Skip to main content

Table 1 Schematic overview of the architecture of the T-GCN on the X-strain data with 42 nodes

From: A computational framework for modeling complex sensor network data using graph signal processing and graph neural networks in structural health monitoring

Layer

Activation

Filters

Shape

Parameters

Input

\(42 \times 10\)

0

GCN 1

ReLU

8

\(42 \times 8\)

1886

GCN 2

ReLU

8

\(42\times 8\)

1870

Reshape 1

\(42 \times 8 \times 1\)

0

Permute

\(8 \times 42 \times 1\)

0

Reshape 2

\(8 \times 42\)

0

LSTM 1

Tanh

50

\(8 \times 50\)

18600

LSTM 2

Tanh

50

50

20200

Dropout

50

0

Dense

Tanh

42

42

2142