Electrocardiograms (E.C.G.) are discussed in the paper "Arrhythmia detection using multi-lead E.C.G. spectra and Complex Support Vector Machine Classifiers." In this work, the authors investigate machine learning classification algorithms for E.C.G. analysis and arrhythmia detection. Four beat types, Normal (N), Premature Ventricular Contraction (P.V.C.), Atrial Premature Contraction (A.P.C.), and Right Bundle Branch Block Beat (RBBB), are simultaneously presented to a Complex Support Vector Machine (CSVM) classifier. The E.C.G. Akila Sairete et al. / Procedia Computer Science 194 (2021) 18

Sarirete, A. et al./ Procedia Computer Science 00 (2020) 000000 signals are obtained from the St Petersburg INCART 12-lead Arrhythmia Database (INCARTDB). The detection of E.C.G. Wave (P, Q.R.S., T) is performed with the Wave Form Database (WFDB) Software Package, which is used to read the annotation files and find the R (peak) location. For feature extraction, the Discrete Fourier Transform (DFT) is used. The study aims to establish the advantage of CSVM over standard SVM in simultaneously detecting different types of arrhythmias based on multi-lead recordings following signal compression in the Fourier domain. The CSVM classification algorithm provided better performance than the standard SVM classifier with an accuracy of 98.25%. Future work will concentrate on the further development of E.C.G. signal pre-processing using adaptive wavelet algorithms and classification with Clifford SVMs.

Continuing the study of covid-19 and AI, in the paper "AI-based Power Screening Solution for SARS-CoV2 Infection: A Sociodemographic Survey and COVID-19 Cough Detector," the authors propose the Artificial Intelligence (AI) power screening solution for SARS-CoV2 infection that can be deployable through the mobile application. To overcome the shortage of SARS-CoV2 datasets, the transfer learning technique is applied. Multipronged mediator for risk-averse Artificial Intelligence Architecture is induced for minimizing the false diagnosis of risk stemming from the problem of complex dimensionality. This proposed application provides early detection and initial screening for SARS-CoV2 cases. Huge data points can be processed through the AI framework that can examine the users and classify them into "Probably COVID," "Probably not COVID," and "Result indeterminate."

In the paper "Lung Cancer Diagnosis Based on Chan-VEse Contour and Polynomial Neural Network," the authors introduce a computer-aided detection (CAD) system using computed tomography (C.T.) scans for nodule classification. The proposed system is divided into four stages involving image pre-processing using Gabor filter and Kuwahara filter, image segmentation by applying ChanVese active contouring. Feature extraction where features are computed using Discrete Wavelet Transform (DWT) at one, two, and three decomposition levels. After that, 13 features are computed from each wavelet sub-band. As a result, the output features are compared, and the best output is used to train Polynomial Neural Network (P.N.N.) classification method to classify benign and malignant nodules. The result of the proposed system shows high performance in both the segmentation and the classification, with an accuracy of 96.66% for the classifying method.