Skip to main content

Advertisement

Table 2 The performance of our deep phenotyping system (CNN + LSTM) compared to other baseline methods (Using handcrafted features and SVM as a classifier, adding the LSTM to consider temporal information, CNN without temporal information and using CRF instead of LSTM to compare their performance)

From: Deep phenotyping: deep learning for temporal phenotype/genotype classification

  Sf-2 Cvi Ler-1 Col-0 Avg.
Hand-crafted features using SVM 58.4 83.9 65.1 35.7 60.8
Hand-crafted features + LSTM 61.3 90.2 68.2 52.4 68.0
CNN 71.0 86.0 74.4 76.0 76.8
CNN + CRF 84.3 96.1 90.4 89.4 87.6
CNN + LSTM 89.6 93.8 94.2 94.2 93.0
  1. Results are reported in percent (%)
  2. The best performing method for each category is italicized