Summary of Multiple Areal Feature Aware Transportation Demand Prediction, by Sumin Han et al.
Multiple Areal Feature Aware Transportation Demand Prediction
by Sumin Han, Jisun An, Youngjun Park, Suji Kim, Kitae Jang, Dongman Lee
First submitted to arxiv on: 23 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 The proposed novel spatio-temporal multi-feature-aware graph convolutional recurrent network (ST-MFGCRN) effectively predicts short-term transportation demand by fusing multiple areal features, including land use, sociodemographics, and POI distribution. The model incorporates sentinel attention to calculate the areal similarity matrix, allowing each area to take partial attention if the feature is not useful. This approach outperforms state-of-the-art baselines on two real-world transportation datasets, with a maximum improvement of 7% on the BusDJ dataset and 8% on the TaxiBJ dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to predict how people will use public transportation in the near future. This helps cities make better decisions about when to send buses and how many are needed. Right now, some scientists look at just a few things like what buildings are around or who lives there. But cities are really different, with lots of unique features that affect how people travel. The new model, called ST-MFGCRN, looks at multiple features like these and uses them to make more accurate predictions. |
Keywords
» Artificial intelligence » Attention » Recurrent network
