Pneumonia prediction from x-ray images using convolutional neural network deep learning against support vector machine learning algorithm for maximum accuracy and minimum loss

• Main Authors: Sivalingam, Saravanan Madderi, Veeramanickam, M. R. M., Venkatesh, Bandaru, Patil, Pradnya, Mavaveerakannan, R.
• Format: Conference Proceeding
• Language: English
• Subjects: Accuracy; Algorithms; Artificial neural networks; Datasets; Deep learning; Machine learning; Neural networks; Pneumonia; Support vector machines
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0178587

This research study is to predict the Pneumonia severity from chest X-Ray images using an innovative image capture dataset using Convolutional Neural Network (CNN) deep learning algorithms. The objective of this research study is to predict higher accuracy and lower loss of the Pneumonia from chest X-Ray images. This study used 10 samples with two groups of algorithms with the g-power value of 80 percent and the Pulmonology based Images are collected from various web sources with recent study findings. To predict the Pneumonia severity from chest X-Ray images for humans already the Support Vector Machine (SVM) machine learning algorithm has found 75% of accuracy, therefore this study needs to find better accuracy for chest X-Ray images detection with the CNN deep learning algorithm. This research study found 92.6% of accuracy to predict pneumonia from innovative chest X-Ray images detection using the CNN algorithm. This study concludes that the CNN algorithm on the innovative X-Ray image capture dataset is significantly better than the SVM algorithm.