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

Table 12

Comparative analysis of recall.

S. No.	Technique	AR1	AR3	CM1	JM1	KC2	KC3	MC1
1	SVM	0.917	0.889	0.896	0.817	0.828	0.82	0.993
2	J48	0.901	0.873	0.88	0.799	0.814	0.794	0.994
3	RF	0.901	0.921	0.892	0.827	0.833	0.814	0.995
4	MLP	0.901	0.937	0.876	0.82	0.847	0.773	0.994
5	RBF	0.917	0.873	0.896	0.82	0.837	0.799	0.993
6	HMM	0.926	0.873	0.902	0.183	0.795	0.186	0.933
7	CDT	0.926	0.873	0.894	0.817	0.83	0.82	0.994
8	A1DE	0.909	0.921	0.863	0.815	0.833	0.799	0.982
9	NB	0.851	0.905	0.853	0.814	0.835	0.789	0.942
10	KNN	0.901	0.857	0.847	0.771	0.805	0.722	0.995

The bold values in the table indicate the highest recall in each column.