An Effective Big Data Supervised Imbalanced Classification Approach for Ortholog Detection in Related Yeast Species
Table 7
Supervised algorithms and parameter values in the experiments.
Algorithm
Parameter values
RF-BD1
Number of trees: 100 Random selected attributes per node: 32ā Number of maps: 20
RF-BDCS
Number of trees: 100 Random selected attributes per node: 3 Number of maps: 20 ā
ROS (100%) + RF-BD
RS3 = 100%
ROS (130%) + RF-BD
RS = 130%
SVM-BD
Regulation parameter: 1.0, 0.5, and 0.0 Number of iterations: 100 (by default) StepSize: 1.0 (by default) miniBatchFraction: 1.0 (percent of the dataset evaluated in each iteration 100%)
ROS (100%) + SVM-BD
RS = 100%
ROS (130%) + SVM-BD
RS = 130%
BD: big data. , where is the number of attributes of the dataset. RS: resampling size.