Semi-Supervised Ensemble Classifier with Improved Sparrow Search Algorithm and Its Application in Pulmonary Nodule Detection

Table 3

Initial values for the controlling parameters of algorithms.

Algorithm	Parameter	Value
PSO	Cognitive and social constants:	2, 2
	Inertial weight:	Linearly decreases from 0.9 to 0.2
BSA	Flight interval:	10
	Cognitive accelerated and social accelerated coefficients:	1.5,1.5
	Direct effect:	Single point (probability = 1)
CSA	Awareness probability:	0.1
WOA	Probability switch (p)	0.4
GOA	Decreasing coefficient:	Linearly decreases from 1 to 0.00004
SCA	Movement direction between the solution and destination:	Decreases from 2 to 0
	Movement direction towards or outwards the destination:
	A random weight for the destination:	[0, 2]
	Switch between the sine and cosine components:	[0, 1]
SSA	Producers account for percent of the total population size:	0.2
SSA-SCA	Movement direction between the solution and destination:	Decreases from 2 to 0
	Movement direction towards or outwards the destination:
	A random weight for the destination:	[0, 2]
	Switch between the sine and cosine components:	[0, 1]
SCA-CSSA	Movement direction between the solution and destination:	Decreases from 2 to 0
	Movement direction towards or outwards the destination:
	A random weight for the destination:	[0, 2]
	Switch between the sine and cosine components:	[0, 1]