Summary of Origin-destination Demand Prediction: An Urban Radiation and Attraction Perspective, by Xuan Ma et al.
Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective
by Xuan Ma, Zepeng Bao, Ming Zhong, Yuanyuan Zhu, Chenliang Li, Jiawei Jiang, Qing Li, Tieyun Qian
First submitted to arxiv on: 29 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 approach is proposed to predict origin-destination (OD) demand in urban development. Traditional methods focus on spatial or temporal dependencies between regions, ignoring their functional differences. The new method incorporates knowledge-driven physical models that characterize regions’ functions based on radiation and attraction capacities, considering both numerical factors like population and intrinsic nominal attributes such as residential or industrial districts. The model also captures the complex relationships between these two types of capacities. This work addresses a significant gap in existing methods, which neglect to account for these fundamental functional differences. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is being explored to predict where people will go from one place to another. Right now, most computers use math formulas and data from past years to make predictions. But this approach doesn’t take into account what makes different places unique, like whether it’s a residential or industrial area. The researchers are trying to fix this by using a combination of mathematical models that understand how people move around the city based on how crowded or empty an area is. They’re also looking at how these areas change throughout the day. |
Keywords
» Artificial intelligence » Deep learning
