Sequential Human Activity Recognition Based on Deep Convolutional Network and Extreme Learning Machine Using Wearable Sensors

Table 6

score comparison of the proposed architecture and deep architecture, either including or ignoring the Null class.

Deep architectures
	Gesture recognition	Gesture recognition (no Null class)
CNN [17]	0.851
Baseline CNN	0.883	0.783
CNN-LSTM [18]	0.897	0.802
CNN-LSTM-ELM	0.918	0.906