Wearable Sensor-Based Human Activity Recognition Using Hybrid Deep Learning Techniques

Table 7

Experimental parameters of CNN-LSTM model.

Parameters	Value
Input vector size	150
Input channel number	8
Convolution kernel size	3
Pool size	2
Activation function	ReLu
LSTM layer	1
Neurons number	64
Dropout	0.5
Learning rate	0.002
Batch size	150
Epoch	400