A Chip on Your Shoulder

A number of technological advances in recent years have led to the development of sensors that are small, and sometimes even flexible or stretchable. These sensors are ideal for use in wearable devices that collect continuous measurements of physiological parameters. Such on-body sensing systems have important applications in the medical field, where this type of data is typically collected only intermittently, and in clinical settings. Always-on wearable sensors have real potential to diagnose health problems long before they can be detected otherwise, leading to earlier initiation of treatment plans, and better long-term outcomes for patients. But before we get ahead of ourselves, we need to remember that sense is only one part of the equation.

After all, what good is sensor data without processing units that can receive and interpret it? These processing units also need to fit well on wearable platforms, which means they need to be small, flexible and stretchy. In order to run cutting-edge algorithms, these devices must be additionally powerful, but since they run on the power of a small, on-body battery, they must also be highly energy efficient. That’s quite a big ask, so it’s no wonder that processors that meet this description are extremely hard to come by. A collaboration between Argonne National Laboratory and the University of Chicago may one day help fill this gap, although the work is still in its early stages. They have developed a soft, stretchy, wearable neuromorphic computing chip that excels when running advanced machine learning algorithms, and slowly energy.

Also Read :  Acxiom Forecasts Top Five Customer Experience Trends for 2023

The chip is built on a thin plastic semiconductor film. Stretchable gold nanowire electrodes are deposited on the film. The chip can be stretched to twice its normal size without causing damage or reducing performance. Using this platform, the team created a number of transistors. The transistors were arranged to perform vector-matrix multiplications, which are a core component of operating a neural network. Importantly, this chip provides desirable neuromorphic metrics, including linear symmetric weight updates and good state retention, which are essential for high computational efficiency. The unit also appears to be durable, with the transistors proven to withstand more than 100 million state changes.

To test the real-world utility of the prototype chip, the researchers designed and built an implementation of a wearable heart monitor. They paired their neuromorphic processor with a sensor that picks up electrical signals from the heart. They trained the device to recognize the electrical signals characteristic of a healthy heart, as well as those of four pathological conditions. Tests revealed that their chip was 95% accurate in diagnosing the condition of the heart.

Also Read :  Everspin Vs. Micron: MRAM Better Than MU On A Few Key Metrics (MRAM) (MU)

The expansion of the Advanced Photon Source at Argonne National Laboratory greatly aided the team in developing their flexible plastic semiconductor film. The intense X-ray beam emitted by this machine shows in detail how the molecules that make up the material deform and reorganize when it is stretched far beyond its normal size. A planned upgrade to the Advanced Photon Source will boost the brightness of the beam it generates by 500 times, which the team believes will help them further refine their technology in the future.

The principal investigator in the study, Sihong Wang, acknowledged that the technology still “needs further development on several fronts.” However, looking ahead, he believes that “one day our device could be a game changer in which everyone can get their health status in a much more effective and frequent way.”


Leave a Reply

Your email address will not be published.

Related Articles

Back to top button