Knee-related conditions such as osteoarthritis and rheumatoid arthritis significantly impact mobility and also increase susceptibility to injuries, creating a cycle that leads to chronic pain, reduced function, and long-term disability. Now researchers have come up with an AI-powered wearable to analyse complex dynamic motion signals of the knee joint for accurate torque monitoring.

The researchers are affiliated to the University of Oxford, University College London, and Xi'an Jiaotong University in China and their paper,  AI-Enabled Piezoelectric Wearable for Joint Torque Monitoring is included in the May 2025 issue of Nano-Micro Letters.

The starting point for their project was that:

"Monitoring of joint torque can offer an important pathway for the evaluation of joint health and guided intervention. However, there is no technology that can provide the precision, effectiveness, low-resource setting, and long-term wearability to simultaneously achieve both rapid and accurate joint torque measurement to enable risk assessment of joint injury and long-term monitoring of joint rehabilitation in wider environments."

In response, using an Arduino Nano 33 BLE on a STMicroelectronics STM32 NUCLEO F401RE development board, they designed a flexible, soft, and lightweight wearable torque sensor based on boron nitride nanotubes (BNNTs) on a polydimethylsiloxane (PDMS) substrate, which uses the peizoelectric effect to analyze data about the wearer's knee movements while at the same time providing the power required for the device to operate.

The device employs a lightweight artificial neural network (ANN) algorithm to analyse complex dynamic motion signals of the knee joint for accurate torque monitoring and to perform the consequent effective risk assessment.

According to the researchers:

This technology offers a sustainable solution for long-term joint health monitoring, making it particularly suited for resource-constrained environments, where established healthcare, energy and computational infrastructures are not commonly available. 

All the code for this work is to be open accessed on GitHub allowing others to make this a reality.

• Harry Fairhead, I-Programmer's hardware guru, is the author of books about many popular IoT devices including Programming the ESP32 in C Using the Arduino Library and  Programming The Raspberry Pi Pico/W In C, 3rd Ed.

More Information

AI-Enabled Piezoelectric Wearable for Joint Torque Monitoring
by Jinke Chang, Jinchen Li, Jiahao Ye, Bowen Zhang, Jianan Chen, Yunjia Xia, Jingyu Lei, Tom Carlson, Rui Loureiro, Alexander M. Korsunsky, Jin-Chong Tan & Hubin Zhao

Related Articles

Magnetic Core Memory For Arduino

There's an Arduino for that!

Top 10 Projects From Arduino Community Day

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info