Skip to main content

Table 3 PSTNN structure design parameter

From: Spatial and temporal learning representation for end-to-end recording device identification

SFENN TFENN
DNN CNN ResNet LSTM Bi-LSTM
Input (2496) Input (64*39*1) Input Input Input
FC (1024) Conv (6*5*5) BN+Relu LSTM(39) Bi-LSTM(39)
FC (1024) pooling Conv(16*3*3) LSTM(78) Bi-LSTM(78)
FC (1024) Conv (16*5*5) BN+Relu FC(1024) FC(1024)
  pooling Conv(16*3*3)   
  Conv (40*5*5) BN+Relu   
  pooling Conv(16*3*3)   
  FC (1024) BN+Relu   
   Conv(16*3*3)   
   pooling (Input)   
   Add()