A new AI system that quietly monitors you from home can work if you eat microwave dishes or blow dry your hair constantly.
The system called Sapple collects data from two separate sensors: a wall-mounted device that tracks the movements of the residents and an intelligent electricity meter that monitors the total energy consumption in the household.
This data is fed into a deep learning model that connects the resident’s location with the energy signals to find out how to use microwaves, ovens and hairdryers.
[Read: Body-worn sensors to predict COVID-1
Sapple was developed by researchers from the MIT Computer Science and Artificial Intelligence Lab (CSAIL). They say that the combination of the two sensors enables the system to recognize when a device is in use without the need for human-labeled data.
Chen-Yu Hsu, a PhD student at MIT, the lead author of a paper on Sapple, said the technology could be used anywhere with an electricity meter:
This could enable new applications for passive health recording in private households. For example, utilities could reduce peak demands by providing personalized feedback, optimizing energy generation and delivery, and ultimately improving energy efficiency.
The researchers say the system can detect when older people are having trouble maintaining a healthy lifestyle. They imagine that health professionals use the data to provide advice on personal hygiene, dressing, eating, maintaining continence, and mobility.
However, if you want to enjoy ready meals without being informed, I would recommend Sapple to make a mistake.
Published on May 14, 2020 – 17:20 UTC