Electrical Engineering & Computer Science (eecs)

CSAIL researchers have developed a new material with embedded sensors that can track a person’s movement, reports Mashable. The clothing could “track things like posture or give feedback on how you’re walking.”

Fast Company reporter Elizabeth Segran spotlights how CSAIL researchers have crafted a new smart fabric embedded with sensors that can sense pressure from the person wearing it. “Sensors in this new material can be used to gather data about people’s posture and body movements,” writes Segran. “This could be useful in a variety of settings, including athletic training, monitoring the health of elderly patients, and identifying whether someone has fallen over.”

Wired reporter Will Knight writes that MIT researchers have found that many of the key AI data sets used to train algorithms could contain many errors. “What this work is telling the world is that you need to clean the errors out,” says graduate student Curtis Northcutt. “Otherwise the models that you think are the best for your real-world business problem could actually be wrong.”

A new imaging technique created by researchers from MIT and other institutions has been used to shed light on the contents of an unopened letter from 1697, writes Matt Simon for Wired. “With fancy letterlocking techniques, you will forcibly rip some part of the paper, and then that will become detectable,” says Prof. Erik Demaine, of the method used to seal the letter.

Researchers from MIT and other institutions have developed a new virtual-reality technique that has allowed them to unearth the contents of letters written hundreds of years ago, without opening them, writes New York Times reporter William J. Broad. “The new technique could open a window into the long history of communications security,” writes Broad. “And by unlocking private intimacies, it could aid researchers studying stories concealed in fragile pages found in archives all over the world.”

Using X-ray imaging and algorithms, MIT researchers have been able to virtually open and read letters that been sealed for more than 300 years, writes Priti Parikh for New Scientist. “Studying folding and tucking patterns in historic letters allows us to understand technologies used to communicate,” says Jana Dambrogio, a conservator at the MIT Libraries.

Researchers from MIT and other institutions have used algorithms and an X-ray scanner to decipher the secrets inside a letter that has been sealed since 1697, reports Sara Castellanos for The Wall Street Journal. “This is a dream come true in the field of conservation,” said Jana Dambrogio, the Thomas F. Peterson Conservator at MIT Libraries.

Bloomberg reporter Ashlee Vancee spotlights the work of alumnus Youyang Gu SB ’15, MEng’19, who developed a forecasting model for Covid-19 last spring that was widely considered to be one of the most accurate models of the pandemic’s trajectory. “The novel, sophisticated twist of Gu’s model came from his use of machine learning algorithms to hone his figures,” writes Vancee.

Wall Street Journal reporter Dieter Holger spotlights the MIT Climate and Sustainability Consortium. Holger notes that in January “IBM joined a dozen other companies—including Apple Inc., Verizon Communications Inc. and Boeing Co. —as the inaugural members of the MIT Climate and Sustainability Consortium to develop technologies to combat climate change.”

Second-year student Darren Lim speaks with KUOW about his work developing a website aimed at making it easier for Washington state residents to book appointment for Covid-19 vaccines. The website “shows which providers in Washington state have vaccines available, and then allows you to click through to their websites to make an appointment.”

In this video, Mashable spotlights how MIT researchers have developed a new system that can 3-D print objects without human intervention. “The system works thanks to a software toolkit that lets you design custom blueprints,” Mashable explains.

CSAIL researchers have developed a new system, dubbed LaserFactory, that can print custom devices and robots without human intervention, reports Brian Heater for TechCrunch. “The system is comprised of a software kit and hardware platform designed to create structures and assemble circuitry and sensors for the machine,” Heater writes.

TechCrunch reporter Darrell Etherington writes that MIT researchers have developed a new “liquid” machine learning system that can learn on the job. Etherington notes that the system has “the potential to greatly expand the flexibility of AI technology after the training phase, when they’re engaged in the actual practical inference work done in the field.”

Wired reporter Will Knight spotlights how MIT researchers built a machine learning system that can help predict which patients are most likely to develop breast cancer. “What the AI tools are doing is they're extracting information that my eye and my brain can't,” says Constance Lehman, a professor of radiology at Harvard Medical School and division chief of breast imaging at MGH.

New York Times reporter Steve Lohr spotlights Inrupt, an MIT startup founded by Prof. Tim Berners-Lee, which is aimed at providing people more control over their personal data. “Tim has become increasingly concerned as power in the digital world is weighted against the individual,” explains Daniel Weitzner, a principal research scientist at CSAIL.