main content:
Propose a neural network architecture for heart rate estimation from PPG signals;
Network Architecture:
Network design:
1. Use 8s PPG signal, truncate 8 parts, each 1s, spliced as input, PPG sampling frequency is 125Hz;
2. Use 1 × 5 , 1 × 20 , 1 × 40 , 1 × 60 , 1 × 80 1\times 5,1\times20,1\times40,1\times60,1\times801×5,1×20,1×40,1×60,1×The 80 % convolution kernel is convoluted and spliced separately to provide the characteristics of different receptive fields;
3. Followed by 8 convolution blocks, the convolution block contains two sub-blocks, each sub-block has convolution, batch normalization and RELU;
4. Use 8 × 125 8\times1258×The LSTM of 125 operates on the basis of 1;
5. Combine the results of 3 and 4;
6. Transfer the spliced matrix of 5 to 384 × 125 384\times125384×125 LSTM modules;
7. Finally connect to the fully connected layer;
result:
参考:
PPGnet: Deep Network for Device Independent Heart Rate Estimation from Photoplethysmogram