Predicting multiple types of traffic accident severity with explanations: A multi-task deep learning framework
Safety Science(2022)
摘要
•Propose a DNN-based framework for multi-type traffic accident severity prediction.•Use LRP to achieve explainability in the DNN model and identify key factors.•Our model outperforms state-of-the-art methods in prediction quality.•Our model’s explainability is proved to be more reliable than the latest methods.
更多查看译文
关键词
Deep learning,Traffic accident severity prediction,Explainable artificial intelligence,Machine learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要