Abstract Coronavirus (COVID-19) is an epidemic disease that spreads all over the world in a very short time and has fatal consequences. Such infectious diseases must be correctly detected without harming people or with minimal harm, and the necessary treatment must be initiated early. At this point, traditional treatment methods applied by doctors may be insufficient or diagnosis and treatment may be delayed. Therefore, Artificial Intelligence (AI) and Machine Learning (ML) techniques that are widely used in many areas and effective in solving complex problems come to the fore, to obtain a more effective and successful treatment in these situations. This study aimed to diagnose and detect the COVID-19 image from different lung tomography images (COVID-19, viral pneumonia, bacterial pneumonia, and normal) with AI and ML techniques. In this context, it was used the K-Nearest Neighbor (KNN) method, which is an ML algorithm, and Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) deep learning approaches which are among the current techniques of AI. In addition, the results were tested by creating models with combinations of different optimization and activation functions and neuron numbers in the CNN method. Thus, the application potential of CNN, DNN, and KNN methods in image recognition and classification were seen and the success of the proposed model was demonstrated with the obtained findings.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|