@article {10.3844/jcssp.2022.67.77,
article_type = {journal},
title = {Diagnosing Alzheimer’s Disease using Convolution Neural Networks},
author = {Sarita, and Mukherjee, Saurabh and Choudhury, Tanupriya and Kulshrestha, Kush and Singh, Ruby},
volume = {18},
number = {2},
year = {2022},
month = {Feb},
pages = {67-77},
doi = {10.3844/jcssp.2022.67.77},
url = {https://thescipub.com/abstract/jcssp.2022.67.77},
abstract = {Alzheimer’s is a disease wherein constant degeneration of neurons and their synapses result in impaired brain functioning which leads to personality changes, memory loss, thinking and speech disorder. So, there is a requirement of an automated and early diagnosis of this disease to decrease the death rate. The proposed work is coupled with deep learning techniques to predict the Alzheimer’s disease to prevent patient inevitable symptoms. The application of a Convolution Neural Network (CNN) has increased tremendously due to its capability to model the non-linear cognitive transformation and record its complexity. In this research work, CNN is used for the classification of the MRI images of normal control from the patients affected with Alzheimer’s. Total 150 images from ADNI dataset is used to classify the neurological disorder. The purposed work attained 87% accuracy for detection of AD using CNN architecture which is comparatively better than existing techniques. The performance of model can be increased by using hybrid model on multiple dataset.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}