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

Table 2

The convolution and pooling layers of the CNN architecture.

Layers	Conv1d_1	Conv1d_2	Conv1d_2
Size	1 × 2 × 8	1 × 2 × 18	1 × 2 × 36
Stride	1 × 1 × 1	1 × 1 × 1	1 × 1 × 1
Channel	18	36	72
Layers	Pooling_1	Pooling_2	Pooling_3
Size	1 × 2 × 18	1 × 2 × 36	1 × 2 × 72
Stride	1 × 1 × 1	1 × 1 × 1	1 × 1 × 1
Channel	18	36	72