In this paper machine learning methods are studied for classification data containing some misleading items. We use ensembles of known noise correction preprocessing the training set. Preprocessing can be either relabeling or deleting items detected to have noisy labels. After preprocessing, usual convolutional networks applied data. With performance very accurate further improved.

Metabolomics involves the large scale analysis of metabolites and thus, provides information regarding cellular processes in a biological sample. Independently of the analytical technique used, a vast amount of data is always acquired when carrying out metabolomics studies; this results in complex datasets with large amounts of variables. This type of data requires multivariate statistical anal...