A Clustering and SVM Regression Learning-Based Spatiotemporal Fuzzy Logic Controller with Interpretable Structure for Spatially Distributed Systems

Table 1

Learning results of an SVM regression with different values of C and 𝜀.

𝐶	𝜀	Number of SV	RMSE training (×10^−2)	RMSE testing (×10^−2)	SSE (×10^−2)	IAE (×10^−1)	ITAE (×10^−1)
1	0.00001	149	4.89	3.48	1.70	2.566	8.656
	0.0001	140	4.89	3.48	1.70	2.566	8.655
	0.001	129	4.86	3.45	1.71	2.573	8.699
	0.01	105	4.75	3.13	1.84	2.699	9.389
	0.1	13	6.35	3.24	1.99	2.901	10.163
	0.2	12	12.80	6.44	3.74	4.653	19.063
	0.3	10	19.29	7.76	4.77	5.715	24.248
10	0.00001	149	4.89	3.48	1.70	2.566	8.656
	0.0001	140	4.89	3.48	1.70	2.566	8.655
	0.001	129	4.86	3.45	1.71	2.573	8.699
	0.01	105	4.75	3.13	1.84	2.699	9.389
	0.1	13	6.35	3.24	1.99	2.901	10.163
	0.2	12	12.80	6.44	3.74	4.653	19.063
	0.3	10	19.29	7.76	4.77	5.715	24.248
100	0.00001	149	4.89	3.48	170	2.566	8.656
	0.0001	141	4.89	3.48	1.70	2.566	8.655
	0.001	129	4.86	3.45	1.71	2.573	8.699
	0.01	105	4.75	3.13	1.84	2.699	9.389
	0.1	13	6.35	3.24	1.99	2.901	10.163
	0.2	12	12.80	6.44	3.74	4.653	19.063
	0.3	10	19.29	7.76	4.77	5.715	24.248
1000	0.00001	149	4.89	3.48	170	2.566	8.656
	0.0001	141	4.89	3.48	1.70	2.566	8.655
	0.001	129	4.86	3.45	1.71	2.574	8.702
	0.01	106	4.75	3.13	1.84	2.700	9.395
	0.1	13	6.35	3.24	1.99	2.901	10.163
	0.2	12	12.80	6.44	3.74	4.653	19.063
	0.3	10	19.29	7.76	4.77	5.715	24.248