Vision-Based Fall Detection with Convolutional Neural Networks

Table 2

Results of our system on the three datasets (URFD, FDD, and Multicam) using different setups. In the minibatch size column, “full” means batch training and is the value of the weight given to the fall class. Notice that the ReLU activation function is always preceded by batch normalization. Sens. refers to sensitivity, whereas Spec. is used for specificity.

Dataset	Learning rate	Minibatch size		Activation function	Sens.	Spec.
URFD	10^−5	64	1	ReLU	100.0%	94.86%
Multicam	10^−3	Full	1	ReLU	98.07%	96.20%
FDD	10^−4	1,024	2	ELU	93.47%	97.23%