Fig. 4.
Download original image
Confusion matrix for the predictions for the number of absorption lines using the CNN (as shown in Fig. 3). The CNN was trained on 1.6 million lines and tested on 400 K samples, with an equal number of single and double lines. We find the Sensitivity = 97.47%, Specificity = 89.92%, Precision = 89.64% and Negative Predictive Value = 97.55%.
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.