Table 7 Results of the classification DNN using all features.

From: UAV propeller fault diagnosis using deep learning of non-traditional χ2-selected Taguchi method-tested Lempel–Ziv complexity and Teager–Kaiser energy features

UAV type processed dataset

Instances per dataset

Sampling

Repeat train/test

Test/train percentages

Accuracy

F1-score

Precision

Recall

Parrot Bebop 2

345

Random

5

25%, 75%

97.8%

97.8%

97.8%

97.8%

3DR Solo

345

Random

5

25%, 75%

99.1%

99.1%

99.1%

99.1%