Empirical Study of Homogeneous and Heterogeneous Ensemble Models for Software Development Effort Estimation

Table 1

Comparison of related works on the use of ensemble models for software effort estimation.

Study	Ensemble type	Base learner(s)	Combination rule(s)	Number of datasets
Braga et al. [22]	Homogeneous; (bagging)	Linear regression	Linear (averaging)	1
	Homogeneous; (bagging)	MLP	Linear (averaging)
	Homogeneous; (bagging)	M5P regression trees	Linear (averaging)
	Homogeneous; (bagging)	M5P model trees	Linear (averaging)
	Homogeneous; (bagging)	SVR	Linear (averaging)
Kultur et al. [23, 24]	Homogeneous; (bootstrapping)	MLP	Nonlinear (average of largest cluster obtained using adaptive resonance theory (ART) algorithm)	5
Minku and Yao [25, 26]	Homogeneous; (bagging, random, negative correlation learning)	MLP	Linear (averaging)	18
	Homogeneous; (bagging)	RBF	Linear (averaging)
	Homogeneous; (bagging)	Regression Trees	Linear (averaging)
Kocaguneli et al. [27]	Heterogeneous	Gaussian process, MLP, RBF, SMOReg, SVMReg, IBk, LWL, additive regression, bagging with decision tree, RandomSubSpace, DecisionStump, M5P, ConjunctiveRule, DecisionTable	Linear (averaging)	3
Kocaguneli et al. [28]	Heterogeneous	ABE0-1NN, ABE0-5NN, SWReg, CART (yes), CART (no), NNet, LReg, PCR, PLSR	Linear (mean, median, inverse-ranked weighted mean (IRWM))	20
Elish [29]	Heterogeneous	MLP, RBF, RT, KNN, SVR	Linear (median)	5
	Homogeneous (bagging)	MLP	Linear (averaging, weighted averaging) and nonlinear (MLP; SVR, FIS-FCM, FIS-SC, ANFIS-FCM, ANFIS-SC)
This paper	Homogeneous; (bagging)	SVR		5
	Homogeneous; (bagging)	ANFIS
	Heterogeneous	MLP, SVR, ANFIS