Research of GPCEMBP Glucose Prediction Algorithm Based on Continuous Glucose Monitoring

Table 8

Comparison with some previous works reported in the literature.

Methods	Inputs	Max pH (min)	R	RMSE (mg/dl)	MAPE (%)
GPCEMBP	Clinical data	84	0.9866	6.46	2.54
CRNN [13]	Virtual data & clinical data	60	n.r.	33.27	19.01
LSTM [34]	Clinical data	45	0.89	21.52	n.r.
DE-SVR [35]	Clinical data	60	0.982	12.95	5.65
EMD-SSA-KELM [36]	Clinical data	30	n.r.	11.12	6.87
EMD-GA-BP [37]	Virtual data	30	n.r.	8.21	n.r.
VMD-ELM-AdaBoost [38]	Clinical data	60	0.8738	10.14	4.86

n.r., not reported.