MIT's new AI can track people through walls — Here's what that means for healthcare

A team of researchers from the Massachusetts Institute of Technology in Cambridge created RF-Pose, a wireless smart-home system that uses artificial intelligence to sense people's movements through walls. 

The team used a neural network to analyze how radio signals bounce off people's bodies — even when they're on the opposite side of a wall. During a recent research study, the neural network was able to successfully extrapolate these findings to sense a subject's postures and movements.

The researchers are working with physicians to investigate possible healthcare applications for RF-Pose. One idea is to use the AI system to monitor patients with conditions like Parkinson's or multiple sclerosis. The goal would be to help physicians understand disease progression, without requiring a patient to wear a sensor.

"We've seen that monitoring patients' walking speed and ability to do basic activities on their own gives healthcare providers a window into their lives that they didn't have before, which could be meaningful for a whole range of diseases," Dina Katabi, PhD, team leader and professor in MIT's Computer Science and Artificial Intelligence Laboratory, said in a June 12 statement.

The researchers said they plan to implement a consent mechanism for RF-Pose before deploying any "real-world" applications. These mechanisms would likely require a participant to perform a specific set of movements prior to the system monitoring the environment.

More articles on artificial intelligence:
The 4 types of AI Google says it won't develop
The simple reason MIT researchers created Norman, the 'world's 1st psychopath AI'
81% of healthcare execs say they're not prepared for potential social, liability issues of AI

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months