Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics
| Autor: | Cagatay Turkay, Juncong Lin, Jiazhi Xia, Wei Chen, Jincheng Jiang, Chengqiao Lin, Wei Zeng |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Visual analytics Computer science Computer Vision and Pattern Recognition (cs.CV) media_common.quotation_subject Computer Science - Computer Vision and Pattern Recognition Computer Science - Human-Computer Interaction 02 engineering and technology computer.software_genre Bivariate map Human-Computer Interaction (cs.HC) Rendering (computer graphics) Data visualization 0202 electrical engineering electronic engineering information engineering media_common Creative visualization business.industry Deep learning 020207 software engineering Computer Graphics and Computer-Aided Design Modifiable areal unit problem Signal Processing Computer Vision and Pattern Recognition Data mining Artificial intelligence business computer Software |
| Zdroj: | IEEE Transactions on Visualization and Computer Graphics. 27:839-848 |
| ISSN: | 2160-9306 1077-2626 |
| DOI: | 10.1109/tvcg.2020.3030410 |
| Popis: | Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks. However, the widely known modifiable areal unit problem within such aggregation processes can lead to perturbations in the network inputs. This issue can significantly destabilize the feature embeddings and the predictions - rendering deep networks much less useful for the experts. This paper approaches this challenge by leveraging unit visualization techniques that enable the investigation of many-to-many relationships between dynamically varied multi-scalar aggregations of urban traffic data and neural network predictions. Through regular exchanges with a domain expert, we design and develop a visual analytics solution that integrates 1) a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, 2) a Moran's I Scatterplot that provides local indicators of spatial association analysis, and 3) a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales. We evaluate our approach through a series of case studies involving a real-world dataset of Shenzhen taxi trips, and through interviews with domain experts. We observe that geographical scale variations have important impact on prediction performances, and interactive visual exploration of dynamically varying inputs and outputs benefit experts in the development of deep traffic prediction models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|