A comparative analysis of CNN, ResNet-50, and EfficientNet-B4 architectures for automated skindisease classification from dermoscopic images was conducted. The study was performed using the HAM10000dataset comprising 10,015 images across seven nosological classes. Model performance was evaluated usingaccuracy, sensitivity, specificity, F1-score, AUC-ROC, inference time, and memory footprint. EfficientNet-B4demonstrated the best performance, achieving 93.71 % accuracy and an AUC-ROC of 0.978. The obtainedresults indicate the potential of this architecture for integration into clinical decision-support systems
| Mualliflar | Nazirova , Elmira, Abdusalomova , Shokhista |
|---|---|
| Jurnal | Innovation science and technologiy |
| Nashr sanasi | 2026-06-01 |
| Jild | 2 |
| Son | 6 |
| Til | Ingliz |
| DOI | 10.5281/zenodo.20643398 |
DOI: 10.5281/zenodo.20643398 · Maqolaning asl sahifasi
deep learning; skin disease diagnosis; convolutional neural network (CNN); ResNet; EfficientNet; dermoscopy; HAM10000; medical image analysis; transfer learning; AUC-ROC
This article presents a scientific analysis of promising strategies for developing Uzbekistan’sfinancial market in the context of digital and green transformation. The study examines the implementation ofESG principles…
Ushbu maqolada “O‘zbekiston temir yo‘llari” AJning 2015–2025-yillardagi amaliy iqtisodiyholati va raqamli transformatsiya jarayonlari tahlil qilingan. Korxonada IoT, real vaqt monitoringi va sun’iyintellekt (AI)…
Ushbu maqolada uzoq muddatli aktivlar bilan bog‘liq xarajatlarni strategik boshqaruv hisobida to‘liq va to‘g‘riaks ettirish masalalari tahlil qilinadi. Qishloq xo‘jaligi mahsulotlari ishlab chiqaruvchi “Green Heaven”…
2020-yildan boshlab O‘zbekistonda inflyatsion targetlash rejimiga bosqichma-bosqicho‘tish jarayoni pul-kredit siyosati instrumentlaridan foydalanish amaliyotini takomillashtirish zaruratini yuzagakeltirmoqda. Tadqiqotda…
Research objectives: This paper examines the economic mechanisms that catalyze the development ofsmall businesses and entrepreneurship, focusing on finance, taxation, regulatory frameworks, innovation systems…
The article addresses the application of artificial intelligence and machine learning technologiesfor protecting public-sector information systems against cyber threats. The inadequacy of classical signaturebasedtools…
The study explores the meaning of the concept benefit and its semantic field in English andUzbek linguistic cultures. The aim is to determine the formation, development, and usage of this concept in bothlanguages…
This article provides a comprehensive analysis of the theoretical and practical aspects of the mechanismsof institutional regulation of the residential real estate sector in Namangan region. The study studies the…
This article examines the integration of ESG principles—Environmental, Social, and Governance—and digital technologies in the development of the Corporate Social Management (CSM) system. The purposeof the study is to…
This article provides a comprehensive analysis of the formation of the optimal structure of equity capital in jointstockcompanies and its impact on financial stability. The study examines the capital structure of…