As shown in Table 7 and Figure 8 , the first observation is that, with the increase of feature number from one up to four, the accuracies show an increasing trend using all the methods except using deep sparse autoencoder with fine-tuning, whereas the latter has achieved near perfect performance with any number of features.
← all excerpts
Fault Detection and Identification in an Acid Gas Removal Unit Using Deep Autoencoders.
1
—
—