VinTeam is one of the finalists in the XPRIZE Pandemic Response Challenge, which focuses on the development of data-driven AI systems to predict COVID-19 infection rates, and plan interventions. VinTeam is made up of Mudit Jain, a software engineering lead at Google, and Biplab Deka, PhD from the University of Illinois, UC. The duo have created an AI tool that Jain says can help predict where coronavirus related cases are going to rise, and help authorities take the appropriate precautions to stop the spread of the disease.
According to Jain, one of the challenges that the team faced is that different regions faced different spread and peak patterns. In response, VinTeam created separate AI models for each region. Jain told Gadgets 360 in an email that VinTeam built this solution on a traditional epidemiological technique called SEIR model and extended it with AI to make it a dynamic model instead of the traditional static approach.
To train its AI models, VinTeam used publicly available features such as demographics, health infrastructure and economic indicators. The team also used Google Maps mobility index, which is collected from Android phones worldwide in an anonymised and secure way, and measures population movement changes in public areas such as parks, hospitals, workplaces, groceries, railways stations, airports etc. The team also made use of Google’s COVID-19 symptom search trends data, which is similarly aggregated anonymously and contains popularity of Google…
