Open Access

Table 5

Performance comparison in terms of average F1 score and the average of the accuracy of five folds of cross-validation.

Model Bands Accuracy F1 score
ConvEntion (Ours) ugriz 83.90 75.77
ConvEntion (Ours) g 79.47 72.38
CNN+GRU (Gómez et al. 2020) g 74.84 68.95
CNN+LSTM (Carrasco-Davis et al. 2019) g 73.94 67.29

Notes. This table includes only experiments on a dataset with three 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.