Paper Key : IRJ************874
Author: Manjunatha S
Date Published: 05 Sep 2022
Using big data for prediction analysis along with machine learning or deep learning techniques or algorithms is one the most active areas of research in order to improve the health and the medical science. There is a significant increase in the size of the medical data as well as the complexity in the diagnosis of various diseases. With this being said, the diagnosis or the prediction of many terminal or fatal diseases has seen huge success through deep learning. Among those fatal Diseases, pneumonia is one of the greatest threats to the life of a man affecting the lungs leading to lung failure. To diagnose a man with pneumonia, the x-ray of chest is needed, and an expert in the prediction is also required. Hence, it is more convenient to build an automated predictor to predict the pneumonia using the big data deep learning methods. Among all the other techniques, CNN (Convolutional Neural Networks) stand tall and high in this prediction along with other classifiers. Also, pre-training the CNN models for very large datasets that is for big data of healthcare units stands a high chance for accurate classification. A CNN model which is pre-trained along with three models Vgg, Resnet, Efficientet an efficient feature extraction technique and various classifiers to classify the positive from negative is considered to give highly accurate results.
DOI LINK : 10.56726/IRJMETS29620
Paper File to download :