Open Access

ARTICLE

A Healthcare System for COVID19 Classification Using Multi-Type Classical Features Selection

Muhammad Attique Khan¹, Majed Alhaisoni², Muhammad Nazir¹, Abdullah Alqahtani³, Adel Binbusayyis³, Shtwai Alsubai³, Yunyoung Nam⁴, Byeong-Gwon Kang^4,*

1 Department of Computer Science, HITEC University, Taxila, Pakistan
2 Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh, 11671, Saudi Arabia
3 College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia
4 Department of ICT Convergence, Soonchunhyang University, Asan, 31538, Korea

* Corresponding Author: Byeong-Gwon Kang. Email:

Computers, Materials & Continua 2023, 74(1), 1393-1412. https://doi.org/10.32604/cmc.2023.032064

Received 05 May 2022; Accepted 24 June 2022; Issue published 22 September 2022

Abstract

The coronavirus (COVID19), also known as the novel coronavirus, first appeared in December 2019 in Wuhan, China. After that, it quickly spread throughout the world and became a disease. It has significantly impacted our everyday lives, the national and international economies, and public health. However, early diagnosis is critical for prompt treatment and reducing trauma in the healthcare system. Clinical radiologists primarily use chest X-rays, and computerized tomography (CT) scans to test for pneumonia infection. We used Chest CT scans to predict COVID19 pneumonia and healthy scans in this study. We proposed a joint framework for prediction based on classical feature fusion and PSO-based optimization. We begin by extracting standard features such as discrete wavelet transforms (DWT), discrete cosine transforms (DCT), and dominant rotated local binary patterns (DRLBP). In addition, we extracted Shanon Entropy and Kurtosis features. In the following step, a Max-Covariance-based maximization approach for feature fusion is proposed. The fused features are optimized in the preliminary phase using Particle Swarm Optimization (PSO) and the ELM fitness function. For final prediction, PSO is used to obtain robust features, which are then implanted in a Support Vector Data Description (SVDD) classifier. The experiment is carried out using available COVID19 Chest CT Scans and scans from healthy patients. These images are from the Radiopaedia website. For the proposed scheme, the fusion and selection process accuracy is 88.6% and 93.1%, respectively. A detailed analysis is conducted, which supports the proposed system efficiency.

---

Keywords

---