Fully convolutional networks for structural health monitoring through multivariate time series classification

Advanced Modeling and Simulation in Engineering Sciences

Table 3 Damage detection, case 1

SNR (dB)	\(\varvec{\lbrace {\mathcal {F}}_{*} \rbrace }\)	\(\varvec{A}_{\varvec{d}}\)
15	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\)	0.814
15	\(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.850
15	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\) and \(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.879
10	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\)	0.768
10	\(\{{\varvec{u}}^{ax}_i \}_{i=1}^8\)	0.775
10	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\) and \(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.765

Accuracy \(A_{d}\) of the classifier \({\mathcal {G}}_d\) evaluated on \({\mathbb {D}}^d_{test}\)