PlasticArmPit: How Arm and PragmatIC are developing an e-nose that will sniff out your body odour
An intelligent ‘e-nose’ that could be embedded in clothing and provoke a helpful spray of deodorant if the wearer began to sweat is being developed by Arm with the help of fellow Cambridge technology company PragmatIC.
The brilliantly-named PlasticArmPit could also be embedded in packaging to sniff out food that has gone off, or smart bandages to provide crucial early indicators of infection.
Arm’s smart chips will be made from very thin sheets of plastic and will feature eight sensors and a machine learning (ML) circuit.
James Myers, director of devices and circuits research at the Fulbourn-based chip giant, said: “The team’s initial proof of concept will be a flexible plastic clothing insert, capable of monitoring a wearers’ odor levels.
“Should an unexpected run for the bus or particularly tense business meeting result in elevated body odor, this ML-powered wingman could politely encourage the wearer to take a shower – or at least temporarily mask the smell with a deodorant veneer. This is the first step and once proven, the application could be taken in any direction – food being another prime candidate.”
To be viable, Arm needed a super low-cost microcontroller that could be embedded in billions of cheap products. It also needed to be small but robust enough to survive environmental challenges - such as going in the wash.
Step forward PragmatIC, the Cambridge Science Park-based leader in ultra low cost flexible electronics. Its integrated circuits are thinner than a human hair and can be embedded easily in everyday objects in ways that would be impossible for traditional silicon chips.
The project is also supported by Unilever, which is looking to develop consumer applications, the University of Manchester, which has expertise in printed organic field-effect transistors (OFET) and UK funding body Innovate UK.
“Plastic is far cheaper than silicon yet has its trade-offs; silicon chips fit billions of transistors, while the largest published designs for plastic run to just thousands,” said James. “For silicon designers, this is like time-travelling back to the 1970s – so designs needed to make the most of every transistor. The only way to do this, currently, is to make chips non-programmable, with a common base design customized to suit each specific purpose.
“However, our design approach now is to give these chips the ability to run neural networks and machine learning (ML) algorithms, trained offline and uploaded to the device.
“We think this will be the key to accelerate development of low-cost flexible, integrated smart systems that are customized for a specific application.
“ProjectArmPit will be the first application of ML data in a flexible smart device.”
With sensors in packaging detecting a smell or chemical, enabling a consumer to see if food has gone off, the traditional use-by date might be, well, past its use-by date.
And with 46,000 dying annually from sepsis or injury after minor infection, embedding the technology in bandages to give an indication of infection could prove to be a lifesaver.
“Wide adoption of flexible IC technology in packaging could even pave the way for smart recycling centers, enabling automatic sorting of various plastics and reduced contamination,” added James.
“What began with body odor is now growing rapidly as we discover ways to combine the new fields of ML and flexible integrated circuits.”
Amazing what you can achieve with a bit of sweat.
Read more
