Blood Glucose Prediction on Clinical Blood Glucose Monitoring Dataset (train)
94.39Hypoglycemia Acc.Deep network
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Deep networkTraining data (M)=50%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 94.39 | 2.04 | 3.57 | 83.44 | 14.52 | 2.04 | 67.21 | 18.08 | 14.71 | |
| Deep networkTraining data (M)=30%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 86.41 | 2.51 | 11.08 | 85.05 | 12.59 | 2.36 | 62.24 | 15.34 | 22.42 | |
| Shallow networkTraining data (M)=50%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 61.49 | 5.5 | 33.01 | 82.16 | 12.59 | 5.25 | 60.5 | 19.21 | 20.29 | |
| Shallow networkTraining data (M)=30%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 61.1 | 5.21 | 33.69 | 81.96 | 12.77 | 5.27 | 60.01 | 19.62 | 20.37 | |
| Tikhonov reg.Training data (M)=50%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 59.02 | 1.94 | 39.04 | 83.56 | 11.95 | 4.49 | 62.34 | 19.55 | 18.11 | |
| Tikhonov reg.Training data (M)=30%, Filtering=Flat low-pass, Filter type=First-order Butterworth, Cutoff frequency=0.82017.07 | 57.47 | 2.01 | 40.52 | 83.49 | 12 | 4.51 | 62.13 | 19.13 | 18.74 |