Selecting Optimal Moments of Chest Images by Partialized-Dual-Hybrid Feature Selection Scheme for Morphological-based COVID-۱۹ Diagnosis

One way of analyzing COVID-۱۹ is to exploit X-ray and computed tomography (CT) images of the patients' chests. Employing data mining techniques on chest images can provide in significant improvements in the diagnosis of COVID-۱۹. However, in feature space learning of chest images, there exists a large number of features that affect COVID-۱۹ identification performance negatively. In this work, we aim to design the dual hybrid partial-oriented feature selection scheme (DHPFSS) for selecting optimal features to achieve high-performance COVID-۱۹ prediction. First, by applying the Zernike function to the data, moments of healthy chest images and infected ones were extracted. After Zernike moments (ZMs) segmentation, subsets of ZMs (SZMs۱:n) are entered into the DHPFSS to select SZMs۱:n-specific optimal ZMs (OZMs۱:n). The DHPFSS consists of the filter phase and dual incremental wrapper mechanisms (IWMs), namely incremental wrapper subset selection (IWSS) and IWSS with replacement (IWSSr). Each IWM is fed by ZMs sorted by filter mechanism. The dual IWMs of DHPFSS are accompanied with the support vector machine (SVM) and twin SVM (TWSVM) classifiers equipped with radial basis function kernel as SVMIWSSTWSVM and SVMIWSSrTWSVM blocks. After selecting OZMs۱:n, the efficacy of the union of OZMs۱:n is evaluated based on the cross-validation technique. The obtained results manifested that the proposed framework has accuracies of ۹۸.۶۶%, ۹۴.۳۳%, and ۹۴.۸۲% for COVID-۱۹ prediction on COVID-۱۹ image data (CID) including ۱CID, ۲CID, and ۳CID respectively, which can improve accurate diagnosis of illness in an emergency or the absence of a specialist.

Keywords:

Hybrid feature selection scheme , Hyperplane-based learning methods , Optimal Zernike moments , COVID-۱۹ prediction