A Novel Local Feature Generation Technique Based Sound Classification Method for Covid-19 Detection using Lung Breathing Sound

Lung breathing sounds have been used to diagnose many diseases, including Covid-19. Nowadays, Covid-19 has affected daily life worldwide, and it caused a global pandemic. Generally, computer vision methods presented classify healthy, pneumonia, They achieved high classification rates on datasets with limited number of classes without taking into consideration other lung diseases. Our main hypothesis is detect automatically among diseases by using sounds. Therefore, dataset sound ten collected, novel method proposed in this paper. This presents local feature generation technique, Substitution Box (S-Box) the present lightweight encryption utilized as pattern. A nonlinear pattern based S-Box, named Present-SBox-Pat (present S-Box pattern). new pooling-based transformation (maximum tent pooling (MaTP)) generate high, middle, low levels features. It considered preprocessing work. ReliefF iterative neighbourhood component analysis (RFINCA) selector select most discriminative informative Two shallow classifiers are obtain results. The MaTP network RFINCA selector-based 95.43% accuracy SVM classifier. These results demonstrated success techniques generating selecting features that facilitate task classifiers.