Self-Tuning Inference Model for Settlement in Shield Tunneling: A Case Study of the Taipei Mass Rapid Transit System’s Songshan Line

Table 8

Comparison with data balanced by PDDBS.

Algorithm	Training							Testing
	MAPE (%)		RMSE	MAE	R	RI	Rank	MAPE (%)	RMSE	MAE	R	RI	Rank
Original dataset
BPNN	10.75		2.2276	1.4593	0.9023	0.7201	4	12.16	2.3635	1.6551	0.8874	0.7844	3
LSSVM	8.49		1.9266	1.3073	0.9648	0.8250	2	10.12	2.2621	1.5159	0.9442	0.8322	2
ELSIM	8.49		1.9088	1.3308	0.9264	0.7885	3	11.59	5.5700	1.8920	0.7807	0.6331	4
SVM	25.84		6.7033	4.8161	0.8136	0.1090	5	32.51	7.1774	5.6747	0.1400	0.0000	5
SOS-LSSVM	5.00		1.2579	0.8031	0.9811	0.9188	1	7.63	2.0467	1.2002	0.9567	0.8828	1
PDDBS oversampling
BPNN	6.13		1.6970	1.0244	0.9823	0.8805	4	6.68	1.8302	1.1335	0.9768	0.9160	2
LSSVM	6.24		1.5540	1.0117	0.9867	0.8936	3	6.88	1.9755	1.2018	0.9776	0.9099	3
ELSIM	3.43		0.8927	0.6062	0.9890	0.9431	2	5.38	1.9476	1.1413	0.8242	0.8652	4
SVM	54.29		10.0046	7.2173	0.9045	0.0521	5	59.24	10.7365	8.1600	0.2768	0.0000	5
SOS-LSSVM	3.00		0.7852	0.5296	0.9963	0.9664	1	4.82	1.5374	0.8405	0.9859	0.9438	1
PDDBS median sampling
BPNN		5.29	1.6314	1.0664	0.9797	0.8795	4	5.07	2.0343	1.1767	0.9590	0.8897	4
LSSVM		4.77	1.5050	0.9884	0.9833	0.8937	3	5.47	1.8360	1.1282	0.9746	0.8993	3
ELSIM		3.80	1.3211	0.8187	0.9728	0.9015	2	4.65	1.7172	0.9844	0.9566	0.9069	2
SVM		40.12	8.5787	6.0746	0.8896	0.1407	5	43.18	9.2834	6.9853	0.1943	0.0000	5
SOS-LSSVM		2.39	0.9048	0.5243	0.9930	0.9566	1	3.66	1.3851	0.7959	0.9856	0.9385	1