A couple of weeks after the Coronavirus outbreak and the disease has become a full-blown pandemic. According to official Chinese statistics, more than 130 people have died from the mysterious virus.

Contagious diseases may be diagnosed by men and women in face masks and lab coats, but warning signs of an epidemic can be detected by computer programmers sitting thousands of miles away. Around the tenth of January, news of a flu outbreak in Chinas Hubei province started making its way to mainstream media. It then spread to other parts of the country, and subsequently, overseas.

But the first to report of an impending biohazard was BlueDot, a Canadian firm that specializes in infectious disease surveillance. They predicted an impending outbreak of coronavirus on December 31 using an artificial intelligence-powered system that combs through animal and plant disease networks, news reports in vernacular websites, government documents, and other online sources to warn its clients against traveling to danger zones like Wuhan, much before foreign governments started issuing travel advisories.

They further used global airline ticketing data to correctly predict that the virus would spread to Seoul, Bangkok, Taipei, and Tokyo. Machine learning and natural language processing techniques were also employed to create models that process large amounts of data in real time. This includes airline ticketing data, news reports in 65 languages, animal and plant disease networks.

iStock

We know that governments may not be relied upon to provide information in a timely fashion. We can pick up news of possible outbreaks, little murmurs or forums or blogs of indications of some kind of unusual events going on, Kamran Khan, founder and CEO of BlueDot told a news magazine.

The death toll from the Coronavirus rose to 81 in China, with thousands of new cases registered each day. The government has extended the Lunar New Year holiday by three days to restrict the movement of people across the country, and thereby lower the chances of more people contracting the respiratory disease.

However, a lockdown of the affected area could be detrimental to public health, putting at risk the domestic population, even as medical supplies dwindle, causing much anger and resentment.

24 May, 2018

24 May, 2018

24 May, 2018

24 May, 2018

24 May, 2018

Read this article:
This tech firm used AI & machine learning to predict Coronavirus outbreak; warned people about danger zones - Economic Times