Efficient lung disease classification through luminescent feature selection using firefly algorithm

Abstrak

Over the past couple of decades, there has been a substantial increase in the prevalence of lung ailments, resulting in 3.5 million fatalities each year. This necessitates the adoption of a lung disease detection technology that is effective, trustworthy, and cost-effective. In this study, we propose an optimized convolutional neural network (CNN) model, used for multiclass categorization of lung ailments based on frontal chest X-rays. The classification includes four categories: COVID-19, viral pneumonia, lung opacity, and non-infectious normal group. We implemented the firefly algorithm to optimize the global efficiency of feature selection of the lung abnormality in the X-ray images of lung disease and COVID-19 to classify the input according to the target class. The proposed algorithm was tested for accuracy, precision, recall, and F1-score. The findings were validated using the transfer learning model VGG-16; the algorithm achieved a superior accuracy of 99.3% compared to that of other cutting-edge models such as Inceptionv3 and ResNet50.