Ensemble multimodal deep learning for early diagnosis and accurate classification of COVID-19

Santosh Kumar; Sachin Kumar Gupta; Vinit Kumar; Manoj Kumar; Mithilesh Kumar Chaube; Nenavath Srinivas Naik

doi:10.1016/j.compeleceng.2022.108396

Ensemble multimodal deep learning for early diagnosis and accurate classification of COVID-19

Comput Electr Eng. 2022 Oct:103:108396. doi: 10.1016/j.compeleceng.2022.108396. Epub 2022 Sep 20.

Authors

Santosh Kumar¹, Sachin Kumar Gupta², Vinit Kumar³, Manoj Kumar⁴, Mithilesh Kumar Chaube⁵, Nenavath Srinivas Naik¹

Affiliations

¹ Department of Computer Science and Engineering, International Institute of Information Technology (IIIT)-Naya Raipur, Chhattisgarh, 4933661, India.
² School of Electrical and Communication Engineering, Shri Mata Vaishno Devi University, Katra J&K, India.
³ Galgotias College of Engineering and Technology, Greater Noida, 201306, India.
⁴ Faculty of Engineering and Information Sciences, University of Wollongong in Dubai, Dubai Knowledge Park, Dubai, United Arab Emirates.
⁵ Department of Mathematical Science, International Institute of Information Technology (IIIT)-Naya Raipur, Chhattisgarh, 4933661, India.

Abstract

Over the past few years, the awful COVID-19 pandemic effect has become a lethal sickness. The processing of the gathered samples requires extra time due to the use of medical diagnostic equipment, methodologies, and clinical testing procedures for the early diagnosis of infected individuals. An innovative multimodal paradigm for the early diagnosis and precise categorization of COVID-19 is put up as a solution to this issue. To extract distinguishing features from the prepared chest X-ray picture and cough (audio) database, chest X-ray-based and cough-based model are used here. Other public chest X-ray image datasets, and the Coswara cough (audio) dataset containing 92 COVID-19 positive, and 1079 healthy subjects (people) using the deep Uniform-Net, and Convolutional Neural Network (CNN). The weighted sum-rule fusion method and ensemble deep learning algorithms are utilized to further combine the extracted features. For the early diagnosis of patients, the framework offers an accuracy of 98.67%.

Keywords: COVID-19; Deep learning; Ensemble Learning; Fusion; Machine Learning.