Open Access

ARTICLE

Deep Optimal VGG16 Based COVID-19 Diagnosis Model

M. Buvana¹, K. Muthumayil², S. Senthil kumar³, Jamel Nebhen⁴, Sultan S. Alshamrani⁵, Ihsan Ali^6,*

1 Department of Computer Science and Engineering, PSNA College of Engineering and Technology, Dindigul, 624622, India
2 Department of Information Technology, PSNA College of Engineering and Technology, Dindigul, 624622, India
3 Department of Electrical and Electronics Engineering, New Prince Shri Bhavani College of Engineering and Technology, Chennai, 600073, India
4 Prince Sattam Bin Abdulaziz University, College of Computer Engineering and Sciences, Alkharj, 11942, Saudi Arabia
5 Department of Information Technology, College of Computer and Information Technology, Taif University, Taif, 21944, Saudi Arabia
6 Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, 50603, Malaysia

* Corresponding Author: Ihsan Ali. Email:

Computers, Materials & Continua 2022, 70(1), 43-58. https://doi.org/10.32604/cmc.2022.019331

Received 09 April 2021; Accepted 10 May 2021; Issue published 07 September 2021

Abstract

Coronavirus (COVID-19) outbreak was first identified in Wuhan, China in December 2019. It was tagged as a pandemic soon by the WHO being a serious public medical condition worldwide. In spite of the fact that the virus can be diagnosed by qRT-PCR, COVID-19 patients who are affected with pneumonia and other severe complications can only be diagnosed with the help of Chest X-Ray (CXR) and Computed Tomography (CT) images. In this paper, the researchers propose to detect the presence of COVID-19 through images using Best deep learning model with various features. Impressive features like Speeded-Up Robust Features (SURF), Features from Accelerated Segment Test (FAST) and Scale-Invariant Feature Transform (SIFT) are used in the test images to detect the presence of virus. The optimal features are extracted from the images utilizing DeVGGCovNet (Deep optimal VGG16) model through optimal learning rate. This task is accomplished by exceptional mating conduct of Black Widow spiders. In this strategy, cannibalism is incorporated. During this phase, fitness outcomes are rejected and are not satisfied by the proposed model. The results acquired from real case analysis demonstrate the viability of DeVGGCovNet technique in settling true issues using obscure and testing spaces. VGG 16 model identifies the image which has a place with which it is dependent on the distinctions in images. The impact of the distinctions on labels during training stage is studied and predicted for test images. The proposed model was compared with existing state-of-the-art models and the results from the proposed model for disarray grid estimates like Sen, Spec, Accuracy and F1 score were promising.

---

Keywords

---