Scientific Reports

Table 4 Predictive performance of eighteen regression algorithms in predicting AD in the waterbodies.

From: Machine learning-guided determination of Acinetobacter density in waterbodies receiving municipal and hospital wastewater effluents

Rank	ML	MSE	ML	RMSE	ML	R²	ML	MAD
1	XGB	0.0059	XGB	0.0770	XGB	0.9912	Cubist	0.0437
2	Cubist	0.0117	Cubist	0.1081	Cubist	0.9827	XGB	0.0440
3	ANET6	0.0172	ANET6	0.1310	M5P	0.9589	ANET6	0.0856
4	ANRT42	0.0220	ANET42	0.1483	RF	0.9584	M5P	0.0863
5	ANET33	0.0253	ANET33	0.1590	BRT	0.8140	ANET33	0.0987
6	M5P	0.0275	M5P	0.1657	KNN	0.7459	RF	0.1044
7	RF	0.0282	RF	0.1679	ANET6	0.6727	ANET42	0.1078
8	BRT	0.1261	BRT	0.3551	SVR	0.6294	SVR	0.2142
9	KNN	0.1723	KNN	0.4150	MARS	0.5913	KNN	0.2297
10	SVR	0.2475	SVR	0.4975	ANET42	0.5804	BRT	0.2385
11	MARS	0.2770	MARS	0.5263	DTR	0.5460	DTR	0.3146
12	DTR	0.3032	DTR	0.5506	ANET33	0.5178	MARS	0.3176
13	GBM	0.3547	GBM	0.5955	GBM	0.4768	GBM	0.4148
14	NNT	0.3834	NNT	0.6192	NNT	0.4259	NNT	0.4399
15	ENR	0.4853	ENR	0.6967	ENR	0.2732	LRSS	0.5421
16	LR	0.5036	LR	0.7097	LR	0.2570	LR	0.5774
17	LRSS	0.50506	LRSS	0.7107	LRSS	0.2549	ENR	0.6104
18	ELM	0.5447	ELM	0.7380	ELM	0.1965	ELM	0.6368

Back to article page

Search

Advanced search

Quick links