Table 5 Comparison of macro- and micro-averaging for XTinyHAR under 5-fold cross-validation.

From: A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI

Dataset

Averaging method

Accuracy (%)

F1-score (%)

Precision (%)

UTD-MHAD

Macro-averaging

98.41

98.33

98.29

Micro-averaging

98.71

98.65

98.61

MM-Fit

Macro-Averaging

98.21

98.17

98.10

Micro-averaging

98.55

98.50

98.46

Back to article page