Abstract | ||
---|---|---|
Falling is a common health problem for more than a third of the United States population over 65. We are currently developing a Doppler radar based fall detection system that already has showed promising results. In this paper, we study the sensor positioning in the environment with respect to the subject. We investigate three sensor positions, floor, wall and ceiling of the room, in two experimental configurations. Within each system configuration, subjects performed falls towards or across the radar sensors. We collected 90 falls and 341 non falls for the first configuration and 126 falls and 817 non falls for the second one. Radar signature classification was performed using a SVM classifier. Fall detection performance was evaluated using the area under the ROC curves (AUCs) for each sensor deployment. We found that a fall is more likely to be detected if the subject is falling toward or away from the sensor and a ceiling Doppler radar is more reliable for fall detection than a wall mounted one. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/EMBC.2012.6345918 | EMBC |
Keywords | Field | DocType |
doppler radar based fall detection system,system configuration,roc curves,biomedical equipment,svm classifier,fall detection performance,health problem,sensor deployment,medical computing,radar signature classification,doppler radar,sensor placement,support vector machines,doppler radar sensor positioning,sensitivity analysis | Radar,Doppler radar,Population,Receiver operating characteristic,Computer science,Support vector machine,Remote sensing,System configuration,Ceiling (aeronautics),Radar cross-section | Conference |
Volume | ISSN | ISBN |
2012 | 1557-170X | 978-1-4577-1787-1 |
Citations | PageRank | References |
11 | 0.88 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liang Liu | 1 | 69 | 6.22 |
Mihail Popescu | 2 | 469 | 48.76 |
K.C. Ho | 3 | 1311 | 148.28 |
Marjorie Skubic | 4 | 1045 | 105.36 |
Marilyn Rantz | 5 | 310 | 26.24 |