Pneumonia Diagnosis on Chest X-Rays with Machine Learning

This paper presents a mechanism which tackles the problem of pneumonia diagnosis based on machine learning. The mechanism, involved feature extraction and dimensionality reduction algorithm to make it possible for improving classification performance and reducing difficulties of the training process. In the evaluation experiments, several mainstream deep neural networks are employed to realize pneumonia diagnosis with which we compared our proposed mechanism. Experimental results indicate that our proposed method outperforms many of the prevalent deep neural networks for general use, including ResNet, MobileNet and Xception. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the International Conference on Identification, Information and Knowledge in the internet of Things, 2020.