Abstract | ||
---|---|---|
People spend the majority of their time indoors, and human indoor activities are strongly correlated with the rooms they are in. Room localization, which identifies the room a person or mobile phone is in, provides a powerful tool for characterizing human indoor activities and helping address challenges in public health, productivity, building management, etc. Existing room localization methods, however, require labor-intensive manual annotation of individual rooms. We present ARIEL, a room localization system that automatically learns room fingerprints based on occupants' indoor movements. ARIEL consists of (1) a zone-based clustering algorithm that accurately identifies in-room occupancy "hotspot(s)" using Wi-Fi signatures; (2) a motion-based clustering algorithm to identify inter-zone correlation, thereby distinguishing different rooms; and (3) an energy-efficient motion detection algorithm to minimize the noise of Wi-Fi signatures. ARIEL has been implemented and deployed for real-world testing with 21 users over a 10-month period. Our studies show that it supports room localization with higher than 95% accuracy without requiring labor-intensive manual annotation. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2370216.2370282 | UbiComp |
Keywords | Field | DocType |
room localization system,human indoor activity,wi-fi signature,room localization,energy-efficient motion detection algorithm,different room,automatic wi-fi,indoor localization,room fingerprint,labor-intensive manual annotation,individual room,existing room localization method,sensor networks,scheduling,localization | Motion detection,Computer science,Scheduling (computing),Real-time computing,Building management,Occupancy,Mobile phone,Cluster analysis,Hotspot (Wi-Fi),Wireless sensor network | Conference |
Citations | PageRank | References |
71 | 2.69 | 18 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yifei Jiang | 1 | 279 | 22.14 |
Xin Pan | 2 | 120 | 4.57 |
Kun Li | 3 | 230 | 18.70 |
Lv Qin | 4 | 1116 | 91.95 |
Robert P. Dick | 5 | 3130 | 180.88 |
Michael Hannigan | 6 | 183 | 11.32 |
Li Shang | 7 | 1311 | 89.75 |