When the gradient method was applied to all the samples (531) for training, the prediction accuracy was also comparable to other feature selection methods except SVM-RFE.
Our previous exploration indicated that several feature selection methods and classifiers produce comparable results.
Therefore, it is plausible that application of other feature selection methods could provide improvements comparable to the RGIFE technique.
We conclude from the good agreement of the selected genes in both feature selection methods that classical LDA or MLHD in combination with genetic search algorithms delivers comparable results with algorithms using tree classifiers like RF.
In testing using a Support Vector Machine as a classifier, ensemble results for seven datasets demonstrate performance that is at least comparable and often better than the performance of individual feature selection methods.
Many other selection methods are superior.
Three selection methods are evaluated.
Species frequently live in similar habitats with comparable selection pressures.
Therefore in future, other block selection methods could be investigated that do not require execution times as long as a GA and still produce stress recognition measures comparable to the GA hybrid.
