Abstract:
Coronavirus is a viral disease in which the infection has a place with the COVID family. The virus travels down the respiratory tract. This can lead to pneumonia, small intestine or alveoli infection in the lungs, where blood is exchanged for oxygen & carbon dioxide. Due to the current high population growth, automated disease detection has emerged as a crucial area of study in medicine. As the quickest diagnostic method, an automatic detection system ought to be used to stop COVID-19 from spreading. Different researchers have done different tasks in the field of COVID detection and developed various models for COVID detection. This research study is conducted using deep learning model ResNet50 with combination of machine learning model SVM (ResNet50 + SVM) for COVID patient classification. The performance of the proposed model is then compared to other models like ResNet101 and deep learning model VGG. The dataset is collected from publicly available online repository Kaggle.com. For simulation, Python is utilized together with libraries like as Tensor Flow, Keras, and Sklearn. The performances of the models are evaluated in terms of accuracy, precision, recall & f-measure. In comparison of other models, our proposed model (ResNet50 + SVM) achieved better results in term of accuracy as 98% and precision, recall & F-measure as 98% respectively. While another model named ResNet101 achieved the accuracy of 96%, recall 97% and precision and f-Measure 96% respectively. And third model VGG achieved accuracy of 95%, while precision of 96% recall of 95% and F1-score 95%. The overall simulation demonstrates that our proposed model achieved better results as compared to other models in the proposed study.
Page(s):
1-1
DOI:
DOI not available
Published:
Journal: Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book), Volume: 0, Issue: 0, Year: 2024
Keywords:
Classification
,
Covid
,
Resnet
,
Detection
,
VGG