CNN-RNN Hybrid Model for Diagnosis of COVID-19 on X-Ray Imagery

Abstract

Abstract This research aims to implement deep learning in determining Covid-19 or normal cases using X-Ray imagery. The method used is CNN (ResNet50) and RNN (LSTM). The research phase begins with data collection, data preprocessing, method modeling, method testing and method evaluation. The data was taken from the kagle.com site with the amount of data used 1.000 images where 500 covid data and 500 normal data, the data is divided into 80% training data, 10% validation data and 10% test data. The results of the evaluation by calculating the ResNet50-LSTM confusion matrix have a value of 95% accuracy, 96% precision, 94% recall and 95% F1-score. At the method testing stage, the researcher got the results of the proposed method experiencing overfitting seen by the comparison of the loss values ​​in the validation data which were not as good as the loss values ​​of the training data. From the results of evaluation and method testing, research can be used as a recommendation in cases of Covid-19 or normal.

Keywords

• deep learning
• resnet50
• lstm
• image classification
• covid-19