NC State Researchers Use Machine Learning To Create a Fabric-Based Touch Sensor
Wearable technology is becoming increasingly popular. New functions are added to clothing every day. One of the latest innovations in this field comes from researchers at NC State University, who have combined three-dimensional embroidery techniques with machine learning to create a fabric-based sensor that can control electronic devices through touch.
The device is woven into clothing material. It functions like a button. This button can activate and control electronic devices, including mobile apps. This means that users can control their devices entirely by touch, without the need for buttons or screens.
The Technology Behind the Sensor
The fabric-based sensor consists of two components. The first part is an embroidered pressure sensor. The second part is a microchip. The pressure sensor is triboelectric, meaning it generates its own electric charge through friction between its layers. This fabric is created using two types of yarn. Each yarn has a different triboelectric material. One is positively charged, and the other is negatively charged. These yarns are woven into regular fabrics using embroidery machines.
Rong Yin, corresponding author of the study, explained: “Because the pressure sensor is triboelectric, it needed to have two layers with a gap in between them. That gap was one of the difficult parts in the process, because we are using embroidery which is usually two-dimensional. By using a spacer, we were able to control the gap between the two layers which lets us control the sensor’s output.”
The pressure sensor collects data and sends it to the microchip. This microchip uses machine learning algorithms to understand the input. It then controls connected devices based on this understanding. This is crucial in ensuring that the device can differentiate between different gestures and disregard any unintentional inputs from normal cloth movements.
Potential Applications
The researchers demonstrated the capabilities of their fabric-based sensor by developing a simple music playing mobile app that connected to the sensor via Bluetooth. Six different gestures were assigned to various functions, including play/pause, next song, last song, volume up, volume down, and mute. The device was also able to perform other tasks such as setting and inputting passwords and controlling video games.
While this technology is still in its early stages, it has great potential for use in wearable electronics. However, current embroidery technology is not yet capable of handling the materials used in creating this sensor. Nonetheless, it represents another exciting development in the world of wearable technology and is sure to continue generating interest and advancements in the future.
Refereces
- https://www.textileworld.com/textile-world/nonwovens-technical-textiles/2024/04/nc-state-researchers-use-machine-learning-to-create-a-fabric-based-touch-sensor/
- https://www.cell.com/device/fulltext/S2666-9986(24)00162-5
Thanks for reading!
Check out ENTECH magazine at entechonline.com for articles by experienced professionals, innovators, and researchers.
