An Augmentation Method for Small-Sample Imbalanced Industrial IoT Detection Data | Wuhan University Journal of Natural Sciences

Open Access

Table 1

Differences between models

Model design	TMG-GAN	R3GAN	The proposed model
GAN variant	WGAN	RpGAN	RpGAN
Gradient penalty strategy	—	zero-centered gradient penalties ( $R_{1}$ and $R_{2}$ )	zero-centered gradient penalties ( $R_{1}$ and $R_{2}$ )
Multi-generator structure	Multi-generator structure	—	Multi-generator Ssructure
Generator decoupling	Generator decoupling	—	Generator decoupling
Classifier Branch	Classifier branch	—	Classifier branch

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.