Novel FTLRNN with Gamma Memory for Short-Term and Long-Term Predictions of Chaotic Time Series

Table 13

For K = 10, training and testing samples variation for FTLRNN on testing data set.

Time series		Mackey-Glass time series			Duffing time series
Training exemplars	Testing exemplars	MSE	NMSE	𝑟	MSE	NMSE	𝑟
10%	75%	0.00191	0.03733	0.9812	0.00804	0.15432	0.92405
20%	65%	0.00208	0.03994	0.97985	0.00314	0.02395	0.98796
30%	55%	0.02261	0.04205	0.97888	0.00202	0.01315	0.99356
40%	45%	0.00266	0.04815	0.97581	0.00260	0.01653	0.99185
50%	35%	0.03448	0.06483	0.967219	0.00288	0.01936	0.99014
60%	25%	0.004475	0.07940	0.9596	0.00335	0.02185	0.98910
70%	15%	0.00757	0.12238	0.9373	0.00306	0.02046	0.99001
80%	05%	0.02204	0.27796	0.8537	0.00655	0.04429	0.97835