Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence sem...Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.展开更多
The TrafficRiskClassifier model proposed in this study adopts an innovative approach inte-grating migration learning,image classification,and self-supervised learning,with the goal of significantly enhancing the accur...The TrafficRiskClassifier model proposed in this study adopts an innovative approach inte-grating migration learning,image classification,and self-supervised learning,with the goal of significantly enhancing the accuracy and efficiency of traffic accident risk analysis.Compared with traditional traffic safety analysis techniques,this model focuses on utiliz-ing contextual information and situational data from traffic accidents to achieve higher risk classification accuracy.The core of this approach is to deeply mine and analyze the detailed information in the accident environment,to provide more scientific and effective support for traffic accident risk prevention and response.Initially,by integrating migration learning with image classification techniques,the model efficiently extracts pivotal features from complex traffic scenarios and forms initial risk assessments.Subsequently,self-supervised learning is incorporated in this study,augmenting the model’s capability to comprehend and categorize accident imagery.The TrafficRiskClassifier model exhibits a generalization ability of 91.82%,85.16%,and 80.92%on individual classification tasks,respectively,signifying its robust learning capacity and proficiency in managing unseen data.Furthermore,the TrafficRiskClassifier model delineates a functional nexus between accident risk and variables such as weather,road conditions,and personal factors,employ-ing a polynomial regression approach.This methodology not only amplifies the predictive precision of the model but also renders it versatile across diverse scenarios.Through ana-lyzing various polynomial functions,the model achieves improved accuracy in classifying different risk levels.The outcomes demonstrate that the TrafficRiskClassifier model can efficaciously amalgamate contextual information within traffic scenarios,thereby achiev-ing more precise classification of traffic accident risks,and consequently serving as an invaluable instrument for urban traffic safety management.展开更多
With the aging of society,the increase in the number of elderly drivers poses a potential hazard to road traffic safety.Therefore,accurately predicting the severity of possible traffic accidents of elderly drivers is ...With the aging of society,the increase in the number of elderly drivers poses a potential hazard to road traffic safety.Therefore,accurately predicting the severity of possible traffic accidents of elderly drivers is crucial to ensure the safety of drivers and passengers.In this paper,a hybrid model based on the CTGAN-ResNet-XGBoost network is proposed for classifying the severity of the accidents of elderly drivers.The model was trained and tested using traffic accident data of the United States from 2018–2022.The hybrid model first generates a small amount of categorical data via the Conditional Tabular Generative Adversarial Network to address the dataset’s category imbalance.Then,the balanced dataset is transformed into feature images using the DeepInsight method and feature extraction is performed using the residual neural network to improve the feature recognition ability of the classification model.Finally,the XGBoost model is used to classify the severity of the accident and the SHAP method is used to analyse the main features affecting the accident.The superior performance of the hybrid model is verified through experimental comparative analysis.The experimental results show that the hybrid model has a significant advantage in the prediction of driving risk for elderly drivers,that the causes of accidents for elderly drivers are different from those for younger drivers and that the characteristics of speed,seat belt use and driver’s age are the main factors affecting the severity of accidents.The results of this study improve the accuracy and reliability of traffic accident severity prediction and provide more scientific support for traffic safety management.展开更多
基金funded by the Technology Research and Development Plan Program of China State Railway Group Co.,Ltd.(No.Q2024T001)the Foundation of China Academy of Railway Sciences Co.,Ltd.(No:2024YJ259).
文摘Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.
文摘The TrafficRiskClassifier model proposed in this study adopts an innovative approach inte-grating migration learning,image classification,and self-supervised learning,with the goal of significantly enhancing the accuracy and efficiency of traffic accident risk analysis.Compared with traditional traffic safety analysis techniques,this model focuses on utiliz-ing contextual information and situational data from traffic accidents to achieve higher risk classification accuracy.The core of this approach is to deeply mine and analyze the detailed information in the accident environment,to provide more scientific and effective support for traffic accident risk prevention and response.Initially,by integrating migration learning with image classification techniques,the model efficiently extracts pivotal features from complex traffic scenarios and forms initial risk assessments.Subsequently,self-supervised learning is incorporated in this study,augmenting the model’s capability to comprehend and categorize accident imagery.The TrafficRiskClassifier model exhibits a generalization ability of 91.82%,85.16%,and 80.92%on individual classification tasks,respectively,signifying its robust learning capacity and proficiency in managing unseen data.Furthermore,the TrafficRiskClassifier model delineates a functional nexus between accident risk and variables such as weather,road conditions,and personal factors,employ-ing a polynomial regression approach.This methodology not only amplifies the predictive precision of the model but also renders it versatile across diverse scenarios.Through ana-lyzing various polynomial functions,the model achieves improved accuracy in classifying different risk levels.The outcomes demonstrate that the TrafficRiskClassifier model can efficaciously amalgamate contextual information within traffic scenarios,thereby achiev-ing more precise classification of traffic accident risks,and consequently serving as an invaluable instrument for urban traffic safety management.
基金supported by the National Natural Science Foundation of China(Grant No.52072412).
文摘With the aging of society,the increase in the number of elderly drivers poses a potential hazard to road traffic safety.Therefore,accurately predicting the severity of possible traffic accidents of elderly drivers is crucial to ensure the safety of drivers and passengers.In this paper,a hybrid model based on the CTGAN-ResNet-XGBoost network is proposed for classifying the severity of the accidents of elderly drivers.The model was trained and tested using traffic accident data of the United States from 2018–2022.The hybrid model first generates a small amount of categorical data via the Conditional Tabular Generative Adversarial Network to address the dataset’s category imbalance.Then,the balanced dataset is transformed into feature images using the DeepInsight method and feature extraction is performed using the residual neural network to improve the feature recognition ability of the classification model.Finally,the XGBoost model is used to classify the severity of the accident and the SHAP method is used to analyse the main features affecting the accident.The superior performance of the hybrid model is verified through experimental comparative analysis.The experimental results show that the hybrid model has a significant advantage in the prediction of driving risk for elderly drivers,that the causes of accidents for elderly drivers are different from those for younger drivers and that the characteristics of speed,seat belt use and driver’s age are the main factors affecting the severity of accidents.The results of this study improve the accuracy and reliability of traffic accident severity prediction and provide more scientific support for traffic safety management.
