• M S V Sanjana
• Nikita Gudapati
• K Lakshmi Prasanna
• Chandra Sekhar

Many academics are employing convolutional neural networks (CNNs) to extract deep-level characteristics from medical images to categorize Alzheimer's disease (AD) and estimate clinical scores as medical imaging and deep learning technology advance. PCANet is a little DL network. It creates principal component analysis-based layered filter banks for sample learning. Picture characteristics are obtained from blockwise histograms after binarization. Layered filter banks created from sample data make it less adaptable than other networks. This implies tens or hundreds of thousands of dimensions for its characteristics. To overcome these challenges, this research presents the data-independent PCANet-based nonnegative matrix factorization tensor decomposition network (NMF-TDNet). NMF is used to create multilayer filter banks to learn from samples instead of PCA. Create a higher-order tensor using the learning outputs and reduce the data dimensions using tensor decomposition to get the final picture features. These factors let our SVM diagnose AD, predict the clinical score, and classify it

Deep learning, regression, and classification are all terms used to describe Alzheimer's disease (AD).

"Regression and Classification of Alzheimer’s Disease Diagnosis From 3D Brain MR Image", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.g219-g224, March-2024, Available :http://www.jetir.org/papers/JETIR2403631.pdf

"Regression and Classification of Alzheimer’s Disease Diagnosis From 3D Brain MR Image", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppg219-g224, March-2024, Available at : http://www.jetir.org/papers/JETIR2403631.pdf