жасақтаманың істен шығу қаупін бағалау моделін қолдану қарастырылады. Модель мәтіндерді салыстыру модельдерін (Джаро-Винклердің ұқсастығы) бөлісуге, уақыт қатарындағы ауытқуларды анықтауға (Фридманның супер тегістеуі, MST ыдырауы, квартиларалық ауқым) және тәуекелдерді талдауға (Failure Modes and Effects Analysis) негізделген. Құрамдас бөліктер ретінде тәжірибеде белсенді қолданылатын жақсы зерттелген модельдер қолданылады. Осы модельдерді қатар қолданудың арқасында журнал жазбалары мен қосымшаның орындалу көрсеткіштері негізінде тәуекел параметрлерін есептеу мүмкіндігі пайда болады. Бұл зерттеу орындалу көрсеткіштерінен жедел жадты тұтынуды қарастырады. Зерттеу аясында авторлар алдыңғы мақалада келтірілген экспериментті аяқтады, соның арқасында осы модельдің тұрақтылығы туралы қорытынды жасауға мүмкіндік туды. Эксперимент кездейсоқ аралықтарда жүйенің одан әрі жұмыс істеуі үшін қауіпті мінез-құлықты имитациялайтын қосымшаны қамтиды, атап айтқанда қате туралы жазбалар журналына шығарылатын жедел жадты тұтынудағы күрт шығарындылар. Талдаудың өзі R және Kotlin бағдарламалау тілі құралдарының көмегімен жүргізілді. Зерттеу нәтижесі қатені анықтап, онымен байланысты тәуекелді бағалай отырып, мінез-құлықтың әртүрлі уақыт кезеңдеріндегі модельдің өнімділігін көрсетті және модельді одан әрі зерттеу және жетілдіру мүмкіндігін ашты

12 October 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
BKBekzat Kabyshke
Bekzat Kabyshke
Assel MukashevaAssel Mukasheva
Assel Mukasheva
DMDinargul Mukhammejanova
Dinargul Mukhammejanova
BTBakyt Tulegenova
Bakyt Tulegenova
ABAlmagul Bizhanova
Almagul Bizhanova
This paper presents a performance evaluation of WPA2 and WPA3 security protocols in private Wi-Fi 6 environments. The study investigates how the transition from WPA2-PSK to WPA3-Personal affects wireless network performance under practical residential conditions. Measurements were conducted using a consumer Wi-Fi 6 access point operating in the 2.4 GHz and 5 GHz frequency bands. TCP throughput was measured with iperf3, while UDP tests and ICMP ping measurements were used to evaluate bitrate stability, jitter, packet loss, and round-trip latency. A Wi-Fi 5 WPA2 configuration was additionally considered as a baseline to provide contextual comparison with the Wi-Fi 6 results. The experimental results show that, in the tested Wi-Fi 6 configuration, switching from WPA2 to WPA3 caused only a moderate decrease in average TCP throughput: approximately 5–6% in the 2.4 GHz band and 2–3% in the 5 GHz band. UDP and ICMP measurements also indicate that WPA3 did not introduce noticeable degradation in jitter, packet loss, or latency. These findings suggest that WPA3-Personal can be enabled in private Wi-Fi 6 environments with relatively low performance cost, making it a practical choice for users who seek stronger wireless security without substantial loss of network performance.