ABSTRACT
The variants of coronavirus both delta and omicron are much more contagious and affecting greater percentage of human population. In this research, an attempt is made to predict classification of clinical emergency treatment of corona variant infected patients using their recorded cough sound file. Cough audio signal features such as zero crossing and mel-frequency cepstral coefficients (MFCC), chromo gram (chroma_stft), spectral centroid, spectral roll off, spectral-bandwidth are to be extracted and stored along with patient ID, date, and timings. Digital signal processing of recorded cough audio file obtained needs to be cleaned and pre-processed and normalized to get a training dataset in order to build intelligent ML model using multiclass classifier SVM for predicting the class labels with maximum accuracy. The model proposed in this research paper helps to systematically plan and handle emergency treatment of the patients by classifying their severity based on the cough audio signal using SVM. The built model predicts and classifies the emergency treatment level as low, medium, and high with 96% accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.