Skip to main content

Table 5 Evaluation of all the methods by cross-validation on Boston dataset at genus level

From: Prediction of microbial communities for urban metagenomics using neural network approach

Evaluation metric
Methods Precision Recall F1 score Ranking loss
IDW 0.5316 0.6177 0.5691 0.1929
kNN 0.7359 0.6266 0.6723 0.1837
SVM 0.7583 0.5366 0.6282 0.1473
Random Forest (RF) 0.7318 0.6214 0.6682 0.1630
Neural Network 0.7228 0.5594 0.6214 0.1297
MetaMLAnn 0.7674 0.6706 0.7095 0.1270
MetaMLAnn+ RF 0.7744 0.6862 0.7229 0.1283
  1. Higher precision, recall, F1 score, and lower ranking loss indicate better performance. Bold entries indicate best performance among different methods