Based on this result, it would seem natural to search for another voting procedure that differs from the majority method in not giving rise to this form of cycles.
However, for purposes of this preliminary study, using the majority method seemed sufficient.
This is because the Average method uses real values output from the individual models, while the Majority method uses voting.
In contrast, the majority method considers all classifiers equally relevant and takes a vote, deciding for class that agrees with the majority.
Note that the Average and Majority methods produce the value for metrics based on classification error (such as Accuracy and TPR), but differ in metrics producing real values (such as RMSE).
Beside reference-free methods [ 22, 23], the majority of methods for whole blood are based on existing reference database of sorted blood cells by using differentially methylated loci across major leukocyte types [ 8, 14, 18].
Moreover, for the highly connected proteins, the topological based methods SAMPLECONNECT and NEIGHCONNECT outperformed the majority based methods, MAJORITYNEIGH and MAJORITYCLUST.
In general, for samples with high tumor cell contents, the majority genotyping methods are suitable; however, for samples without sufficient tumor cell contents, more sensitive methods are preferable.
In addition, we showed that, by employing a DC method, we are able to lower this effect to some extent for the majority of methods used.
In fact, the operational matrices make the method easy to apply the high-order differential equations which are really difficult to handle by the majority of methods, especially those techniques based on weak forms.
