Rimminen Henry, Lindström Juha, Linnavuo Matti, Sepponen Raimo
Department of Electronics, Aalto University, 02150 Espoo, Finland.
IEEE Trans Inf Technol Biomed. 2010 Nov;14(6):1475-6. doi: 10.1109/TITB.2010.2051956. Epub 2010 Jun 3.
We present a new fall-detection method using a floor sensor based on near-field imaging. The test floor had a resolution of 9 × 16. The shape, size, and magnitude of the patterns are used for classification. A test including 650 events and ten people yielded a sensitivity of 91% and a specificity of 91%.
我们提出了一种基于近场成像的使用地面传感器的新型跌倒检测方法。测试地面的分辨率为9×16。图案的形状、大小和幅度用于分类。一项包含650个事件和十个人的测试的灵敏度为91%，特异性为91%。
