File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TMC.2019.2939791
- Scopus: eid_2-s2.0-85097736097
- WOS: WOS:000597149600013
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Smars: Sleep monitoring via ambient radio signals
Title | Smars: Sleep monitoring via ambient radio signals |
---|---|
Authors | |
Keywords | radio signals vital signs monitoring WiFi sensing Breathing estimation signal processing maximal ratio combining sleep monitoring |
Issue Date | 2021 |
Citation | IEEE Transactions on Mobile Computing, 2021, v. 20, n. 1, p. 217-231 How to Cite? |
Abstract | We present the model, design, and implementation of SMARS, the first practical Sleep Monitoring system that exploits Ambient Radio Signals to recognize sleep stages and assess sleep quality. This will enable a future smart home that monitors daily sleep in a ubiquitous, non-invasive and contactless manner, without instrumenting the subject's body or the bed. The key enabler underlying SMARS is a statistical model that accounts for all reflecting and scattering multipaths, allowing highly accurate and instantaneous breathing estimation with best-ever performance achieved on commodity devices. On this basis, SMARS then recognizes different sleep stages, including wake, rapid eye movement (REM), and non-REM (NREM), which was previously only possible with dedicated hardware. We implement a real-time system on commercial WiFi chipsets and deploy it in 6 homes, resulting in 32 nights of data in total. Our results demonstrate that SMARS yields a median absolute error of 0.47 breaths per minute (BPM) and a 95 percent-tile error of only 2.92 BPM for breathing estimation, and detects breathing robustly even when a person is 10 meters away from the link, or behind a wall. SMARS achieves a sleep staging accuracy of 88 percent, outperforming the prevalent unobtrusive commodity solutions using bed sensor or UWB radar. The performance is also validated upon a public sleep dataset of 20 patients. By achieving promising results with merely a single commodity RF link, we believe that SMARS will set the stage for a practical in-home sleep monitoring solution. |
Persistent Identifier | http://hdl.handle.net/10722/303718 |
ISSN | 2023 Impact Factor: 7.7 2023 SCImago Journal Rankings: 2.755 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Feng | - |
dc.contributor.author | Wu, Chenshu | - |
dc.contributor.author | Wang, Beibei | - |
dc.contributor.author | Wu, Min | - |
dc.contributor.author | Bugos, Daniel | - |
dc.contributor.author | Zhang, Hangfang | - |
dc.contributor.author | Liu, K. J.Ray | - |
dc.date.accessioned | 2021-09-15T08:25:53Z | - |
dc.date.available | 2021-09-15T08:25:53Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Mobile Computing, 2021, v. 20, n. 1, p. 217-231 | - |
dc.identifier.issn | 1536-1233 | - |
dc.identifier.uri | http://hdl.handle.net/10722/303718 | - |
dc.description.abstract | We present the model, design, and implementation of SMARS, the first practical Sleep Monitoring system that exploits Ambient Radio Signals to recognize sleep stages and assess sleep quality. This will enable a future smart home that monitors daily sleep in a ubiquitous, non-invasive and contactless manner, without instrumenting the subject's body or the bed. The key enabler underlying SMARS is a statistical model that accounts for all reflecting and scattering multipaths, allowing highly accurate and instantaneous breathing estimation with best-ever performance achieved on commodity devices. On this basis, SMARS then recognizes different sleep stages, including wake, rapid eye movement (REM), and non-REM (NREM), which was previously only possible with dedicated hardware. We implement a real-time system on commercial WiFi chipsets and deploy it in 6 homes, resulting in 32 nights of data in total. Our results demonstrate that SMARS yields a median absolute error of 0.47 breaths per minute (BPM) and a 95 percent-tile error of only 2.92 BPM for breathing estimation, and detects breathing robustly even when a person is 10 meters away from the link, or behind a wall. SMARS achieves a sleep staging accuracy of 88 percent, outperforming the prevalent unobtrusive commodity solutions using bed sensor or UWB radar. The performance is also validated upon a public sleep dataset of 20 patients. By achieving promising results with merely a single commodity RF link, we believe that SMARS will set the stage for a practical in-home sleep monitoring solution. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Mobile Computing | - |
dc.subject | radio signals | - |
dc.subject | vital signs monitoring | - |
dc.subject | WiFi sensing | - |
dc.subject | Breathing estimation | - |
dc.subject | signal processing | - |
dc.subject | maximal ratio combining | - |
dc.subject | sleep monitoring | - |
dc.title | Smars: Sleep monitoring via ambient radio signals | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TMC.2019.2939791 | - |
dc.identifier.scopus | eid_2-s2.0-85097736097 | - |
dc.identifier.volume | 20 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | 217 | - |
dc.identifier.epage | 231 | - |
dc.identifier.eissn | 1558-0660 | - |
dc.identifier.isi | WOS:000597149600013 | - |