Traffic accident prediction is a crucial task in the mobility domain. State-of-the-art accident prediction approaches are based on static and uniform grid-based geospatial aggregations, limiting their capability for fine-grained predictions. This property becomes particularly problematic in more complex regions such as city centers. In such regions, a grid cell can contain subregions with different properties; furthermore, an actual accident-prone region can be split across grid cells arbitrarily. This paper proposes Adaptive Clustering Accident Prediction (ACAP) - a novel accident prediction method based on a grid growing algorithm. ACAP applies adaptive clustering to the observed geospatial accident distribution and performs embeddings of temporal, accident-related, and regional features to increase prediction accuracy. We demonstrate the effectiveness of the proposed ACAP method using open real-world accident datasets from three cities in Germany. We demonstrate that ACAP improves the accident prediction performance for complex regions by 2-3 percent points in F1-score by adapting the geospatial aggregation to the distribution of the underlying spatio-temporal events. Our grid growing approach outperforms the clustering-based baselines by four percent points in terms of F1-score on average.
%0 Conference Proceedings
%1 dadwal2021adaptive
%A Dadwal, Rajjat
%A Funke, Thorben
%A Demidova, Elena
%B Proc. of the 24th IEEE International Intelligent Transportation Systems Conference, ITSC 2021
%D 2021
%I IEEE
%K campaneo dadwal demand funke myown smashhit worldkg
%R 10.1109/ITSC48978.2021.9564564
%T An Adaptive Clustering Approach for Accident Prediction
%X Traffic accident prediction is a crucial task in the mobility domain. State-of-the-art accident prediction approaches are based on static and uniform grid-based geospatial aggregations, limiting their capability for fine-grained predictions. This property becomes particularly problematic in more complex regions such as city centers. In such regions, a grid cell can contain subregions with different properties; furthermore, an actual accident-prone region can be split across grid cells arbitrarily. This paper proposes Adaptive Clustering Accident Prediction (ACAP) - a novel accident prediction method based on a grid growing algorithm. ACAP applies adaptive clustering to the observed geospatial accident distribution and performs embeddings of temporal, accident-related, and regional features to increase prediction accuracy. We demonstrate the effectiveness of the proposed ACAP method using open real-world accident datasets from three cities in Germany. We demonstrate that ACAP improves the accident prediction performance for complex regions by 2-3 percent points in F1-score by adapting the geospatial aggregation to the distribution of the underlying spatio-temporal events. Our grid growing approach outperforms the clustering-based baselines by four percent points in terms of F1-score on average.
@proceedings{dadwal2021adaptive,
abstract = {Traffic accident prediction is a crucial task in the mobility domain. State-of-the-art accident prediction approaches are based on static and uniform grid-based geospatial aggregations, limiting their capability for fine-grained predictions. This property becomes particularly problematic in more complex regions such as city centers. In such regions, a grid cell can contain subregions with different properties; furthermore, an actual accident-prone region can be split across grid cells arbitrarily. This paper proposes Adaptive Clustering Accident Prediction (ACAP) - a novel accident prediction method based on a grid growing algorithm. ACAP applies adaptive clustering to the observed geospatial accident distribution and performs embeddings of temporal, accident-related, and regional features to increase prediction accuracy. We demonstrate the effectiveness of the proposed ACAP method using open real-world accident datasets from three cities in Germany. We demonstrate that ACAP improves the accident prediction performance for complex regions by 2-3 percent points in F1-score by adapting the geospatial aggregation to the distribution of the underlying spatio-temporal events. Our grid growing approach outperforms the clustering-based baselines by four percent points in terms of F1-score on average. },
added-at = {2021-07-31T20:14:27.000+0200},
author = {Dadwal, Rajjat and Funke, Thorben and Demidova, Elena},
biburl = {https://www.bibsonomy.org/bibtex/22a6305fb5db1f65c371974b60bbaf21c/demidova},
booktitle = {Proc. of the 24th {IEEE} International Intelligent Transportation Systems Conference, {ITSC} 2021},
doi = {10.1109/ITSC48978.2021.9564564},
interhash = {596e726043e8513f4b281c611ba7fb4f},
intrahash = {2a6305fb5db1f65c371974b60bbaf21c},
keywords = {campaneo dadwal demand funke myown smashhit worldkg},
publisher = {IEEE},
timestamp = {2022-02-27T13:52:40.000+0100},
title = {An Adaptive Clustering Approach for Accident Prediction},
year = 2021
}