LSTMAutoEncoder

Description

This API calls the LSTMAutoEncoder model, which can be used for anomaly detection, time series prediction.

LSTMAE Model Architecture

Image Source: Positional Health Assessment of Collaborative Robots Based on Long Short-Term Memory Auto-Encoder (LSTMAE) Network Naimul Hasan et al

LSTMAE is an LSTM-based Autoencoder model primarily used for anomaly detection in time series data. The model compresses the input data and reconstructs it to learn important features and capture patterns in time series data.

Model Structure:

  • Encoder
    • LSTM layers process the input sequence to extract important features of the time series data.
  • Latent Space
    • The latent space holds the important information learned by the model through the encoder.
    • This space contains the essential features of the input time series data.
  • Decoder
    • LSTM layers reconstruct the time series data from the latent space representation.

API module path

from api.v2.model.LSTMAE import LSTMAutoencoder

Parameters

input_dim

  • Specifies the input feature size.
  • Example
    • If data's shape (x,x,5).
    • input_dim = 5

hidden_dim

  • Specifies the hidden dim size.
  • This value sets the number of nodes in the intermediate layer.
  • Example
    • This value must be smaller than the input_dim.
    • hidden_dim = 2

num_layer

  • Specifies the number of LSTM layers.
  • Example
    • num_layer = 3

Use_revin

  • Specifies whether to use RevIN normalization.
  • default : False
  • Example
    • Use_revin = False

Example Sample Code (Python)

Results

Check the entire module code.

datahub/api/v2/model/LSTMAE.py at main · machbase/datahub
All Industrial IoT DataHub with data visualization and AI source - machbase/datahub

Back to Top