Table 2 Accuracy values resulting from validation and testing with the LDA model.

From: Rapid analysis of meat floss origin using a supervised machine learning-based electronic nose towards food authentication

Window number

Accuracy (%)

Maximum

Minimum

Mean

Median

Validation

Testing

Validation

Testing

Validation

Testing

Validation

Testing

0

95.5

92.0

89.0

90.7

91.5

93.3

93.3

90.7

1

95.6

90.7

97.7

90.7

96.9

94.7

97.8

93.3

2

92.3

90.7

99.0

94.7

97.4

97.3

100

97.3

3

92.3

90.7

99.6

100

98.6

100

99.2

100

4

92.3

90.7

99.2

100

98.8

100

100

100

5

99.9

100

99.7

100

99.6

100

99.4

100

6

99.4

100

99.2

100

99.3

100

98.7

100

  1. Validation accuracy was used during development of machine learning model under cross-validation. Testing accuracy was employed to evaluate the developed machine learning model on the unseen data. Different window numbers were evaluated using the LDA model (W1–W6).
Back to article page