4.4 Article

Real-time traffic incident detection based on a hybrid deep learning model

期刊

TRANSPORTMETRICA A-TRANSPORT SCIENCE
卷 18, 期 1, 页码 78-98

出版社

TAYLOR & FRANCIS LTD
DOI: 10.1080/23249935.2020.1813214

关键词

Generative adversarial networks; deep learning; autoencoder; small sample size; imbalanced data

资金

  1. Sichuan New Generation Artificial Intelligence Special Programme [2018GZDZX0029]
  2. Shenzhen Science and Technology program [KQTD20180412181337494]

向作者/读者索取更多资源

A hybrid model is proposed in this study to tackle the issues of small sample sizes and imbalanced datasets in traffic incident detection. The model utilizes a generative adversarial network (GAN) to expand the sample size and balance the datasets, as well as a temporal and spatially stacked autoencoder (TSSAE) to extract temporal and spatial correlations for incident detection. Evaluations using real-world data show that the proposed model, considering both temporal and spatial variables, outperforms benchmark models and improves real-time detection capacity.
Small sample sizes and imbalanced datasets have been two difficulties in previous traffic incident detection-related studies. Moreover, real-time characteristics of incident detection models must be improved to satisfy the needs of traffic management. In this study, a hybrid model is proposed to address the above problems. In the proposed model, a generative adversarial network (GAN) is used to expand the sample size and balance datasets, and a temporal and spatially stacked autoencoder (TSSAE) is used to extract temporal and spatial correlations of traffic flow and detect incidents. Using a real-world dataset, the model is evaluated from different aspects. The results show that the proposed model, considering both temporal and spatial variables, outperforms some benchmark models. The model can both increase the incident sample size and balance the dataset. Furthermore, the sample selection method improves the real-time capacity of the detection.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.4
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据