TY - GEN
T1 - Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model
AU - Soltanaghaei, Elahe
AU - Sharma, Rahul Anand
AU - Wang, Zehao
AU - Chittilappilly, Adarsh
AU - Luong, Anh
AU - Giler, Eric
AU - Hall, Katie
AU - Elias, Steve
AU - Rowe, Anthony
N1 - Funding Information:
This work was funded in part by ARPA-E grant DE-AR0000932. We thank our shepherd and the anonymous reviewers for their valuable feedback.
Publisher Copyright:
© 2020 ACM.
PY - 2020/11/18
Y1 - 2020/11/18
N2 - The ubiquity of WiFi devices combined with the ability to cover large areas, pass through walls, and detect subtle motions makes WiFi signals an ideal medium for sensing occupancy. While extremely promising, existing WiFi sensing solutions have not been rigorously tested outside of lab environments and don't often consider real-world constraints associated with non-expert installers, cost-effective platforms and long-term changes in the environment. This paper presents M-WiFi, a user-in-the-loop self-tuning framework for WiFi-based human presence detection with on-device learning and domain adaption capabilities that operates entirely on an embedded platform. M-WiFi robustly detects human presence by separating human-specific disturbances on WiFi signals from those of static objects, moving furniture or even pets. The high-level features of human presence are captured in an initial generalized classification model which adapts over time to a new building by selectively asking users to annotate a small number of critical time periods. We evaluate M-WiFi in 7 different houses, for a total of 100 days, with a mixture of pets and including periods of sleep and stationary activities. We show that our domain adaptive model can detect the human presence with an average accuracy of 90% in a completely new house after only 3 days of self-tuning and rapidly reaches a steady-state performance of 98% in long-term operations.
AB - The ubiquity of WiFi devices combined with the ability to cover large areas, pass through walls, and detect subtle motions makes WiFi signals an ideal medium for sensing occupancy. While extremely promising, existing WiFi sensing solutions have not been rigorously tested outside of lab environments and don't often consider real-world constraints associated with non-expert installers, cost-effective platforms and long-term changes in the environment. This paper presents M-WiFi, a user-in-the-loop self-tuning framework for WiFi-based human presence detection with on-device learning and domain adaption capabilities that operates entirely on an embedded platform. M-WiFi robustly detects human presence by separating human-specific disturbances on WiFi signals from those of static objects, moving furniture or even pets. The high-level features of human presence are captured in an initial generalized classification model which adapts over time to a new building by selectively asking users to annotate a small number of critical time periods. We evaluate M-WiFi in 7 different houses, for a total of 100 days, with a mixture of pets and including periods of sleep and stationary activities. We show that our domain adaptive model can detect the human presence with an average accuracy of 90% in a completely new house after only 3 days of self-tuning and rapidly reaches a steady-state performance of 98% in long-term operations.
KW - CSI
KW - human sensing
KW - multipath propagation
KW - WiFi
UR - http://www.scopus.com/inward/record.url?scp=85097172680&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097172680&partnerID=8YFLogxK
U2 - 10.1145/3408308.3427983
DO - 10.1145/3408308.3427983
M3 - Conference contribution
AN - SCOPUS:85097172680
T3 - BuildSys 2020 - Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
SP - 150
EP - 159
BT - BuildSys 2020 - Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
PB - Association for Computing Machinery
T2 - 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2020
Y2 - 18 November 2020 through 20 November 2020
ER -