Skip to main content

Table 2 Characteristics and principal results (number of cases, training time, number of trials, percentage of bad predictions) of the SLFN model (training and internal test) in predicting the classification of the different treatments: control, Fusarium, Rhizoctonia, salinity and water deficit

From: Sorting biotic and abiotic stresses on wild rocket by leaf-image hyperspectral data mining with an artificial intelligence model

Training (70%)

 Number of cases

105

 Number of hidden layers

1

 Number of nodes

40

 Training time

00:00:03

 Number of trials

955

 % bad predictions

0.0

Testing (30%)

 Number of cases

45

 % bad predictions (N)

26.7 (12)