AUTHOR=Sharan Praveer 

TITLE=Automated Discrimination of Cough in Audio Recordings: A Scoping Review

JOURNAL=Frontiers in Signal Processing

VOLUME=Volume 2 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/signal-processing/articles/10.3389/frsip.2022.759684

DOI=10.3389/frsip.2022.759684

ISSN=2673-8198

ABSTRACT=The objective of this paper’s systematic review is to compile the different tools used to identify coughs, and how artificial intelligence may be used to discriminate a COVID-19 cough from another type of cough. A systematic search was done on the Google Scholar and MIT library engines to identify papers relevant to cough detection, discrimination, and epidemiology. A total of 96 papers have been compiled and reviewed. Cough recording datasets such as the ESC-50, FSDKaggle 2018 and 2019 datasets can be used for neural networking and identifying coughs. Although these datasets are not available to the public, and the ones that are, are not extensive or do not focus on coughs. For cough discrimination techniques, neural networks such as k-NN, Feed Forward Neural Network, RF, SVM and naive Bayesian classifiers are used. While there are many proposed ideas for cough discrimination, the method best suited for detecting COVID-19 coughs within this urgent time frame is unknown. The unavailability of datasets which can be used for thorough training of such neural networks complicates the idea of having a widespread application to detect COVID-19 solely through coughing. The main contribution of this review is to compile information on what has been researched on machine learning algorithms and its effectiveness for diagnosing COVID-19, as well as highlight the areas of future areas for research. This review shall aid future researchers in taking the best course of action for building a machine learning algorithm to discriminate COVID-19 related coughs with accuracy and accessibility.