About this document

Applsci 15 11426 by rcharanteja2006 is a document available to read on EtoBox.

This study presents a multi-model ensemble learning framework for pneumonia classification using multi-head attention and transfer learning, leveraging pre-trained models DenseNet-121, ResNet-50, and VGG-19. The proposed approach achieved accuracies of 91.67%, 93.79%, and 90.60% for binary, three-class, and four-class classification tasks, respectively, demonstrating its effectiveness in improving diagnostic accuracy. Future work will focus on expanding the dataset and assessing the model

Author

rcharanteja2006

Language

EN