Paper Title
Respiratory Disease Prediction Using Deep Learning
Abstract
The medical sector may analyze data with Convolutional Neural Networks (CNN) at extremely fast speeds
without compromising accuracy. As a result of the dearth of samples for lung diseases, it is challenging to predict respiratory
diseases with any level of certainty. Traditional supervised machine learning algorithms do not yield more accurate results
when taught with fewer data samples. A deep learning-based respiratory illness prediction approach is suggested to
categorize COVID-19, pneumonia, and tuberculosis. Data augmentation, Contrast Limited Adaptive Histogram (CLHAE),
and Visual Geometry Group are all combined in this method (VGG). The use of integrated data augmentation and the Visual
Geometry Group (VGG) model for better illness prediction is the innovative component of this work.
Keywords - Deep Learning, Contrast Limited Adaptive Histogram (CLHAE), Visual Geometry Group, (VGG), Disease
Detection, Data Augmentation