Pneumonia Detection on X-Ray Imaging using Softmax Output in Multilevel Meta Ensemble Algorithm of Deep Convolutional Neural Network Transfer Learning Models

Pneumonia is the leading cause of death from a single infection worldwide in children. A proven clinical method for diagnosing pneumonia through chest X-ray. However, resulting X-ray images often need clarification, subjective judgments. In addition, process diagnosis requires longer time. One technique can be applied by applying advanced deep learning, namely, Transfer Learning with Deep Convolutional Neural Network (Deep CNN) and modified Multilevel Meta Ensemble using Softmax. The purpose this research was to improve accuracy classification model. This study proposes model meta-ensemble approach five algorithms: Xception, Resnet 15V2, InceptionV3, VGG16, VGG19. ensemble stage used two different concepts, where first level combined output ResNet15V2, InceptionV3 algorithms. Then reused following learning process, other algorithms, namely VGG16 called two. algorithm at same as previous stage, KNN Based on experiments, proposed has better than others, test value 98.272%. benefit could help doctors recommendation tool make more accurate timely diagnoses, thus speeding up treatment reducing risk complications.