Skip to main content

Table 3 Damage detection, case 1

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

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