Selected article for: "accurate sensitive and low performance"
Author: Jakub M Bartoszewicz; Anja Seidel; Bernhard Y Renard
Title: Interpretable detection of novel human viruses from genome sequencing data
  • Document date: 2020_1_30
    • ID: ac00tai9_49
    Snippet: We selected LSTM All and CNN All for further evaluation. Table 2 presents the results of a benchmark using the "All" test set. Low performance of the k-NN classifier (Zhang et al., 2019) is caused by frequent conflicting predictions for each read in a read pair (in a single-read setting it achieves 75.5% accuracy, while our best model -87.8%). Although BLAST achieves the highest precision, it yields no predictions for over 10% of the samples. CNN.....
    Document: We selected LSTM All and CNN All for further evaluation. Table 2 presents the results of a benchmark using the "All" test set. Low performance of the k-NN classifier (Zhang et al., 2019) is caused by frequent conflicting predictions for each read in a read pair (in a single-read setting it achieves 75.5% accuracy, while our best model -87.8%). Although BLAST achieves the highest precision, it yields no predictions for over 10% of the samples. CNN All is the most sensitive and accurate (Table 3) .

    Search related documents:
    Co phrase search for related documents
    • accuracy achieve and high precision achieve: 1
    • accuracy achieve and low performance: 1
    • accuracy achieve and sample 10: 1
    • accuracy achieve and test set: 1, 2, 3, 4, 5, 6, 7, 8
    • good model and high precision: 1, 2
    • good model and sample 10: 1, 2
    • good model and test set: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
    • high precision and sample 10: 1
    • high precision and test set: 1, 2
    • low performance and sample 10: 1, 2, 3, 4
    • low performance and test set: 1, 2, 3
    • read pair and single read: 1, 2, 3
    • sample 10 and single read: 1
    • sample 10 and test set: 1