An Approach for Identifying Cytokines Based on a Novel Ensemble Classifier

Algorithm 3

Ensemble algorithm of under-sampling combined with over-sampling.

(1) Input: small sample set 𝑆, big sample set 𝐵, the sample number of output sets 𝑘;

(2) Output: balanced sample set 𝑈𝑈=𝑆^′+𝐵^′,𝑆^′=𝐵^′=𝑘;

(3) Extending 𝑆 to a new set 𝑆^′ that has 𝑘 samples according to SMOTE algorithm;

(4) Down sample set 𝐵 to a new set 𝐵^′ that has 𝑘 samples according to K-mean clustering;

(5) Output 𝑈.