Toggle light / dark theme

EPFL researchers have developed electronic fibers that, when embedded in textiles, can be used to collect data about our bodies by measuring fabric deformation. Their technology employs flexible transmission lines and offers a host of applications, including in the medical industry.

Professor Fabien Sorin and doctoral assistant Andreas Leber, at the Laboratory of Photonic Materials and Fibre Devices (FIMAP) in EPFL’s School of Engineering, have developed a technology that can be used to detect a body’s movements—and a whole lot more.

“Imagine clothing or hospital bed sheets capable of monitoring your breathing and physical gestures, or AI-powered textiles that allow humans to interact more safely and intuitively with robots” says Leber. “The flexible transmission lines that we’ve developed can do all of this.”

As artificial intelligence (AI) becomes increasingly used for critical applications such as diagnosing and treating diseases, predictions and results regarding medical care that practitioners and patients can trust will require more reliable deep learning models.

In a recent preprint (available through Cornell University’s open access website arXiv), a team led by a Lawrence Livermore National Laboratory (LLNL) computer scientist proposes a novel aimed at improving the reliability of classifier models designed for predicting disease types from diagnostic images, with an additional goal of enabling interpretability by a medical expert without sacrificing accuracy. The approach uses a concept called confidence calibration, which systematically adjusts the ’s predictions to match the human expert’s expectations in the .

“Reliability is an important yardstick as AI becomes more commonly used in high-risk applications, where there are real adverse consequences when something goes wrong,” explained lead author and LLNL computational scientist Jay Thiagarajan. “You need a systematic indication of how reliable the model can be in the real setting it will be applied in. If something as simple as changing the diversity of the population can break your system, you need to know that, rather than deploy it and then find out.”

A personal, handheld device emitting high-intensity ultraviolet light to disinfect areas by killing the novel coronavirus is now feasible, according to researchers at Penn State, the University of Minnesota and two Japanese universities.

There are two commonly employed methods to sanitize and disinfect areas from bacteria and viruses—chemicals or ultraviolet radiation exposure. The UV radiation is in the 200 to 300 nanometer range and known to destroy the virus, making the virus incapable of reproducing and infecting. Widespread adoption of this efficient UV approach is much in demand during the current pandemic, but it requires UV radiation sources that emit sufficiently high doses of UV light. While devices with these high doses currently exist, the UV radiation source is typically an expensive mercury-containing gas discharge lamp, which requires high power, has a relatively short lifetime, and is bulky.

The solution is to develop high-performance, UV light emitting diodes, which would be far more portable, long-lasting, energy efficient and environmentally benign. While these LEDs exist, applying a current to them for light emission is complicated by the fact that the also has to be transparent to UV light.

As countries around the world begin lifting pandemic lockdowns, researchers are entering a new phase of work — donning masks with their lab coats, staggering hours in laboratory spaces and taking shifts on shared instruments. Some universities have created detailed plans to track and test staff, and many have limited the capacity of indoor spaces and the flow of people through hallways and entrances. For others, post-lockdown plans are still taking shape. And whereas some universities have worked in lockstep with governments to formulate safety plans, others have charted their own paths.


As scientists around the world return to work, they’re encountering new safety rules and awkward restrictions — and sometimes writing the protocols themselves.