Table 3 The performance of the deep learning prediction model on training and test sets.

From: Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice

Data set

Total samples

RMSE

log loss

MCE

AUC

Gini

Accuracy

Sensitivity

Specitivity

TPV

TNV

White rice 2014 (Training set)

60

0.45

0.55

0.00

1.00

1.00

1.00

1.00

1.00

1.00

1.00

White rice 2015 (A) (Test set 1)

40

0.54

0.83

0.00

1.00

1.00

1.00

1.00

1.00

1.00

1.00

White rice 2015 (B) (Test set 2)

26

0.46

0.59

0.00

1.00

1.00

1.00

1.00

1.00

1.00

1.00

  1. RMSE: Root mean squared error.
  2. LogLoss: Logarithmic loss.
  3. MCE: Mean per-class error.
  4. AUC: Area under the ROC curve.
  5. Gini: Gini coefficient.
  6. TPR: True positive rate.
  7. TNR: True negative rate.
Back to article page