EDP Sciences logo
Subscriber Authentication Point
Search
Menu
Home All issues Volume 668 (December 2022) A&A, 668 (2022) A99 Full HTML
Open Access

Table 3

Classifier using XGBoost with two feature set configurations as applied to the imbalanced test dataset.

Completeness Purity
Features Star Quasar Galaxy Star Quasar Galaxy
Gaia_f 0.9714 0.9040 0.9914 0.9766 0.9091 0.9759
Gaia_f + W1-W2 + G-W1 0.9858 0.9799 0.9922 0.9937 0.9705 0.9784

Notes. Classification performances of the model trained on an imbalanced dataset show lower completeness but higher purity compared to the balanced classifier. Classification performances increase when the infrared data are incorporated as input features.

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.