In this paper, we propose a deep learning-based framework for detecting COVID-19 positive subjects from their cough sounds. In particular, the proposed framework comprises two main steps. In the first step, we generate a feature representing the cough sound by combining embedding features extracted from a pre-trained model and handcrafted features, referred to as the front-end feature extraction. Then, the combined features are fed into different back-end classification models for detecting COVID-19 positive subjects. The experimental results on the Second 2021 DiCOVA Challenge - Track 2 dataset achieve the top-2 ranking with an AUC score of 81.21 on the blind Test set, improving the challenge baseline by 6.32 and showing competitive with the state-of-the-art systems.

A Cough-based deep learning framework for detecting COVID-19.

This paper presents a deep learning framework for detecting COVID-19 positive subjects from their cough sounds. In particular, the proposed approach comprises two main steps. In the first step, we generate a feature representing the cough sound by combining an embedding extracted from a pre-trained model and handcrafted features extracted from draw audio recording, referred to as the front-end feature extraction. Then, the combined features are fed into different back-end classification models for detecting COVID-19 positive subjects in the second step. Our experiments on the Track-2 dataset of the Second 2021 DiCOVA Challenge achieved the second top ranking with an AUC score of 81.21 and the top F1 score of 53.21 on a Blind Test set, improving the challenge baseline by 8.43% and 23.4% respectively and showing deployability, robustness and competitiveness with the state-of-the-art systems. 

/pdf/a-cough-based-deep-learning-framework-for-detecting-covid-19-49tf1686.pdf

A Cough-based deep learning framework for detecting COVID-19

Contrary to expectations that the coronavirus pandemic would terminate quickly, the number of people infected with the virus did not decrease worldwide and coronavirus-related deaths continue to occur every day. The standard COVID-19 diagnostic test technique used today, PCR testing, requires professional staff and equipment, which is expensive and takes a long time to produce test results. In this paper, we propose a feature set consisting of four features: MFCC, Δ2-MFCC, Δ-MFCC, and spectral contrast as a feature set optimized for the diagnosis of COVID-19, and apply it to a model that combines ResNet-50 and DNN. Crowdsourcing datasets from Cambridge, Coswara, and COUGHVID are used as the cough sound data for our study. Through direct listening and inspection of the dataset, audio recordings that contained only cough sounds were collected and used for training. The model was trained and tested using cough sound features extracted from crowdsourced cough data and had a sensitivity and specificity of 0.95 and 0.96, respectively.

/pdf/covid-19-detection-model-with-acoustic-features-from-cough-1tqxnrd5.pdf

COVID-19 Detection Model with Acoustic Features from Cough Sound and Its Application

Vocal Biomarker Based COVID-19 Detection Using DNN and Transfer Learning ResNet50

The coronavirus disease 2019 (COVID-19) outbreak has given rise to a high number of human deaths as well as chaos in the world’s economic, social, sociological, and health sectors. Controlling an epidemic requires a thorough understanding of the evolution of the epidemic’s features, which may be discovered by gathering and evaluating relevant big data. Big data analytics are essential for obtaining the data needed to make judgments and take precautionary steps. Big data analytics tools are critical for obtaining the information required to make well-informed judgments and take proactive measures. However, assuming the massive data on COVID-19 from different resources, it will be necessary to review the role of big data analysis in controlling COVID-19’s spread, as well as present the main encounters and guidelines of COVID-19 data analysis, and provide a framework for related current applications and frameworks to enable future COVID-19 analysis. Artificial intelligence (AI) technologies are widely used as powerful weapons in the fight against COVID-19. In this chapter, we examine the fundamental scope and contributions of AI in combating COVID-19 from the standpoints of sickness detection and diagnosis. A rundown of the data and technologies available for AI-based COVID-19 research is described. Finally, the major challenges and AI options for fighting COVID-19 are discussed. AI is presently mostly applied in medical image analysis, genomics, and prediction, but it still has a lot of potential in the healthcare sector. 

Artificial Intelligence and Big Data for COVID-19 Diagnosis

With the periodic rise and fall of COVID-19 and countries being inflicted by its waves, an efficient, economic, and effortless diagnosis procedure for the virus has been the utmost need of the hour. COVID-19 positive individuals may even be asymptomatic making the diagnosis difficult, but amongst the infected subjects, the asymptomatic ones need not be entirely free of symptoms caused by the virus. They might not show any observable symptoms like the symptomatic subjects, but they may differ from uninfected ones in the way they cough. These differences in the coughing sounds are minute and indiscernible to the human ear, however, these can be captured using machine learning-based statistical models. In this paper, we present a deep learning approach to analyze the acoustic dataset provided in Track 1 of the DiCOVA 2021 Challenge containing cough sound recordings belonging to both COVID-19 positive and negative examples. To perform the classification on the sound recordings as belonging to a COVID-19 positive or negative examples, we propose a ConvNet model. Our model achieved an AUC score percentage of 72.23 on the blind test set provided by the same for an unbiased evaluation of the models. The ConvNet model incorporated with Data Augmentation further increased the AUC-ROC percentage from 72.23 to 87.07. It also outperformed the DiCOVA 2021 Challenge's baseline model by 23% thus, claiming the top position on the DiCOVA 2021 Challenge leaderboard. This paper proposes the use of Mel frequency cepstral coefficients as the feature input for the proposed model.

Darsh Kaushik

Papers

COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation.