Oral Presentation , Page 307-311 (5)

Volume Title: 2nd IEEE International Conference on Electronic Eng., Faculty of Electronic Eng., Menouf, Egypt, 3-4 July. 2021

¹Wafaa Ahmed ; ¹waleed saad; ²mona shokair; ²moawad dessouky; ³fathi A El-Samie

¹faculty of electronic engineering

²menouf

³Minufia- Egypt

Coronavirus (COVID-19) is considered as a viral disease, which caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Spreading COVID-19 will continue to effect on the health and economy. Imaging techniques such as chest X-ray and CT scans are a crucial step of infected patients in the battle with COVID-19. Recently, Convolutional Neural Network is a class of deep learning and can be used for classifying medical diseases such as COVID-19. This paper introduces an efficient architecture for COVID-19 diagnosis using X-ray dataset. The proposed architecture start with image pre-processing using lung segmentation and image resizing. Deep feature extraction through using the proposed CNN model and different pre-trained models. The classification process is performed using either support vector machine SVM or Softmax classifier. Two classes of COVID-19 cases are classified. Simulation results indicates that, our proposed model is able to classify the classes of COVID-19 with high accuracy (98 . 7%) and (98 . 5%) for SVM and Softmax, respectively. The performance metrics are the processing time, system complexity, accuracy, loss, confusion matrix, sensitivity, precision, F1 score, specificity and Receiver Operating Characteristics.

COVID-19; feature extraction; Deep learning