Washington Post reporter Paige Winfield Cunningham spotlights how MIT researchers have developed a new way to estimate the impact of Covid-19. The researchers “developed a way to compare and merge more than two dozen different models from universities and analytics groups around the country.”
Research scientist Brian Subirana speaks with The Economist’s Babbage podcast about his work developing a new AI system that could be used to help diagnose people asymptomatic Covid-19.
MIT researchers have developed a new model that could be used to help determine “how long you will be safe in a room with someone who is positive for COVID-19 based on room type, size and even the ventilation and filtration system,” reports Boston 25 News.
Fast Company reporter Mark Sullivan writes that Prof. John Bush and Prof. Martin Z. Bazant have developed a mathematical model that “simulates the fluid dynamics of virus-loaded respiratory droplets in any space, from a cozy kitchen to a gigantic concert hall.”
A new algorithm developed by MIT researchers could be used to help detect people with Covid-19 by listening to the sound of their coughs, reports Zoe Kleinman for BBC News. “In tests, it achieved a 98.5% success rate among people who had received an official positive coronavirus test result, rising to 100% in those who had no other symptoms,” writes Kleinman.
Mashable reporter Rachel Kraus writes that a new system developed by MIT researchers could be used to help identify patients with Covid-19. Kraus writes that the algorithm can “differentiate the forced coughs of asymptomatic people who have Covid from those of healthy people.”
A new took developed by MIT researchers uses neural networks to help identify Covid-19, reports Alyse Stanley for Gizmodo. The model “can detect the subtle changes in a person’s cough that indicate whether they’re infected, even if they don’t have any other symptoms,” Stanley explains.
TechCrunch reporter Devin Coldewey writes that MIT researchers have built a new AI model that can help detect Covid-19 by listening to the sound of a person’s cough. “The tool is detecting features that allow it to discriminate the subjects that have COVID from the ones that don’t,” explains Brian Subirana, a research scientist in MIT’s Auto-ID Laboratory.
MIT researchers have developed a new AI model that could help identify people with asymptomatic Covid-19 based on the sound of their cough, reports CBS Boston. The researchers hope that in the future the model could be used to help create an app that serves as a “noninvasive prescreening tool to figure out who is likely to have the coronavirus.”
Researchers from the Singapore-MIT Alliance for Research and Technology (SMART) Critical Analytics for Manufacturing Personalized Medicine (CAMP) research group have been awarded new research grants aimed at supporting work exploring personalized medicine and cell therapy, reports Health Europa. “In addition to our existing research on our three flagship projects, we hope to develop breakthroughs in manufacturing other cell therapy platforms that will enable better medical treatments and outcomes for society,” says Associate Provost Krystyn Van Vliet.
New tools developed by CSAIL researchers allow users to design a pattern that can be used to 3D print knitted garments, reports Elizabeth Segran for Fast Company. “We’re exciting about how this can be used by everyday, nonexpert knitters,” says graduate student Alexandre Kaspar. “This lets anybody become a designer.”
7 News spotlights how CSAIL researchers have developed two new software systems that are aimed at allowing anyone to customize and design their own knitted design patterns. “The researchers tested the software by having people with no knitting experience design gloves and hats,” explains 7 News reporter Keke Vencill.
TechCrunch reporter Catherine Shu writes that CSAIL researchers have developed two new systems that enable users to design and customize their own knitted items, no knitting experience required. Shu explains that the researchers want “to make designing and making machine-knitted garments as accessible as 3D printing is now.”
TechCrunch reporter Darrell Etherington writes that MIT researchers have developed a system that can predict a perso's trajectory. The tool could allow “robots that typically freeze in the face of anything even vaguely resembling a person walking in their path to continue to operate and move around the flow of human foot traffic."
Researchers from MIT and a number of other institutions have found that grammar-enriched deep learning models had a better understanding of key linguistic rules, reports Kyle Wiggers for VentureBeat. The researchers found that an AI system provided with knowledge of basic grammar, “consistently performed better than systems trained on little-to-no grammar using a fraction of the data, and that it could comprehend ‘fairly sophisticated’ rules.”