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.
Under Review
Introducing Cultural Knowledge in Language Models: KazCulture Dataset for Kazakh Culture
Submitted to IEEE Access. Currently under review (Manuscript ID: Access-2025-53012).
Submission confirmation email from IEEE Access