Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

Chinese Journal of Mechanical Engineering

Table 6 Comparison of performance of novelty detection

	The proposed method	One-class SVM fed by multi-head DNN features	Isolation forest fed by multi-head DNN features
\({\varvec{T}}{\varvec{P}}{\varvec{R}}\)(%)	98.41	98.68	97.55
\({\varvec{T}}{\varvec{N}}{\varvec{R}}\)(%)	94.69	32.67	58.04
\({{\varvec{F}}}_{1}\) score	0.97	0.79	0.81