Table 6 Performance of 1-second ResNet34 using quantitative metrics for MUST dataset.

From: Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML

Metrics

RMSE (mg/dL)

MSE (mg/dL)2

MAE (mg/dL)

MARD (%)

ResNet34-1s

19.7

389.3

14.8

12.8

Vgg16-1s

21.0

410

17

15.0

CNN-LSTM-ATTENTION-1s

24.4

599.2

17.1

13.0

Back to article page