Skip to main content

Table 5 Deep neural network

From: Recognition of cooking activities through air quality sensor data for supporting food journaling

 

Original predictions

After post-processing

TN

4506

727

FP

1109

482

TP

527

491

FN

142

178

Accuracy (%)

80.09

64.86

Specificity (%)

80.25

60.13

Recall (%)

78.77

73.39

Precision (%)

32.21

50.46

\(F_1\) score (%)

45.73

59.81

  1. Results with cooking instance modality, online recognition
  2. Numbers in italic indicate the largest value obtained in the experiment for each considered metric