Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective

Zhou, Zhengyang; Wang, Yang; Xie, Xike; Chen, Lianliang; Zhu, Chaochao

doi:10.1109/tkde.2020.3034312

Cited by 32 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used precision, recall, F1-score and AUC as the evaluation standards of the model, which are shown in Equations ( 24) to (27), respectively.…”

Section: Methodsmentioning

confidence: 99%

“…traffic events, weather data [8] propose differential time-varying graph neural network (DTGN), which divides the research area into rectangular grids with unequal length according to the road network structure, and carries out multi task accident prediction, that is, it can predict traffic flow as well as traffic risk. Zhou et al [27] propose a unified framework, RiskSeq, to predict urban traffic accidents in multiple steps from the perspective of time and space. Yu et al [5] collect large-scale heterogeneous data related to traffic accidents in Beijing, including traffic flow, weather conditions, road network, POIs, and traffic accident data, and propose a deep spatio-temporal graph neural network (DSTGCN) for road accident prediction.…”

Section: Related Workmentioning

confidence: 99%

“…Zhou et al. [27] propose a unified framework, RiskSeq, to predict urban traffic accidents in multiple steps from the perspective of time and space. Yu et al.…”

Section: Related Workmentioning

confidence: 99%

“…pred pos > pred neg posNum * negNum (27) where pred pos and pred neg represent the prediction probability of positive and negative samples respectively, and posnum and negnum represent the number of positive and negative samples, respectively.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A multi‐attention dynamic graph convolution network with cost‐sensitive learning approach to road‐level and minute‐level traffic accident prediction

Jia

Luo

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Traffic accident prediction on road levels and minute levels plays an important role in optimizing public safety and improving traffic infrastructure. However, there are still some challenges in this work. Firstly, the dynamic factors (e.g. traffic flow) affecting traffic accidents make the road network have dynamic spatio‐temporal dependency, which leads to biased prediction results. Secondly, the occurrence of traffic accidents is a small probability event, which brings about zero‐inflation problem. To address aforementioned problems, the authors propose a Multi‐Attention Dynamic Graph Convolution Network with Cost Sensitive Learning approach (MADGCN). Specifically, in the spatial dimension, MADGCN calculates the attention scores of different types of dynamic factors through attention mechanism to simulate the different influence degrees of different factors, and models dynamic inter‐road spatial correlation through Graph Convolution Network (GCN). In the temporal aspect, MADGCN adaptively models the dynamic temporal correlations through self‐attention blocks. In addition, MADGCN improves the loss function based on cost‐sensitive learning strategy to increase the cost of false classification of positive samples, so as to accurately mine sparse positive samples. Experimental results on two real‐world traffic accident datasets demonstrate the superiority of MADGCN. Compared with the existing state‐of‐the‐art methods, F1‐score of MADGCN on two real‐world traffic accident datasets is improved by 11.61% and 9.15%, respectively.

show abstract

“…We used precision, recall, F1-score and AUC as the evaluation standards of the model, which are shown in Equations ( 24) to (27), respectively.…”

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Zhou et al. [27] propose a unified framework, RiskSeq, to predict urban traffic accidents in multiple steps from the perspective of time and space. Yu et al.…”

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A multi‐attention dynamic graph convolution network with cost‐sensitive learning approach to road‐level and minute‐level traffic accident prediction

Jia

Luo

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…To empower an adaptive topology, AGCRN [31] learns a dynamic topology based on feature-wise product, while STAR-GNN [46] and L2P framework [47] respectively design a mutual-information based strategy and a generative process, to estimate the optimal receptive fields for GNNs. More recently, exogenous context factors those are out-of-graph have been demonstrated to potentially interfere the intrinsic graph topology and have complicated interactions on element-wise aggregations [25], [27], [48]. Unfortunately, existing literature has barely discussed this issue.…”

Section: F Hyperparameter Settingsmentioning

confidence: 99%

Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics

Zhou¹,

Kuo²,

Sun³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Spatiotemporal forecasting is an imperative topic in data science due to its diverse and critical applications in smart cities. Existing works mostly perform consecutive predictions of following steps with observations completely and continuously obtained, where nearest observations can be exploited as key knowledge for instantaneous status estimation. However, the practical issues of early activity planning and sensor failures elicit a brand-new task, i.e., non-consecutive forecasting. In this paper, we define spatiotemporal learning systems with missing observation as Grey Spatiotemporal Systems (G2S) and propose a Factor-Decoupled learning framework for G2S (FDG2S), where the core idea is to hierarchically decouple multi-level factors and enable both flexible aggregations and disentangled uncertainty estimations. Firstly, to compensate for missing observations, a generic semantic-neighboring sequence sampling is devised, which selects representative sequences to capture both periodical regularity and instantaneous variations. Secondly, we turn the predictions of non-consecutive statuses into inferring statuses under expected combined exogenous factors. In particular, a factor-decoupled aggregation scheme is proposed to decouple factor-induced predictive intensity and region-wise proximity by two energy functions of conditional random field. To infer region-wise proximity under flexible factor-wise combinations and enable dynamic neighborhood aggregations, we further disentangle compounded influences of exogenous factors on regionwise proximity and learn to aggregate them. Given the inherent incompleteness and critical applications of G2S, a DisEntangled Uncertainty Quantification is put forward, to identify two types of uncertainty for reliability guarantees and model interpretations.Extensive experiments demonstrate that our solution can promote the performance by at least 8.50% on early planning and 2.01%-18.00% on the sensor failure setting.

show abstract

Deep Spatial–Temporal Graph Modeling of Urban Traffic Accident Prediction

Huang

Zhang

2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective

Cited by 32 publications

References 40 publications

A multi‐attention dynamic graph convolution network with cost‐sensitive learning approach to road‐level and minute‐level traffic accident prediction

A multi‐attention dynamic graph convolution network with cost‐sensitive learning approach to road‐level and minute‐level traffic accident prediction

Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics

Deep Spatial–Temporal Graph Modeling of Urban Traffic Accident Prediction

Contact Info

Product

Resources

About