Tag: spatio-temporal modeling

A rigorous benchmark of six machine learning families across eight Ahmedabad monitoring stations finds that a hybrid GCN-LSTM model only ...

Researchers in India have developed CAT-Net, a hybrid deep learning model combining convolutional networks, coordinate attention, and Transformer encoders to ...

A new decoupled graph-augmented transformer architecture separates static road topology from dynamic traffic patterns to reduce optimization interference and achieve ...

Researchers in India have developed a deep learning framework called ASTILM that fuses fuzzy logic and CNN-LSTM networks to assess ...

Researchers have developed a graph neural network model that learns dynamic time delays between variables in multivariate time series, improving ...