ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-Temporal Graph Attention and Bidirectional Recurrent United Neural Networks.
Zepu WangDingyi ZhuangYankai LiJinhua ZhaoPeng SunShenhao WangYulin HuPublished in: ITSC (2023)
Keyphrases
- spatio temporal
- neural network
- data imputation
- recurrent neural networks
- feed forward
- missing values
- missing data
- pattern recognition
- random walk
- spatial and temporal
- graph representation
- moving objects
- space time
- artificial neural networks
- graph structure
- back propagation
- graph theory
- directed graph
- movement patterns
- network traffic
- road network
- fuzzy logic
- image sequences
- spiking neural networks
- recurrent networks
- machine learning
- data mining
- multilayer perceptron
- neural network model
- traffic flow
- graph mining