A Visual Analytics System for Improving Attention-based Traffic Forecasting Models

  title={A Visual Analytics System for Improving Attention-based Traffic Forecasting Models},
  author={Seungmin Jin and Hyunwoo Lee and Cheonbok Park and Hyeshin Chu and Yunwon Tae and Jaegul Choo and Sungahn Ko},
  journal={IEEE transactions on visualization and computer graphics},
With deep learning (DL) outperforming conventional methods for different tasks, much effort has been devoted to utilizing DL in various domains. Researchers and developers in the traffic domain have also designed and improved DL models for forecasting tasks such as estimation of traffic speed and time of arrival. However, there exist many challenges in analyzing DL models due to the black-box property of DL models and complexity of traffic data (i.e., spatio-temporal dependencies… 



Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

A novel Spatial-Temporal Dynamic Network (STDN) is proposed, in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting.

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

This paper proposes a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain, and builds the model with complete convolutional structures, which enable much faster training speed with fewer parameters.

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics

This paper designs and develops a visual analytics solution that integrates a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, and creates a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales.

An Empirical Experiment on Deep Learning Models for Predicting Traffic Data

It is found that prediction models tend to have varying performances with data and intervals, which calls for in-depth analysis of models on difficult intervals for real-world deployment.

Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions

A comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives is provided, and the state-of-the-art approaches in different traffic prediction applications are listed.

ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models

ActiVis is developed, deployed, and iteratively improved, an interactive visualization system for interpreting large-scale deep learning models and results and can explore complex deep neural network models at both the instance-and subset-level.

Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data

A Hetero-ConvL STM framework is proposed, where a few novel ideas are implemented on top of the basic ConvLSTM model, such as incorporating spatial graph features and spatial model ensemble, which makes reasonably accurate predictions and significantly improves the prediction accuracy over baseline approaches.

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow and evaluates the framework on two real-world large scale road network traffic datasets and observes consistent improvement.

A Visual Analytics System for Exploring, Monitoring, and Forecasting Road Traffic Congestion

An interactive visual analytics system that enables traffic congestion exploration, surveillance, and forecasting based on vehicle detector data is presented, wherein the model is more accurate than other forecasting algorithms.

Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers

A survey of the role of visual analytics in deep learning research is presented, which highlights its short yet impactful history and thoroughly summarizes the state-of-the-art using a human-centered interrogative framework, focusing on the Five W's and How.