A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning

Table 4

Accuracy of diagnosis with different data filtering methods.

Model	Accuracy
Proposed model (LLE+CNN+JDA)	87.3±0.5%
PCA+CNN+JDA	65.7±0.7%
K-Means+CNN+JDA	68.6±0.4%
DBSCAN+CNN+JDA	77.6±0.4%
GMM+CNN+JDA	85.2±0.6%
BIRCH+CNN+JDA	71.4±0.7%