Transfer learning yordamida kasallik tashxisi
Kalit so'zlar:
Transfer Learning, tibbiy tasvirlar, kasallik tashxisi, sun’iy intellektAnnotatsiya
Ushbu tezisda tibbiy tasvirlar asosida kasalliklarni aniqlash jarayonida mashinali o‘qitishning zamonaviy yo‘nalishi bo‘lgan Transfer Learning texnologiyasidan foydalanish imkoniyatlari keng yoritiladi. Tadqiqot davomida EfficientNetB0, ResNet50 va MobileNetV2 modellarining pnevmoniya tasvirlarini aniqlashdagi samaradorligi solishtirildi. Shuningdek, tasvirlarni oldindan qayta ishlash, data augmentation, modelni qayta o‘qitish (fine-tuning) bosqichlari va natijalar barqarorligini oshirishga qaratilgan texnik yechimlar ham batafsil bayon qilindi. Olingan natijalar Transfer Learning yondashuvi tibbiy tasvirga asoslangan diagnostikada yuqori aniqlik va ishonchlilikni ta’minlashini ko‘rsatadi.
Библиографические ссылки
1. Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering.
2. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Google Research.
3. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.
4. Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. CVPR.
5. Howard, A. G., et al. (2017). MobileNet: Efficient Convolutional Neural Networks for Mobile Vision Applications. Google Research.
6. Szegedy, C., et al. (2015). Going Deeper with Convolutions. Google Inception Architecture.
7. Dosovitskiy, A., et al. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition. ViT Architecture.
8. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
