Table F.1.
Optimal representations and random forest hyperparameters that yielded the best validation macro recalls (RMV) on the synthetic samples.
Sample | Representation | n_estimators | min_samples_leaf | max_features | RDCV | RSDV | RCV | RMV | RDCT | RSDT | RCT | RMT |
---|---|---|---|---|---|---|---|---|---|---|---|---|
W0C0 |
![]() |
100 | 1 | sqrt | 0.98 | 0.97 | 0.98 | 0.98 | 0.97 | 0.97 | 0.97 | 0.97 |
W0C1L25 |
![]() |
500 | 1 | sqrt | 0.90 | 0.89 | 0.96 | 0.92 | 0.87 | 0.87 | 0.95 | 0.89 |
W0C1L50 |
![]() |
100 | 1 | sqrt | 0.93 | 0.92 | 0.96 | 0.94 | 0.91 | 0.90 | 0.96 | 0.92 |
W0C1L100 |
![]() |
500 | 1 | sqrt | 0.96 | 0.96 | 0.97 | 0.96 | 0.95 | 0.96 | 0.97 | 0.96 |
W0C5L25 |
![]() |
100 | 10 | sqrt | 0.85 | 0.74 | 0.85 | 0.81 | 0.81 | 0.68 | 0.81 | 0.77 |
W0C5L50 |
![]() |
500 | 10 | sqrt | 0.84 | 0.76 | 0.86 | 0.82 | 0.82 | 0.71 | 0.82 | 0.78 |
W0C5L100 |
![]() |
500 | 1 | sqrt | 0.89 | 0.90 | 0.94 | 0.91 | 0.87 | 0.87 | 0.91 | 0.89 |
W0C10L25 |
![]() |
500 | 10 | sqrt | 0.80 | 0.67 | 0.74 | 0.74 | 0.76 | 0.61 | 0.70 | 0.69 |
W0C10L50 |
![]() |
500 | 10 | sqrt | 0.76 | 0.71 | 0.72 | 0.73 | 0.75 | 0.66 | 0.70 | 0.70 |
W0C10L100 |
![]() |
100 | 10 | sqrt | 0.88 | 0.76 | 0.91 | 0.85 | 0.84 | 0.73 | 0.89 | 0.82 |
W1C0 |
![]() |
500 | 1 | sqrt | 0.96 | 0.95 | 0.98 | 0.96 | 0.96 | 0.94 | 0.97 | 0.96 |
W1C1L25 |
![]() |
500 | 10 | sqrt | 0.93 | 0.86 | 0.96 | 0.92 | 0.90 | 0.84 | 0.95 | 0.89 |
W1C1L50 |
![]() |
500 | 10 | sqrt | 0.94 | 0.89 | 0.97 | 0.93 | 0.93 | 0.88 | 0.95 | 0.92 |
W1C1L100 |
![]() |
500 | 1 | sqrt | 0.95 | 0.94 | 0.98 | 0.96 | 0.95 | 0.93 | 0.97 | 0.95 |
W1C5L25 |
![]() |
500 | 10 | sqrt | 0.85 | 0.74 | 0.85 | 0.81 | 0.82 | 0.67 | 0.81 | 0.77 |
W1C5L50 |
![]() |
100 | 10 | sqrt | 0.84 | 0.76 | 0.85 | 0.82 | 0.82 | 0.72 | 0.80 | 0.78 |
W1C5L100 |
![]() |
500 | 1 | sqrt | 0.89 | 0.88 | 0.93 | 0.90 | 0.87 | 0.86 | 0.91 | 0.88 |
W1C10L25 |
![]() |
100 | 10 | sqrt | 0.79 | 0.67 | 0.73 | 0.73 | 0.78 | 0.61 | 0.69 | 0.69 |
W1C10L50 |
![]() |
100 | 10 | sqrt | 0.76 | 0.69 | 0.74 | 0.73 | 0.74 | 0.65 | 0.69 | 0.69 |
W1C10L100 |
![]() |
500 | 1 | sqrt | 0.84 | 0.84 | 0.86 | 0.85 | 0.79 | 0.81 | 0.82 | 0.81 |
W10C0 |
![]() |
500 | 1 | sqrt | 0.92 | 0.89 | 0.96 | 0.92 | 0.90 | 0.87 | 0.93 | 0.90 |
W10C1L25 |
![]() |
