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

Table 11

Comparative analysis of RRSE.

S. No.	Technique	AR1	AR3	CM1	JM1	KC2	KC3	MC1
1	SVM	109.405	99.6674	108.4851	110.4067	102.8529	109.2121	100.3607
2	J48	114.0496	102.3912	110.822	104.7491	98.2924	110.5573	92.2254
3	RF	108.6878	81.4368	99.0872	92.4278	86.4543	94.2824	79.2174
4	MLP	109.6657	76.5306	104.785	95.7816	84.6955	113.4827	89.3325
5	RBF	101.3862	87.8669	97.9878	95.1733	84.5435	99.7454	99.0846
6	HMM	190.2829	149.5011	167.8622	129.2111	123.8513	128.5606	592.0558
7	CDT	99.9593	100.9585	102.2522	96.9708	89.8344	98.1628	91.4393
8	A1DE	111.5568	87.4683	106.8639	97.0031	88.0436	103.724	140.1728
9	NB	142.0683	94.9565	127.572	110.8776	99.5502	116.8883	284.2012
10	KNN	118.7971	111.1859	131.084	122.7563	109.6576	134.8914	84.3477

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