:This paper describes the high precision early diagnosis and classification of Alzheimer's disease using Functional Magnetic
Resonance Imaging (fMRI). Since fMRIs records metabolic activity of brain over the time, it has excellent spatial and good temporal resolution
then MRI imaging technique. To perform an early diagnosis of brain disorders such as Alzheimer’s disease (AD) and Parkinson’s disease (PD).
To apply deep learning (DL) classification algorithms for the accurate detection of severity levels in order to begin the healing process. To
improve the performance metrics of the proposed classification model in terms of Sensitivity, Specificity and accuracy. The proposed
methodology is going to deal with fMRI image sets using 3D – Convolutional Neural Network (3D – CNN) is preferred to produce high
accuracy. The 3D - CNN based brain disorder classification is divided into two phases such as training and testing phases. The number of
images is divided into different category by using labels name such as AD, and normal brain image (NBI). In the training phase, preprocessing,
feature exaction and classification with Loss function is performed to make a prediction model. Initially, label the training image set. Finally,
the convolution neural network is used for automatic brain disorder classification.
Index Terms— Functional Magnetic Resonance Imaging (fMRI), Normal Brain Image (NBI), Alzheimer’s disease (AD), Parkinson’s disease
(PD), Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Deep Learning (DL)