MIT Weaves Neural Networks Into Shirts, Creates First Of Its Kind Digital Fibre

Advertisement

MIT researchers have come out with a digital fabric. The fibre, embedded in a shirt, can detect, store, extract, analyse and communicate helpful information and data, including body temperature, physical activities etc. Till date, electronic fibres have been analog. “This work presents the first realisation of a fabric with the ability to store and process data digitally, adding a new information content dimension to textiles and allowing fabrics to be programmed literally,” Yoel Fink, the senior author on the study.

The research was carried out in close collaboration with the textile department at Rhode Island School of Design (RISD), led by Professor Anais Missakian. 

THE BELAMY

Sign up for your weekly dose of what's up in emerging technology.

The polymer fibre--created using hundreds of square silicon microscale digital chips– is thin and flexible enough to thread a needle, be sewn into fabrics, and withstand at least ten washes.

Image Credits: MIT

The digital fibre can hold a large amount of data in memory. The researchers were able to write, store, and read data on the fibre, including a full-colour short movie file of 767 kb and a 0.48 MB music file. The data can be stored for two months without power. The fibre has a neural network of around 1,650 connections. As part of the research, the digital fibre was stitched into the armpit portion of a participant’s shirt, and the digital garment took the body surface temperature for around 270 minutes. The digital fibre was able to discern what activity the person wearing it was involved in at 96 percent accuracy.

Analytics power, combined with fibre, holds potential for further applications: It can monitor real-time health issues such as a drop in oxygen level or pulse rate; respiratory issues warning; and AI-based apparel that can give athletes advice on how to improve their performance and limit their chance of injury (think Sensoria Fitness). Sensoria provides a full range of smart garments to provide real-time health and fitness data to improve performances. As the fibre is controlled with a small external device, the next step for the researchers will be to develop a microchip that can be embedded in the fibre itself.

Future of smart clothing

Recently, Nihaal Singh, a KJ Somaiya College of Engineering student, developed a Cov-tech ventilation system (to maintain the body temperature) for PPE kits for doctors. Smart clothing has entered the domains of sportswear, health wear and defence as well. Moreover, the global smart clothing/fabric market is expected to reach an annual size of more than $5 billion by 2024 or 2025. 

  • For Sportswear: Textile sensors are incorporated in clothes to provide accurate and continuous cardiac, respiratory, and activity monitoring. Daily activities, sleep, and health indicators are analysed and recorded. Take, for example, the smart clothing features from hexoskin. Similarly, insoles from ReTiSense can be used to track impact forces, push-off forces, ground contact time, and degree of overpronation, all of which will be analysed by the app that comes with it. 
  • For Healthcare: Sensors are embedded in smart clothing to detect a range of signals. The signals are then used to detect pressure, stretch, temperature, humidity, and even different compounds in the blood, such as glucose. Take Adrenalease as an example which provides adjustable elastic straps that run down under the armpit and connect together, gently drawing the shoulders back and putting the wearer in a position that relieves muscle stress.
  • For Defence: DRDO is building smart jackets in collaboration with Joint Advanced Technology Centre of IIT Delhi. A variety of sensors will be integrated into textiles. Signal processing chip, chemical sensor, communication chip, and other features will aid soldiers in mobility, threat detection, and communication.

The timeline to artificially intelligent fabrics is shortening. In future, such fabrics will use specially architected ML algorithms to find and gain new insights into underlying biological patterns, and help assess health markers in real time.

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

More Great AIM Stories

kumar Gandharv
Kumar Gandharv, PGD in English Journalism (IIMC, Delhi), is setting out on a journey as a tech Journalist at AIM. A keen observer of National and IR-related news.

Our Upcoming Events

Conference, in-person (Bangalore)
MachineCon 2022
24th Jun

Conference, Virtual
Deep Learning DevCon 2022
30th Jul

Conference, in-person (Bangalore)
Cypher 2022
21-23rd Sep

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM
MORE FROM AIM