Regularised Model Identification Improves Accuracy of Multisensor Systems for Noninvasive Continuous Glucose Monitoring in Diabetes Management
Figure 3
Representative recording sessions of Subjects AA02 (a) and AA04 (b). LASSO, Ridge, and EN models test over independent test data subset (continuous lines) versus RBG levels (open bullets). MARD values for the experimental session on the right are of 16.7% (LASSO), 16.9% (Ridge), and 16.5% (EN), while for the experimental session on the left of 12.7% (LASSO), 11.2% (Ridge), and 9.1% (EN).
