COVID-19 disease diagnosis with light-weight CNN using modified MFCC and enhanced GFCC from human respiratory sounds

Abstract

In the last 2 years, medical researchers and clinical scientists have paid close attention to the problem of respiratory sound classification to classify COVID-19 disease symptoms. In the physical world, very few AI-based (Artificial Intelligence) techniques are often used to detect COVID-19/SARS-CoV-2 respiratory disease symptoms from the human respiratory system-generated acoustic sounds such as acoustic voice sound, breathing (inhale and exhale) sounds, and cough sound. We propose a light-weight Convolutional Neural Network (CNN) with Modified-Mel-frequency Cepstral Coefficient (M-MFCC) using different depths and kernel sizes to classify COVID-19 and other respiratory sound disease symptoms such as Asthma, Pertussis, and Bronchitis. The proposed network outperforms conventional feature extraction models and existing Deep Learning (DL) models for COVID-19/SARS-CoV-2 classification accuracy in the range of 4–10%. The model’s performance is compared with the COVID-19 crowdsourced benchmark dataset and gives a competitive performance. We applied different receptive fields and depths in the proposed model to get different contextual information that should aid in classification. And our experiments suggested 1 12 receptive fields and a depth of 5-Layer for the light-weight CNN to extract and identify the features from respiratory sound data. The model is also trained and tested with different modalities of data to showcase its effectiveness in classification.

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

“…A head-to-head comparison of the results presented in Table 1 would be hasty and unwise as the evaluation metrics were not reported consistently. For instance, Chaudhari et al [ 17 ], Coppock et al [ 29 ], Ponomarchuk et al [ 38 ] and Nguyen et al [ 39 ] used only the AUC metric, while Lella and Pja [ 40 ] used accuracy only. Different evaluation metrics are used as follows: where FP refers to false positive, FN refers to false negative, TP refers to true positive, and TN refers to true negative.…”

“…In addition, the FNR can be straightforwardly computed as . We note that the confusion matrix, a matrix that counts the TN, FN, TP, and FP from actual target and predicted values, is often available, which can provide the reader with all the necessary tools to make a judgment [ 24 , 40 , 41 , 42 ].…”

Interpretation of lung disease classification with light attention connected module

“…A hybrid-scalogram feature extraction method was designed using empirical mode decomposition and continuous wavelet transform, and the accuracy of three and six types was 98.2 % and 98.72 %, respectively. Kranthi Kumar et al [28] proposed a lightweight CNN using Enhanced-GFCC and Modified-MFCC techniques for SARS-CoV-2/COVID-19 approved at Cambridge University. The accuracy was improved by 4–10 % to 91 % compared to the basic MFCC.…”

COVID-19: respiratory disease diagnosis with regularized deep convolutional neural network using human respiratory sounds

“…The SARS-CoV-2 disease can be identified with different human-generated data, such as X-ray, CT-scan, RTPCR, patient tweets, and respiratory sounds. Medical researchers have implemented several deep learning (DL), machine learning (ML), and signal processing (SP) models to diagnose SARS-CoV-2 with the human pulmonary sounds (cough, breathing, and voice) and images (X-ray and CT-scan) [ 17 – 23 ]. Therefore, there are numerous options available to identify SARS-CoV-2, and one of the approaches is human respiratory sound auscultations (HRSA).…”

“…This manuscript contains data linked with it that can be found in a data repository. [Authors’ comment: The data presented in this work are not available publicly, we have collected COVID-19 large-scale sounds (breath, voice, and cough) data from trusted repositories and cited sources in references [ 23 , 36 , 40 , 47 , 48 ].] The data are available with the corresponding author and can be given to the researchers and scientists with the reasonable request.…”