Detection Capability Prediction Based on Broad Learning System during the COVID-19 Pandemic

Junyan Lin, Minghao Tan, Yufan Zheng, Kaihan Wu, Choujun Zhan

Abstract: The greatest threat to global health is the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-Cov-2) currently. COVID-19 was declared as a global pandemic on March 11, 2020. For this highly contagious disease, the way of human-to-human transmission has forced us to implement large-scale COVID-19 testing worldwide. On February 21, 2021, 120 million people have already undergone COVID-19 testing. The large scale of COVID-19 testing has driven innovation in strategies, technologies, and concepts for managing public health testing. It is an unprecedented global testing program. In this study, we describe the role of COVID-19 testing while establishing a comprehensive and validated research dataset that includes data from 189 countries and 893 regions between August 8, 2019, and March 3, 2021. Through our analysis, we observed that the more COVID-19 testings provided, the more confirmed cases were detected. The availability of large-scale COVID-19 testing is indispensable to fully control the outbreak, as it is the main way to cut off the source of COVID-19 transmission. Then we used this dataset to predict the COVID-19 detection capabilities of each country by Machine Learning, Ensemble Learning, and Broad Learning System. Experimental results show that Broad Learning System significantly outperformed the Machine Learning. The R2 of predicted the ability of the COVID-19 testing can reach 0.999921.