Two- Way Bernoulli distribution for Predicting Dementia with Machine Learning and Deep Learning Methodologies

Authors

  • Vishal Dutt, Rohit Raturi , Vicente García-Díaz, Sreenivas Sasubilli

Abstract

Neural Disorders mostly depend on food habits. It has been noticed that with the increase of age they are getting worse than ever with respect to some of the brain issues. The modelling of information is based on the flow that has been observed in convolutional neural networks and the information that has been gathered will be based on HC (Healthy Control). And in AD, the value of the Area Under the Curve (AUC) for the Condition entropy which is a major assert for the work is accessed. Prediction of the Conditional Entropy feature classification gave the result of the prediction based on three different comparisons. These comparisons will define the implementation between AD Vs HC, Age patterns of young Vs old and lastly, gender patterns female Vs male. Different results are obtained with CNN and CENT classification with varying accuracy rate. Statistical analysis proves that the conditional entropy features are good with the brain labels and are very helpful for the brain imaging and deep learning. Previously, AD disease was not focused on the research board. It was not much focused because of lack of facilities in the clinical treatments and even medication. The major cause of AD disease is over reaction on the brain tissues when there is a lot more stress on those tissues. It is important to predict the cause of AD without AE as the major criteria and it should be done using age. However, age shouldn’t be only the criteria. This case has worked both on textual data and on brain MRI images.

Published

2020-11-01

Issue

Section

Articles