Can I read Alz-ConvNets for Classification of Alzheimer Disease Using Transfer Learning Approach on EtoBox?

Alz-ConvNets for Classification of Alzheimer Disease Using Transfer Learning Approach by Amar Shukla; Rajeev Tiwari; Shamik Tiwari is a Computer Science article available to read on EtoBox.

What is Alz-ConvNets for Classification of Alzheimer Disease Using Transfer Learning Approach about?

Alzheimer disease (AD) is a progressive brain disorder that gradually deprives patients of their basic abilities. Despite the absence of specific treatments, early detection of this neurodegenerative disease can slow its progression and prevent further deterioration. AD can manifest in different stages, including non-demented (nD), mildly demented (mD), moderately demented (moD), and very mildly demented (vmD) which are taken from the Kaggle repository naming [Alzheimer dataset (4 class of Images)]. To classify these stages, we utilized various convolutional network models such as Alz-DenseConvNet, Alz-ResConvNet, Alz-VGGConvNet, Alz-MobileConvNet, and Alz-XceptionConvNet. Both binary and multiclass classification is performed to classify the different stages of AD. After testing and validation, Alz-MobileConvNet was found to be the superior method for multiclass classification with an accuracy (A cc ) of 94%. On the other hand, Alz-VGGConvNet surpassed other methods for binary classification with an effective A cc of 99%.

Who reads Alz-ConvNets for Classification of Alzheimer Disease Using Transfer Learning Approach?

Author

Amar Shukla; Rajeev Tiwari; Shamik Tiwari

Publisher

Springer Science and Business Media LLC

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)