Pneumonia Classification using Deep Learning in Healthcare
Garima Verma1, Shiva Prakash2

1Garima Verma, Department of Information Technology and Computer Application Madan Mohan Malaviya University of Technology, Gorakhpur, India.
2Shiva Prakash, Department of Information Technology and Computer Application Madan Mohan Malaviya University of Technology, Gorakhpur, India.
Manuscript received on January 17, 2020. | Revised Manuscript received on January 22, 2020. | Manuscript published on February 10, 2020. | PP: 1715-1723 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1599029420/2020©BEIESP | DOI: 10.35940/ijitee.D1599.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: There is a great growing interest in the domain of deep learning techniques for identifying and classifying images with various datasets. An enormous availability of datasets (e.g. ChestX-Ray14 dataset) has developed a keen interest in deep learning. Pneumonia is a disease that is caused by various bacteria, virus etc. X-ray is one of the major diagnosis tools for diagnosing pneumonia. This research work mainly proposes a convolutional neural system (CNN) model prepared without any preparation to group and identify the occurrence of pneumonia disease from a given assortment of chest X-ray image tests. Dissimilar to different strategies that depend exclusively on more learning draws near or conventional carefully assembled systems to accomplish an amazing grouping execution, and developed a convolutional neural arrange model without any preparation to separate and character the images to decide whether an individual is suffering with pneumonia. This model could help alleviate the dependability and difficult challenges frequently confronted to manage therapeutic problems. In this paper, CNN algorithm has been used along with different data augmentation techniques for improving the classification accuracies which has been discussed to increase the performance which will help in improving the validation and training accuracies and characterization of exactness of the CNN model and accomplished various results. This experiment was carried out using python language and has shown improved outcomes. 
Keywords:  Deep Learning, CNN (Convolution Neural Network), Architecture, Data Preprocessing, Data Augmentation
Scope of the Article:  Deep Learning