Automated Detection of COVID-19 Cough Sound using Mel-Spectrogram Images and Convolutional Neural Network

COVID-19 is a new disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) variant. The initial symptoms of the disease commonly include fever (83-98%), fatigue or myalgia, dry cough (76-82%), and shortness of breath (31-55%). Given the prevalence of coughing as a symptom, artificial intelligence has been employed to detect COVID-19 based on cough sounds. This study aims to compare the performance of six different Convolutional Neural Network (CNN) models (VGG-16, VGG-19, LeNet-5, AlexNet, ResNet-50, and ResNet-152) in detecting COVID-19 using mel-spectrogram images derived from cough sounds. The training and validation of these CNN models were conducted using the Virufy dataset, consisting of 121 cough audio recordings with a sample rate of 48,000 and a duration of 1 second for all audio data. Audio data was processed to generate mel-spectrogram images, which were subsequently employed as inputs for the CNN models. This study used accuracy, area under curve (AUC), precision, recall, and F1 score as evaluation metrics. The AlexNet model, utilizing an input size of 227×227, exhibited the best performance with the highest Area Under the Curve (AUC) value of 0.930. This study provides compelling evidence of the efficacy of CNN models in detecting COVID-19 based on cough sounds through mel-spectrogram images. Furthermore, the study underscores the impact of input size on model performance. This research contributes to identifying the CNN model that demonstrates the best performance in COVID-19 detection based on cough sounds. By exploring the effectiveness of CNN models with different mel-spectrogram image sizes, this study offers novel insights into the optimal and fast audio-based method for early detection of COVID-19. Additionally, this study establishes the fundamental groundwork for selecting an appropriate CNN methodology for early detection of COVID-19