Dina Katabi, SM ’99, PhD ’03, came from a family of doctors in Syria, where she was born, but she abandoned medical school for a more math-focused life, studying electrical engineering at the University of Damascus and then computer science as a grad student at MIT, where she is now a professor.
In her early work, she came up with novel ways to prevent congestion in wireless networks, making things like Wi-Fi and cellular service faster and more efficient. To overcome the problem of interference—signals competing for the same pathway—she embraced it, developing a way to mix together signals from different sources and decode them on the receiving end.
A hallmark of her work, she says, is bridging disciplines, and her approach to wireless networks is unique in that it goes all the way from the signal to the application. “It’s not the traditional way people think about a field,” she says.
By the time she won a MacArthur “genius grant” in 2013, Katabi had turned her focus from how wireless signals carry data to how they bounce off people. Her team built a wall-mounted device that emits extremely low-powered radio waves and uses machine learning to extract information from the way those signals reflect off people’s bodies. Since the signals travel through walls, the device becomes a kind of x-ray vision that can measure a person’s heartbeat, breathing, gait, and more without any kind of wearable sensor. This information can also reveal emotional states and even distinct stages of sleep.
“The vision is to do passive monitoring for health and wellness,” Katabi says. The device could detect subtle changes in Alzheimer’s patients, for example, and monitor some effects of their medications. She thinks her technology could also make metrics like the pain scale more objective, yet another way to improve medicine.
The big new idea for making self-driving cars that can go anywhere
The mainstream approach to driverless cars is slow and difficult. These startups think going all-in on AI will get there faster.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.