Moore’s Law for your pants.
Wearable devices are popular these days, but they’re largely restricted to watches, rings, and eyewear. Researchers have now developed a thread-based computer that can be stitched into clothes.
Being able to sense what our bodies are up is useful in areas like healthcare and sports. And while devices like smartwatches can track metrics like heart rate, body temperature, and movement, humans produce huge amounts of data that devices tethered to specific points of the body largely miss.
That’s what prompted MIT engineers to create a fabric computer that can be stitched into regular clothes. The device features sensors, processors, memory, batteries, and both optical and Bluetooth communications, allowing networks of these fibers to provide sophisticated whole-body monitoring.
“Our bodies broadcast gigabytes of data through the skin every second in the form of heat, sound, biochemicals, electrical potentials, and light, all of which carry information about our activities, emotions, and health,” MIT professor Yoel Fink, who led the research, said in a press release.
“Wouldn’t it be great if we could teach clothes to capture, analyze, store, and communicate this important information in the form of valuable health and activity insights?”
The MIT team has been working on incorporating electronics into fibers for more than a decade, but in a recent paper in Nature they outline a breakthrough that significantly boosts the sophistication of the devices they can build.
One of the biggest challenges the team faced was the mismatch between flat, 2D chip layouts and the 3D structure of fibers. This made it difficult to establish reliable connections between components and led to failure in previous generations of their fiber computers.
To get around this, the team designed a novel flexible circuit board. This allowed them to attach an electronic component, such as a microcontroller or Bluetooth module, onto a chip in 2D and then fold it into a tiny box with the component nestled inside.
They connected several of these chips using copper microwires arranged in a spiral and coated them in a flexible plastic material. These fibers were then braided with traditional textile materials like polyester, wool, and nylon so they could be stitched into clothes.
The resulting threads had enough computing power to run a rudimentary neural network able to detect the kinds of exercises someone was doing. The researchers stitched four of them into the sleeves of a shirt and the legs of a pair of pants and used these to monitor the wearer’s activity.
Individually, the fabric computers could distinguish between squats, planks, arm circles, and lunges with 67 percent accuracy. But when they used Bluetooth connections to communicate and vote on the predictions, the accuracy jumped to 95 percent.
The technology is currently undergoing a rigorous real-world trial. This month, participants in the US Army and Navy are conducting a month-long winter research mission to the Arctic wearing merino wool base layers featuring the fabric computers. The devices will provide real-time information on the health and activity of the servicemen involved in the exercise.
“As a leader with more than a decade of Arctic operational experience, one of my main concerns is how to keep my team safe from debilitating cold weather injuries,” US Army Major Mathew Hefner, the commander of the mission, said in the press release.
“Conventional systems just don’t provide me with a complete picture. We will be wearing the base layer computing fabrics on us 24/7 to help us better understand the body’s response to extreme cold and ultimately predict and prevent injury.”
While the extreme conditions the military operates in make the technology particularly useful for them, it’s easy to see how whole-body monitoring could benefit areas like elite sports and healthcare too. It may not be long before your pants have as much computing power as an early home computer.
The post Move Over Smart Rings. MIT’s New Fabric Computer Is Stitched Into Your Clothes. appeared first on SingularityHub.
* This article was originally published at Singularity Hub
0 Comments