The development of automated systems that track occupants and adapt themselves to their preferences is an important next step in the future of smart homes. For example, when you walk into a room, the system can be set to your preferred temperature. Or when you are sitting on the sofa, the system can instantly flick the TV to your favorite channel.
However, when the occupants move in the room, the home system identification is a more complicated problem. Recently, systems have been established to locate humans by measuring the reflection of wireless signals leaving the body. But these systems cannot identify individuals. The system can recognize people, but only if they always carry mobile devices. Both systems also rely on tracking signals that may be weak or blocked by various structures.
Researchers at the Massachusetts Institute of Technology have established a system to identify occupants, even if they do not carry a mobile device, they can move towards a fully automated smart home. This system is called Duet and uses reflected wireless signals to locate individuals. But it also contains some algorithms that can predict nearby mobile devices based on the person who used the device last time and its predicted movement trajectory to predict the identity of an individual. It also uses logic to determine who is who, even in areas where the signal is rejected.
"Smart homes are still based on explicit input from apps or telling Alexa to do something. Ideally, we want the family to be more responsive and adaptable to our work." MIT Computer Science and Artificial Intelligence Laboratory ( CSAIL) PhD student Deepak Vasisht said,
But the system is not just novel. Duet may be used to identify intruders or to ensure that visitors do not enter the private areas of your home. In addition, Vasisht said, the system can capture behavioral analysis insights for healthcare applications. For example, people with depression may move more or less, depending on how they feel on any given day. This information collected over time may be valuable for monitoring and treatment.
The researchers envision that their system will be used with the explicit consent of anyone who will be identified and tracked by Duet. Vasisht added that if needed, they can also develop an application for users to grant or revoke Duet's access to their location information at any time.
Tracking and identification
Duet is a wireless sensor mounted on the wall, about one and a half square feet. It contains a floor map with annotated areas such as bedroom, kitchen, bed and living room sofa. It also collects identification tags from the occupant's phone.
The system is based on a device-based positioning system built by Vasisht, Katabi and other researchers, which tracks individuals within tens of centimeters based on the reflection of wireless signals from their devices. It uses the central node to calculate the time it takes for the signal to hit the person's device and return. In experiments, the system was able to determine the location of people in two-bedroom apartments and cafes.
However, the system relies on the person carrying the mobile device. "But when we built [Duet], we realized that you don't always carry your phone with you at home," Vasisht said. "Most people put the equipment on the table or table, and then walk around the house."
The researchers combined their device-based positioning with a deviceless tracking system called WiTrack developed by Katabi and other CSAIL researchers to locate people by measuring the reflections of wireless signals from the human body.
Duet locates the smartphone and associates its actions with personal actions captured without device localization. If both are moving in closely related trajectories, the system pairs the device with the individual and therefore knows the identity of the individual.
To ensure that Duet knows the identity of someone when they leave their device, the researchers designed the system to capture the power distribution of the signal received from the mobile phone while in use. The contour changes according to the direction of the signal, and the change is mapped to the individual's trajectory to identify them.
logical thinking
The last problem is that structures such as bathroom tiles, TV screens, mirrors and various metal devices may block the signal.
To compensate for this, the researchers used probabilistic algorithms to apply logical reasoning to localization. To this end, they designed a system to identify the entrance and exit boundaries of specific spaces in the home, such as the door of each room, the side of the bed and the side of the sofa. At any time, the system will identify the most likely identity of everyone in each boundary. Then infer who is who through the elimination process.
"There are blind spots in the family and the system cannot work. But because you have a logical framework, you can make these inferences," Vasisht said.
Next, the researchers' goal is to deploy Duet in more spaces for a long time, and provide advanced analysis services for applications such as health monitoring and responsive smart homes.
Travel Charger Adapter is convenience for these people who always travel in many countries. Desktop Power Adapter have normal DC connector for your need, and wall power adapter have mutil plug, like US/UK/AU/EU etc. We also can produce the item according to your specific requirement. The material of this product is PC+ABS. All condition of our product is 100% brand new.
Our products built with input/output overvoltage protection, input/output overcurrent protection, over temperature protection, over power protection and short circuit protection. You can send more details of this product, so that we can offer best service to you!
Travel Charger Adapter,Portable Travel Charger Adapter,Mini Travel Charger Adapter,Travel Charger Supply
Shenzhen Waweis Technology Co., Ltd. , https://www.laptopsasdapter.com