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

<div>Results in<i> clean</i> conditions for the three test cases. “Set 1” comprises human falls, human activities, and music. “Set 2” comprises human falls and object falls. “Set 3” comprises human falls, object falls, human activities, and music.</div>

Computational Intelligence and Neuroscience

fig9

Figure 9

Figure 9: A Combined One-Class SVM and Template-Matching Approach for User-Aided Human Fall Detection by Means of Floor Acoustic Features 