官方服务：
资源简介：
F1 scores after feature ablation.
应用场景：
创建时间：
2019-07-18
相关数据集
Classification results obtained on subsets generated using Pearson correlation.
Statistically significant differences (), as compared to using all the features and measured by a two-tailed t-test, are marked as ‘+’ (positive differences) and ‘−’ (negative differences).
NIAID Data Ecosystem70
Accuracy percentage of the SVM classifier at different stages of removal of similar genes and applied filtration results for 200 discriminative genes.
Accuracy percentage of the SVM classifier at different stages of removal of similar genes and applied filtration results for 200 discriminative genes.
NIAID Data Ecosystem40
Number of train-test cycles in which feature was selected for the classifier.
Number of train-test cycles in which feature was selected for the classifier.
NIAID Data Ecosystem30
F1 scores for synthetic data feature selection when part of the variables is continuous.
F1 scores for synthetic data feature selection when part of the variables is continuous.
NIAID Data Ecosystem50
The drop in F-score when a feature is removed from the NBCP system.
Numbers that are statistically significant with 95% confidence are marked in bold. Negative numbers indicate that a feature is making a useful contribution to the system.
NIAID Data Ecosystem40
