Machine learning allows self-powered fabric to correct posture
An important element of health is posture. Pain and discomfort can result from long-term bad posture, such as slouching or slumping to one side. Additionally, it has been shown to increase the chance of cardiovascular disease, vision issues, strokes, and musculoskeletal diseases. To avoid these issues and enhance the health of students and those in sedentary occupations, solutions are required to assist individuals in correcting their posture. The drawbacks of the available monitoring technologies have hindered their general adoption. Researchers have created a comfortable, long-lasting self-powered fabric that can be combined with sensors to help correct posture in real-time to address this issue.
Triboelectric nanogenerators (TENGs), which utilize movement to harvest the energy required to power the posture monitoring sensors, were used to create the self-powered fabric. An integrated machine learning algorithm analyzes the information gathered by the sensors and can deliver immediate feedback, informing the user when they need to modify their posture.
The technology was described in a paper recently published in Nano Research.
“People often sit in various poor postures in their daily life, leading to pain and discomfort,” said paper author Kai Dong, an associate researcher at the Beijing Institute of Nanoenergy and Nanosystems at the Chinese Academy of Sciences. “This ‘sitting disease’ could be alleviated if individuals were able to observe their real-time sitting posture by wearing a specific type of clothing made with smart textiles. With the self-powered sitting position monitoring vest we developed, users can watch their posture change on their screen and make necessary adjustments.”
The unusual fabric is made by knitting together a nylon fiber and a conductive fiber. The fabric’s fibers are stretched and compressed when the user moves. The constant movement and contact of the two fibers generate electricity, a phenomenon known as contact electrification.
The fabric stretches easily, is durable, washable, and breathable, and can be worn comfortably for long periods of time. This makes it ideal for long-term posture monitoring. According to the paper author Zhong Lin Wang, the Hightower Chair of the School of Materials Science and Engineering and the Regents’ Professor at the Georgia Institute of Technology in the United States, factors like durability and comfort are important for how people use smart textiles.
“The flexibility, stretchability, and bending ability all impact the comfort of the wearable sensors,” Wang said. “But these factors also affect how well the fabric works. The fabric exhibits good stretchability due to its knitting structure, which also increases its output and produces a higher voltage.”
In addition to the comfort of the fabric, another important aspect is the reliability of the posture monitoring. The sensors are stitched directly into the fabric in positions along the cervical spine, thoracic spine, and lumbar spine. These positions help collect data on the most common slouching positions, like humpback posture. The data that is collected by the sensors is then interpreted by a machine learning algorithm, which processes information about how the wearer is sitting, classifies their sitting position, and monitors how they correct their posture when prompted. This system is able to accurately recognize the wearer’s posture 96.6% of the time.
With this combination of wearability and precision, researchers hope this self-powered monitoring vest will help students and people with sedentary jobs avoid pain, discomfort, and long-term health problems. “We believe the TENG-based self-powered monitoring vest offers a reliable healthcare solution for long-term, non-invasive monitoring,” said Dong. “This also widens the application of triboelectric-based wearable electronics.”
The study was funded by the National Key Research and Development Program of China, the National Natural Science Foundation of China, the Natural Science Foundation of the Beijing Municipality, and the Fundamental Research Funds for the Central Universities.
Reference: “Knitted self-powered sensing textiles for machine learning-assisted sitting posture monitoring and correction” by Yang Jiang, Jie An, Fei Liang, Guoyu Zuo, Jia Yi, Chuan Ning, Hong Zhang, Kai Dong and Zhong Lin Wang, 24 May 2022, Nano Research.
DOI: 10.1007/s12274-022-4409-0