Tracking people’s activities and health conditions at smart homes using radio reflections and big data
The goal of this research is to develop a living activity and health condition monitoring and analyzing system in a smart home. This system can identify human activities, such as walking, dining, and sleeping, by collecting radio signals reflected by RFID tags that are widely attached to household appliances and furniture in the smart home, without requiring any special devices worn by a human. By using big data technology to extract unique patterns of activities, it can quickly report emergent events, like sudden illness, elder falling, fire, and intruders. By analyzing long-term human-activities, this system can monitor human health condition and discover latent disease. Furthermore, this system can share the identified human activity and associated patterns with other smart devices in the smart home, so that they can collaborate to provide a healthy, convenient, energy-efficient and safe living condition.
Identification of the humans’ location
As the first-step of living activity tracking, identification of human location is important and provides the most fundamental information about the living activity. The body reflection has the significant impact on the RSSI (Radio Signal Strength Indicator) values received by the COTS (commercial off-the-shelf) Impinj R420 reader. Hence, it is relatively easy to recognize whether a person is in a specific room. The accuracy of human identification is no less than 90%.
Device-free identification of the humans
We can distinguish people living in the same environment without requiring them to wear any special devices. By identifying different people in a family, we can track personal activities, and provide corresponding services. The accuracy of human localization is no less than 90%.