Software Defect Prediction for Healthcare Big Data: An Empirical Evaluation of Machine Learning Techniques

Table 10

Comparative analysis of RMSE.

S. No.	Technique	AR1	AR3	CM1	JM1	KC2	KC3	MC1
1	SVM	0.2875	0.3333	0.3231	0.4272	0.4152	0.4247	0.0848
2	J48	0.2997	0.3424	0.3301	0.4053	0.3968	0.43	0.0779
3	RF	0.2856	0.2724	0.2951	0.3577	0.349	0.3667	0.0669
4	MLP	0.2882	0.256	0.3121	0.3706	0.3419	0.4414	0.0754
5	RBF	0.2664	0.2939	0.2919	0.3683	0.3413	0.3879	0.0837
6	HMM	0.5	0.5	0.5	0.5	0.5	0.5	0.5
7	CDT	0.2627	0.3377	0.3046	0.3752	0.3627	0.3818	0.0772
8	A1DE	0.2931	0.2925	0.3183	0.3754	0.3554	0.4034	0.1184
9	NB	0.3733	0.3176	0.38	0.4291	0.4019	0.4546	0.24
10	KNN	0.3122	0.3719	0.3905	0.475	0.4427	0.5246	0.0712

The bold values in the table indicate the reduced error rate.