Applicability of deep learning for blood pressure estimation during hemodialysis based on facial images

Table 2 Configuration of the CNN

Layer no	Layer	Size	Number	Layer no	Layer	Size	Number
1	Input	201 × 201	–	18	Conv 5	4 × 4	32
2	Conv 1	4 × 4	8	19	Batch norm 5	–	–
3	Batch norm 1	–	–	20	ReLU	–	–
4	ReLU	–	–	21	Pool 5	2 × 2	–
5	Pool 1	2 × 2	–	22	Conv 6	4 × 4	32
6	Conv 2	4 × 4	16	23	Batch norm 6	–	–
7	Batch norm 2	–	–	24	ReLU	–	–
8	ReLU	–	–	25	Pool 6	2 × 2	–
9	Pool 2	2 × 2	–	26	Conv 7	4 × 4	32
10	Conv 3	4 × 4	32	27	Batch norm 7	–	–
11	Batch norm 3	–	–	28	ReLU	–	–
12	ReLU	–	–	29	Pool 7	2 × 2	–
13	Pool 3	2 × 2	–	30	Conv 8	4 × 4	32
14	Conv 4	4 × 4	32	31	Batch norm 8	–	–
15	Batch norm 4	–	–	32	ReLU	–	–
16	ReLU	–	–	33	FC	–	–
17	Pool 4	2 × 2	–	34	Reg	–	–

“Input” is the input layer, “Conv n” is the nth convolutional layer, “Pool n” is the nth mean pooling layer, “Batch Norm n” is the nth batch normalization layer, “ReLU” is the layer to which the activation function, Rectified Linear Unit, is applied, “Dropout” is the Dropout layer to prevent over learning, “FC” is the total combined layer, “Reg” is the regression output layer, “Size” is the size of the input layer, convolution layer filters, and average pooling, and “Number” is the number of convolution layer filters. The average pooling stride and dropout rate were set to 2 and 0.2, respectively

ISSN: 2059-1381