Fiber medicine

MIT engineers create programmable digital fiber – with memory, sensors and AI

Researchers at MIT have created the first textile fiber with digital capabilities, ready to collect, store and analyze data using a neural network. Credit: Anna Gittelson. Photo by Roni Cnaani

First, the digital fiber contains memory, temperature sensors, and a trained neural network program to infer physical activity.

MIT researchers have created the first fiber with digital capabilities, capable of detecting, storing, analyzing and inferring activity after being sewn into a shirt.

Yoel Fink, who is a professor of materials science and electrical engineering, principal investigator of the Electronics Research Laboratory and lead author of the study, says that digital fibers expand the possibilities for tissues to discover the context of hidden patterns in the human body that could be used for physical performance monitoring, medical inference, and early disease detection.

Or, you could one day store your wedding music in the dress you wore on the big day – more on that later.

Fink and his colleagues describe the characteristics of digital fiber today (June 3, 2021) in Nature Communication. Until now, electronic fibers have been analog – carrying a continuous electrical signal – rather than digital, where discrete bits of information could be encoded and processed as 0s and 1s.

“This work presents the first realization of a fabric capable of storing and processing data digitally, adding a new dimension of information content to textiles and allowing fabrics to be literally programmed,” says Fink.

Gabriel Loke, PhD student at MIT, and Tural Khudiyev, postdoctoral fellow at MIT, are the main authors of the article. Other co-authors MIT postdoc Wei Yan; MIT undergraduates Brian Wang, Stephanie Fu, Ioannis Chatziveroglou, Syamantak Payra, Yorai Shaoul, Johnny Fung, and Itamar Chinn; John Joannopoulos, Francis Wright Davis Professor of Physics and Director of the Institute for Soldier Nanotechnologies at MIT; Pin-Wen Chou, master’s student at Harrisburg University of Science and Technology; Anna Gitelson-Kahn, Associate Professor at the Rhode Island School of Design, and Anais Missakian, Pevaroff-Cohn Family Chair in Textiles at RISD.

Memory and more

The new fiber was created by placing hundreds of square silicon digital microchips into a preform which was then used to create a polymer fiber. By precisely controlling the flow of polymer, the researchers were able to create a fiber with a continuous electrical connection between the chips over a length of several tens of meters.

The fiber itself is fine and flexible and can be threaded through a needle, sewn into fabrics, and washed at least 10 times without breaking down. According to Loke, “When you put it in a shirt, you don’t feel it at all. You wouldn’t know it was there.

Making a digital fiber “opens up different areas of opportunity and actually solves some of the problems of functional fibers,” he says.

For example, it provides a way to control individual elements in a fiber, from a point at the end of the fiber. “You can think of our fiber as a hallway, and the elements are like rooms, and they each have their own unique digital room number,” Loke explains. The research team came up with a method of digital addressing that allows them to “enable” an element’s functionality without activating all elements.

A digital fiber can also store a lot of information in memory. The researchers were able to write, store and read information on the fiber, including a 767 kilobit color short film and a 0.48 megabyte music file. Files can be stored for two months without power.

When they dreamed up “crazy ideas” for the fiber, Loke says, they thought of applications like a wedding dress that would store digital wedding music in the weave of its fabric, or even write down the story of creation. fiber in its components.

Fink notes that the research at MIT was in close collaboration with the textile department of RISD headed by Anais Missakian. Associate Professor Anna Gitelson-Kahn has incorporated digital fibers into a knitted garment sleeve, paving the way for the creation of the first digital garment.

artificial intelligence on the body

The fiber also takes a few steps forward towards artificial intelligence by integrating a neural network of 1,650 connections within the fiber’s memory. After sewing it around the armpit of a shirt, the researchers used the fiber to collect 270 minutes of surface body temperature data from a person wearing the shirt and analyze how that data correlated with different physical activities. . Trained on these data, the fiber was able to determine with 96% precision what activity the wearer was engaged in.

Adding an AI component to the fiber further increases its possibilities, the researchers say. Tissues with digital components can collect a lot of information from across the body over time, and this “lush data” is perfect for machine learning algorithms, Loke says.

“This kind of tissue could provide open source quantity and quality data to extract new body models that we didn’t know before,” he says.

With this analytical power, fibers could one day detect and alert people in real time to health changes like respiratory decline or irregular heartbeat, or provide muscle activation or heart rate data to athletes during training. .

The fiber is controlled by a small external device. The next step will therefore be to design a new chip as a microcontroller that can be connected inside the fiber itself.

“When we can do that, we can call it a fiber computer,” Loke says.

Reference: “Digital Electronics in Fibers Enable Tissue-Based Machine Learning Inference” by Gabriel Loke, Tural Khudiyev, Brian Wang, Stephanie Fu, Syamantak Payra, Yorai Shaoul, Johnny Fung, Ioannis Chatziveroglou, Pin- Wen Chou, Itamar Chinn, Wei Yan, Anna Gitelson-Kahn, John Joannopoulos and Yoel Fink, June 3, 2021, Nature Communication.
DOI: 10.1038/s41467-021-23628-5

This research was supported by the US Army Institute of Soldier Nanotechnology, National Science Foundation, US Army Research Office, MIT Sea Grant and Defense Threat Reduction Agency.