Loose Clothing Sensors Track Movement 40% More Accurately Than Tight Wearables
Loose clothing sensors track movement 40% more accurately and use 80% less data than tight wearables, per a King's College London study in Nature Communications.
New research from King's College London, published in the journal Nature Communications, has found that measuring human movement with tracking devices on looser clothing is more accurate than on tight body suits or straps. Loose fabric can predict and capture the body's movements with 40 percent more accuracy and using 80 percent less data than if a sensor were stuck to the skin.
The findings challenge the common belief that if a sensor is loose, the data will be "noisy" or messy. The research proved over multiple experiments that loose, flowing clothing actually makes motion tracking significantly more accurate. Loose fabric acts like a "mechanical amplifier," meaning movement is easier to detect. When a person starts to move their arm, a loose sleeve doesn't just sit there; it folds, billows, and shifts in complex ways, reacting more sensitively to the movements than a tighter fitting sensor.
Scientists tested sensors on a wide range of different fabrics with human and robot subjects undertaking a variety of movements. They compared the findings from loose fabrics with standard motion sensors attached to straps and tight clothing and found that every time the fabric-based approach detected movements more quickly, more accurately, and needed less movement data to make predictions. Sensor accuracy was not affected by its location in the clothes or the distance from where the fabric touches the body. Looser fabric was also able to distinguish between very similar or subtle, barely detectable movements.
The approach could help sense small movements that current wearables often miss, such as Parkinson's tremors. Through this approach, researchers could "amplify" people's movement, helping capture them even when they are smaller than typical abled-bodied movements. This could allow tracking people in the comfort of their own homes or a care home, in their everyday clothing, by adding sensors to buttons on shirts. It could become easier for doctors to monitor their patients, as well as medical researchers to gather vital data needed to inform understanding of these conditions and develop new therapies, including wearable technologies that cater for these kinds of disabilities.
The discovery could mark a potential breakthrough for a range of technologies, including improving accuracy on personal health devices such as Fitbits and smart watches, enhancing motion capture for CGI movie characters, and transforming the field of robotics research as well as automated technologies that use gesture-based control. A co-author and reader in engineering at King's College London said the research offers the possibility of attaching discreet sensors to everyday clothing, so researchers can start to collect internet-scale human behavior data needed to revolutionize the field of robotics.
Current wearables have proven useful for measuring steps and movement during exercise; however, they have limitations in clinical metrics, such as heart rate variability, blood pressure, and oxygen levels. Recent research has found that wearables such as Apple Watches accurately measure heartbeats at rest; however, they show inconsistency and large errors in measuring energy expenditure, especially during activity.