Shaking up the worlds of Sport & Healthcare
Innovation
Body Mapping
Deformation pressure sensing

Shaking up the worlds of Sport & Healthcare

Dr Dinghuang Zhang from the University of Portsmouth describes how his research into three-dimensional ground reaction forces is already rewriting the rules. 

The ability to accurately measure the way someone moves has been something of a holy grail for those working in sport and healthcare. The ability to accurately measure how someone moves would revolutionise training for athletes and rehabilitation for those less mobile. But historically, the technology they’ve had at their disposal just hasn’t been up to the task. 

That could be about to change. Dr Dinghuang Zhang,  knowledge transfer programme (KTP) associate at TG0 and the University of Portsmouth has been developing a way to measure three-dimensional ground reaction forces (GRFs) using TG0’s smart insole and embedded artificial intelligence (AI). The research is being funded by Innovate UK. 

It’s been going well so far. Just six months into the 2.5 year project, and the team is already achieving estimating 3-dimensional GRFs with 95% accuracy, Zhang says. “The advantage of TG0’s insole is it provides us with pressure data with higher resolution of the whole foot, and the direction and acceleration of the foot when moving.” He has submitted his preliminary findings to the Intelligent Sports and Health Journal for peer review. 

Historically, sport scientists and healthcare professionals would need to use a force plate or treadmill to measure GRF. Both are highly inflexible, expensive and disruptive to natural gait patterns. “If our insole can provide a similar result and can be embedded into any shoe, it’s a huge revolution for the industry,” Zhang adds. 

Working with the University of Portsmouth and TG0, Zhang has been able to collect and synchronise the data between TG0’s smart insole and the university’s force plate. It’s the first time two inputs have been used to capture detailed pressure distributions across the foot and dynamic movement parameters. 

The research study’s participants have been asked to perform a group of movements including jumping, running in place, walking in place, swaying, and squatting, with inputs collected from both the insole and the force plate. Once the AI model has been trained to map the relationship between the two, the force plate will be unnecessary. 

It’s just the beginning but the progress is promising. “At this stage, we are only focusing on predicting the 3-D GRF between a foot and the ground, and refining the experiment scenarios,” Zhang explains. “So far, we’ve only included six behaviours and that’s not enough. We are also planning to pick a foot movement from sports such as baseball or golf, and to use that behaviour to enrich our dataset. If we can achieve that higher accuracy, it will surpass anything else on the market.”  

Zhang believes there are other possibilities to use this research to expand the use of embedded AI into healthcare in the future. “Once we have the framework and platform, we may be able to choose another device or scenario. In the future, we hope to select a foot condition that is measurable via the 3-D GRF of the foot or gait, so the smart insole can be used as a medical aid. There are real benefits to developing a portable and easily accessible solution for continuous monitoring in everyday settings.” This would be good for privacy too – all of the data processing happens on small modules, embedded within the device, meaning that it doesn’t need to be stored or uploaded to the cloud.

The research is still in its early stages but its future potential is extensive. It’s an opportunity to advance wearable tech, personalised training and biomechanics across the board.