Massachusetts Institute of Technology (MIT) researchers have designed a system which can identify each person in the home space, to further provide personalized home automation experience.
Looking to the next stage of smart home, Massachusetts Institute of Technology (MIT) researchers have designed a system which can identify each person in the home space, to further provide personalized home automation experience.
Two tracking systems are used in the individual identification technology. The first one, called Duet, uses wireless sensors installed on a wall of 1.5 square feet. The system incorporates the floor map with annotated areas, such as the bedroom, kitchen and living room sofa. It identifies individuals based on their phone signals.
But most people don’t carry their phones at home all the time. The second system, called WiTrack, was therefore developed, to locate people by measuring the reflection of wireless signals from their bodies.
Let’s assume that an apartment has two people living in it: Peter and Melissa. When they arrive home, Duet recognizes their identifies and locations based on phone signals. Both of them leave their phones on a table to charge, while Melissa enters the room and Peter stays in the living room watching TV.
At this moment, Duet knows it’s Peter sitting in the couch in the living room for he sometimes checks his phone while watching TV. And by the process of elimination, the other person in the bedroom is Melissa.
Some house structures such as television screens, mirrors and various metal equipment block signals. Nonetheless, the logical framework mentioned above can overcome these barriers.
MIT researchers have tried their innovation in a two-bedroom apartment with four people and an office with nine people over two weeks. The result showed that the system can identify individuals with 96% and 94% accuracy, respectively, even if people didn’t carry their smartphones or stood in the blocked areas.
“Smart homes are still based on explicit input from apps or telling Alexa to do something. Ideally, we want homes to be more reactive to what we do, to adapt to us. If you enable location awareness and identification awareness for smart homes, you could do this automatically. Your home knows it’s you walking, and where you’re walking, and it can update itself,” said Deepak Vasisht, a PhD student in MIT’s Computer Science and Artificial Intelligence Laboratory and the lead author on a paper of the system, to MIT News.
By knowing who the person is at home right now, the smart home system can provide personalized experience and automated control, and immediately point out intruders in the house.
The MIT research team is looking to deploy the smart home system in more spaces and to provide high-level analytics services for health monitoring and responsive smart homes.