Summary of Trafps: a Shapley-based Visual Analytics Approach to Interpret Traffic, by Zezheng Feng et al.
TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic
by Zezheng Feng, Yifan Jiang, Hongjun Wang, Zipei Fan, Yuxin Ma, Shuang-Hua Yang, Huamin Qu, Xuan Song
First submitted to arxiv on: 7 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel deep learning-based traffic prediction approach is presented, called TrafPS, which offers a visual analytics framework to increase transparency and interpretability in traffic flow predictions. By leveraging region SHAP and trajectory SHAP measurements, the model quantifies the impact of different flow patterns on urban traffic at varying levels. A multi-aspect interactive interface is designed for exploring significant flow patterns, demonstrating its effectiveness in identifying key routes and supporting decision-making in urban planning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to understand how traffic flows work. Most machines that predict traffic are like magic boxes – we don’t really know how they make their predictions. Some researchers tried to “open the box” so people could see what’s going on, but it’s still hard to use these complex machines with big amounts of data. To fix this, a new approach called TrafPS is developed to help understand traffic flow predictions. It uses special measurements to show how different patterns affect urban traffic and offers an interactive tool for experts to explore the findings. Two real-world examples show how TrafPS can help identify important routes and make better decisions about city planning. |
Keywords
* Artificial intelligence * Deep learning
