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

Advanced Modeling and Simulation in Engineering Sciences

Table 4 Damage localization, case 1

SNR (dB)	\(\varvec{\lbrace {\mathcal {F}}_{*} \rbrace }\)	\(\varvec{A}_{\varvec{l}}\)
15	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\)	0.768
15	\(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.769
15	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\) and \(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.812
10	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\)	0.654
10	\(\{{\varvec{u}}^{ax}_i\}_{i=1}^8 \)	0.642
10	\(\{{\varvec{u}}^{sh}_i\}_{i=1}^8\) and \(\{{\varvec{u}}^{ax}_i\}_{i=1}^8\)	0.707

Accuracy \({\mathbb {A}}_{l}\) of the classifier \({\mathcal {G}}_l\) evaluated on \({\mathbb {D}}^l_{test}\)