Skip to main content
. 2023 Apr 19;23(8):4111. doi: 10.3390/s23084111

Figure 22.

Figure 22

Results of training neural network with 25 input nodes, two hidden layers with 45 and 10 nodes, respectively, and 2 output nodes. Used correlation threshold for filtering: 0.7. Regularization: L1 regularization on input features. (a) Scatter plot of systolic values. (b) Scatter plot of diastolic values.