100 | 10 | sqrt | 0.92 | 0.83 | 0.95 | 0.90 | 0.91 | 0.80 | 0.91 | 0.88 |
W10C1L50 |
![]() |
500 | 1 | sqrt | 0.90 | 0.87 | 0.94 | 0.90 | 0.89 | 0.84 | 0.91 | 0.88 |
W10C1L100 |
![]() |
500 | 1 | sqrt | 0.91 | 0.88 | 0.95 | 0.91 | 0.89 | 0.86 | 0.92 | 0.89 |
W10C5L25 |
![]() |
100 | 10 | sqrt | 0.86 | 0.74 | 0.85 | 0.82 | 0.83 | 0.67 | 0.79 | 0.76 |
W10C5L50 |
![]() |
500 | 10 | sqrt | 0.85 | 0.76 | 0.84 | 0.82 | 0.82 | 0.70 | 0.81 | 0.78 |
W10C5L100 |
![]() |
500 | 1 | sqrt | 0.85 | 0.84 | 0.90 | 0.86 | 0.82 | 0.81 | 0.87 | 0.83 |
W10C10L25 |
![]() |
100 | 10 | sqrt | 0.76 | 0.67 | 0.73 | 0.72 | 0.74 | 0.61 | 0.69 | 0.68 |
W10C10L50 |
![]() |
500 | 10 | sqrt | 0.76 | 0.70 | 0.75 | 0.74 | 0.74 | 0.65 | 0.69 | 0.69 |
W10C10L100 |
![]() |
500 | 10 | None | 0.84 | 0.75 | 0.84 | 0.81 | 0.82 | 0.70 | 0.80 | 0.77 |
W100C0 |
![]() |
500 | 10 | sqrt | 0.90 | 0.73 | 0.81 | 0.82 | 0.89 | 0.69 | 0.77 | 0.78 |
W100C1L25 |
![]() |
100 | 10 | sqrt | 0.89 | 0.73 | 0.82 | 0.81 | 0.86 | 0.68 | 0.78 | 0.77 |
W100C1L50 |
![]() |
500 | 10 | log2 | 0.91 | 0.74 | 0.81 | 0.82 | 0.87 | 0.68 | 0.77 | 0.77 |
W100C1L100 |
![]() |
100 | 10 | sqrt | 0.89 | 0.73 | 0.81 | 0.81 | 0.87 | 0.68 | 0.77 | 0.77 |
W100C5L25 |
![]() |
500 | 10 | log2 | 0.85 | 0.70 | 0.77 | 0.78 | 0.82 | 0.65 | 0.72 | 0.73 |
W100C5L50 |
![]() |
100 | 10 | sqrt | 0.83 | 0.71 | 0.77 | 0.77 | 0.80 | 0.66 | 0.73 | 0.73 |
W100C5L100 |
![]() |
500 | 10 | log2 | 0.82 | 0.72 | 0.79 | 0.78 | 0.79 | 0.68 | 0.74 | 0.74 |
W100C10L25 |
![]() |
500 | 10 | sqrt | 0.80 | 0.67 | 0.68 | 0.72 | 0.77 | 0.59 | 0.65 | 0.67 |
W100C10L50 |
![]() |
500 | 10 | sqrt | 0.78 | 0.68 | 0.68 | 0.71 | 0.76 | 0.62 | 0.65 | 0.68 |
W100C10L100 |
![]() |
500 | 10 | sqrt | 0.78 | 0.71 | 0.74 | 0.75 | 0.76 | 0.66 | 0.71 | 0.71 |
Notes. We also present the validation class recalls for the dark companion (RDCV), semidetached (RSDV), and contact (RCV) binary light curves as well as the test class recalls (RDCT, RSDT, RCT) and the test macro recall (RMT) of the best performing classifiers. We describe the synthetic samples in Sect. 2 and provide the definitions of the representations in Sects. 3.1–3.2. The symbol denotes the extended full representation. The definitions of the hyperparameters are given in Sect. 3.4.
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.