Photometric redshift-aided classification using ensemble learning

Open Access

Table 4

Classification metrics for the XGBoost, LightGBM, and CatBoost models for the multi-class and one versus all approaches.

Approach	Class	Algorithm	Accuracy	Precision	Recall	F1-score
		XGBoost	0.988	0.985	0.978	0.981
Multi-class	Multi	CatBoost	0.986	0.983	0.976	0.979
		LightGBM	0.987	0.984	0.978	0.981

		XGBoost	0.989	0.989	0.986	0.988
	Galaxy	LightGBM	0.989	0.989	0.986	0.987
		CatBoost	0.988	0.988	0.984	0.986

		XGBoost	0.991	0.985	0.978	0.981
One vs all	QSO	LightGBM	0.991	0.985	0.978	0.982
		CatBoost	0.990	0.983	0.976	0.980

		XGBoost	0.995	0.993	0.988	0.991
	Star	LightGBM	0.995	0.993	0.989	0.991
		CatBoost	0.994	0.992	0.987	0.990

Notes. The metric values shown are calculated over all classes.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.