Table 2
Comparison of the classification metrics for each learning model in the POC tasks.
spec-z | Algorithm | Accuracy | Precision | Recall | F1-score |
---|---|---|---|---|---|
No | Random-Forest (Clarke) | 0.983 | 0.981 | 0.967 | 0.974 |
No | XGBoost | 0.987 | 0.984 | 0.977 | 0.980 |
Yes | Random-Forest | 0.989 | 0.991 | 0.979 | 0.984 |
Yes | XGBoost | 0.994 | 0.993 | 0.989 | 0.991 |
Notes. For the reproduction and improvement of the results by Clarke et al. (2020), the spec-z, spectroscopic redshift, column is set as No; for the exploratory analysis of the inclusion of the spectroscopic redshift in the data, the spec-z column is set as Yes.
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.