Summary of Efficient Large-scale Urban Parking Prediction: Graph Coarsening Based on Real-time Parking Service Capability, by Yixuan Wang et al.
Efficient Large-Scale Urban Parking Prediction: Graph Coarsening Based on Real-Time Parking Service Capability
by Yixuan Wang, Zhenwu Chen, Kangshuai Zhang, Yunduan Cui, Yang Yang, Lei Peng
First submitted to arxiv on: 5 Oct 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 This paper proposes an innovative framework for predicting large-scale urban parking graphs leveraging real-time service capabilities to improve accuracy and efficiency. It introduces a graph attention mechanism that assesses real-time service capabilities of parking lots to construct dynamic parking graphs reflecting real preferences in parking behavior. Combining graph coarsening techniques with temporal convolutional autoencoders, the study achieves unified dimension reduction of complex urban parking graph structures and features. A spatio-temporal graph convolutional model makes predictions based on the coarsened graph, while a pre-trained autoencoder-decoder module restores predicted results to original data dimensions. The methodology is tested on a real dataset from Shenzhen parking lots, achieving improvements of 46.8% in accuracy and 30.5% in efficiency compared to traditional models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps cities solve the problem of parking difficulties by using special computer programs that learn from real-time information about parking lots. It creates a new way to predict where people will park based on how they behave now. The method uses two main parts: one that makes the graph smaller and easier to work with, and another that predicts where people will park. This combination allows for more accurate predictions, making it useful for cities. |
Keywords
» Artificial intelligence » Attention » Autoencoder » Decoder
