Skip to main content

View full-text article in PMC

. 2021 Dec 29;22(1):235. doi: 10.3390/s22010235

Table 7.

Root mean square error for artificial dataset.

Method	Set	Average Value	Minimum Value	Maximum Value	Standard Deviation
Seasonal ARIMA	Training	18.358	NA
Seasonal ARIMA	Test	17.974	NA
Support vector regression	Training	0.159 *	NA
Support vector regression	Test	11.035	NA
Multi-layer perceptron	Training	1.859	0.514	6.473	1.822
Multi-layer perceptron	Test	10.779	9.910	13.207	0.921
Convolutional neural network	Training	0.770	0.296	1.169	0.321
Convolutional neural network	Test	12.947	12.504	13.290	0.234
LSTM-EEMD	Training	21.642	20.282	23.424	1.612
LSTM-EEMD	Test	22.064	21.309	23.378	1.141
LSTM RNN many-to-one	Training	21.829	10.247	38.096	7.806
LSTM RNN many-to-one	Test	23.635	11.165	37.080	8.469
LSTM RNN many-to-many	Training	11.044	11.000	11.050	0.015
LSTM RNN many-to-many	Test	10.405 *	10.397	10.408	0.003

*: Best result.