Research
I am passionate about research and have published and submitted papers to journals. Below is the status of my current work.
Published
Browser-Based Dermoscopy Triage with Calibrated MobileNet: A Privacy-First Approach
Nurbek Taizhanov • Published January 02, 2026
Early melanoma detection saves lives, yet rural clinics often lack dermatologists and reliable connectivity. We present a browser-based, client-side skin-lesion classifier that returns top-three diagnostic suggestions in under 1 s on commodity smartphones. Using a leakage-safe lesion-level split of HAM10000 (10,015 images, seven classes), a fine-tuned MobileNet attains 97.9% top-3 accuracy, macro-F1 0.78, and melanoma sensitivity 0.908 at specificity 0.95. The 2.8 MB TensorFlow.js model runs entirely on-device, enabling rapid triage in connectivity-limited settings.
Introducing Cultural Knowledge in Language Models: KazCulture Dataset for Kazakh Culture
Published in IEEE Access, volume 14, pages 44027–44042 (2026).
Akylbek Maxutov, Batyr Arystanbekov, Zhanat Makhataeva, Adil Yergen, Nurbek Taizhanov, Guldana Nauryzbaikyzy, and Huseyin Atakan Varol
View Paper · DOI: 10.1109/ACCESS.2026.3675790