Performance on the benchmark training dataset was evaluated based on AUC, MCC, Accuracy, Specificity, Sensitivity and Precision, using 5-fold cross-validation test.

NIAID Data Ecosystem20

Classification errors and computational costs (CCs) of MHC and the proposed method with the optimized parameters.

分类器性能评估

计算成本分析

Classification errors include type I error (T.I), type II error (T.II), total error (T.E) and kappa (κ).

Figshare2017-05-03 更新60

Performance comparisons of our ensemble classifier with existing methods on the same independent testing dataset.

分类器性能评估

集成学习对比

Performance comparisons of our ensemble classifier with existing methods on the same independent testing dataset.

Figshare2016-09-24 更新40

Per-class performance of the InceptionV3 model.

资源简介：

相关数据集