A Combined One-Class SVM and Template-Matching Approach for User-Aided Human Fall Detection by Means of Floor Acoustic Features

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/cin/volume-2017/1512670/figures/1512670.fig.003a.svgz" name="1512670.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>1: the outer container. 2: the inner container. 3: the microphone slot. 4: the membrane touching the floor</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/cin/volume-2017/1512670/figures/1512670.fig.003b.svgz" name="1512670.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>A picture of the Floor Acoustic Sensor used during the recordings</td></tr></table>

<div>The Floor Acoustic Sensor scheme (a) and picture of the prototype (b).</div>

Computational Intelligence and Neuroscience

fig3

Figure 3

Figure 3: A Combined One-Class SVM and Template-Matching Approach for User-Aided Human Fall Detection by Means of Floor Acoustic Features 