Research Article
A Combined One-Class SVM and Template-Matching Approach for User-Aided Human Fall Detection by Means of Floor Acoustic Features
Table 1
Composition of the dataset.
| Class | Number of occurrences | Total length (s) |
| Basket | 64 | 86 | Fork | 64 | 82 | Ball | 64 | 129 | Book | 64 | 63 | Bag | 64 | 57 | Chair | 96 | 157 | Human falls | 44 | 76 | Human activity | 665 | 1218 | Music | 776 | 1498 |
|
|