Skip to main content

Advertisement

Table 6 Accuracies for the synthetic datasets [%]

From: Supervised DNA Barcodes species classification: analysis, comparisons and results

Dataset SVM Jrip J48 Naïve Bayes Average Standard deviation
Ne1000 96.53 96.26 94.07 96.48 95.84 1.19
Ne10000 96.77 95.26 94.88 96.79 95.93 0.99
Ne50000 93.92 89.28 89.63 92.46 91.32 2.24
  1. Results of the Weka supervised learning methods tested on synthetic datasets show that SVM and Naïve Bayes outperform the other techniques in term of percentage of the correct species identification. The differences between SVM and the other algorithms result statistically significant (p-value ≤ 0.001). The best performances are highlighted in bold for each dataset.