Cross-validation results across five folds.

<div><p>Malaria continues to be a severe health problem across the globe, especially within resource-limited areas which lack both skilled diagnostic personnel and diagnostic equipment. This study investigates the use of deep learning diagnosis for malaria through ConvNeXt models that in...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Outlwile Pako Mmileng (21485620) (author)
مؤلفون آخرون:	Albert Whata (14307682) (author), Micheal Olusanya (21485623) (author), Siyabonga Mhlongo (21485626) (author)
منشور في:	2025
الموضوعات:	Microbiology Cell Biology Biotechnology Cancer Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified resnet50 obtained 81 resnet18 reached 62 remote healthcare facilities final augmented dataset explainability frameworks demonstrate exhibited strong robustness adamw optimiser produced version v1 tiny time diagnostic applications skilled diagnostic personnel better model performance transfer learning techniques deep learning diagnosis malaria parasite detection especially within resource data augmentation methods convnext tiny model transfer learning data augmentation swin tiny diagnostic equipment malaria diagnosis total number study investigates reaching 98 practical solution often observed microscopy expertise limited regions limited areas large datasets label smoothing findings highlight convnext models 9 %. 6 %,
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

Cross-validation results across five folds.

مواد مشابهة