Figure 4.

Architecture of a CNN model for sensor-based HAR. T, S and $n_k$ designate the time length of the input data, the number of sensor channels, and the number of convolutional kernels of the kth layer, respectively. The convolutional and pooling kernels of the kth layer process patches of the input data of sizes $(f_T^{(k)},f_S^{(k)})$ and $(p_T^{(k)},p_S^{(k)})$, respectively. Neurons of intermediate convolutional layers perform convolution products across all convolutional maps of the previous layer.