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

Table 5

Sample sizes: imbalanced and balanced datasets.

Dataset	Method	Total number of samples		Ratio (MA/MI)
		Majority (MA)	Minority (MI)
Imbalanced	—	924	75	12.32
Balanced	PDDBS oversampling	924	924	1.00
	PDDBS median sampling	499	499	1.00
	SMOTE oversampling	924	918	1.01
	SMOTE median sampling	499	495	1.01