IIIT Hyderabad researchers create AI-embedded sensor to help with physiotherapy
Published 20 March 2021
Processes, Architecture and Technologies Research in IoT (PATRIoT) researchers from The International Institute of Information Technology, Hyderabad (IIIT) have created a low-cost flexible sensor with an AI algorithm that will help to keep a check on the performance and progress of the patients who come in for physiotherapy.
Physiotherapy is to restore the physical strength in people who have arthritis and muscle weakness.
One of the main exercises that is prescribed is the movement of the hands and placing an object from one point to the other. The researchers at PATRIot came up with the idea of creating a pressure sensor which could analyze and recognize such activities but they also made sure that the device is low cost and low weight, said the institution in a blog post.
“In this case, apart from the typical smart properties of sensors, we also wanted to cover a large area and try to map the pressure distribution in the entire area,” said Dr. Aftab Hussain, Principal investigator of the lab.
For this experiment, they placed a sensory mat that contained designated areas for placing weights. The conductive foam was their main ingredient which was fabricated with a layer of paper on the top and bottom with the copper electrodes in between. Every time the foam is touched by the patient with the pressure there is a resistance which can be detected via the external circuit. Added the blog post.
Image Credit: IIIT Hyderabad
“We are looking if the value of resistance has changed. And if it has, then we try to interpret how much pressure has been applied and where,” explained Dr Aftab Hussain.
Instead of using a mathematical analysis to detect the change in resistance value, the researchers decided to train a machine learning model to do the job.
“In addition to tracking progress of patients in terms of accuracy of where they’re placing the load, one can also monitor time taken to place the load. So with this pressure sensor matrix, we can get both the speed and accuracy of the load positioning,” added Dr Hussain.
The team is also working to make the device cost effective.
Adding to this Dr Hussain said, “We are trying to see if we can manufacture conductive foam that makes the sensor pixels possible via synthetic organic chemistry. That will further reduce the costs but more importantly we’ll be able to tweak the properties of foam to better suit our applications and make them more reliable. In the longer term, technology can happen or a startup may evince interest.”