Deep Learning Based Intelligent Classification Of Covid-19 & Pneumonia Using Cough Auscultations

• Published in: 2021 6th International Multi-Topic ICT Conference (IMTIC) pp. 1 - 6
• Main Authors: Naqvi, Syed Zohaib Hassan, Khan, Misha Urooj, Raza, Ali, Saeed, Zubair, Abbasi, Zeeshan, Ali, Syeda Zuriat-e-Zehra
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.11.2021
• Subjects: Analytical models; Cough auscultation; COVID-19; Deep learning; Lung; MobileNet v2; Pandemics; Pneumonia; Pulmonary diseases; Sociology
• DOI: 10.1109/IMTIC53841.2021.9719740

The World Health Organization has designated COVID-19 a pandemic because its emergence has influenced more than 50 million world's population. Around 14 million deaths have been reported worldwide from COVID-19. In this research work, we have presented a method for autonomous screening of COVID-19 and Pneumonia subjects from cough auscultation analysis. Deep learning-based model (MobileNet v2) is used to analyze a 6757 self-collected cough dataset. The experimentation has demonstrated the efficiency of the proposed technique in distinguishing between COVID-19 and Pneumonia. The results have demonstrated the cumulative accuracy of 99.98%, learning rate of 0.0005 and validation loss of 0.0028. Furthermore, cough analysis can be performed for other patients screening of other pulmonary abnormalities.