The earthquake early warning(EEW)system provides advance notice of potentially damaging ground shaking.In EEW,early estimation of magnitude is crucial for timely rescue operations.A set of thirty-four features is extr...The earthquake early warning(EEW)system provides advance notice of potentially damaging ground shaking.In EEW,early estimation of magnitude is crucial for timely rescue operations.A set of thirty-four features is extracted using the primary wave earthquake precursor signal and site-specific information.In Japan's earthquake magnitude dataset,there is a chance of a high imbalance concerning the earthquakes above strong impact.This imbalance causes a high prediction error while training advanced machine learning or deep learning models.In this work,Conditional Tabular Generative Adversarial Networks(CTGAN),a deep machine learning tool,is utilized to learn the characteristics of the first arrival of earthquake P-waves and generate a synthetic dataset based on this information.The result obtained using actual and mixed(synthetic and actual)datasets will be used for training the stacked ensemble magnitude prediction model,MagPred,designed specifically for this study.There are 13295,3989,and1710 records designated for training,testing,and validation.The mean absolute error of the test dataset for single station magnitude detection using early three,four,and five seconds of P wave are 0.41,0.40,and 0.38 MJMA.The study demonstrates that the Generative Adversarial Networks(GANs)can provide a good result for single-station magnitude prediction.The study can be effective where less seismic data is available.The study shows that the machine learning method yields better magnitude detection results compared with the several regression models.The multi-station magnitude prediction study has been conducted on prominent Osaka,Off Fukushima,and Kumamoto earthquakes.Furthermore,to validate the performance of the model,an inter-region study has been performed on the earthquakes of the India or Nepal region.The study demonstrates that GANs can discover effective magnitude estimation compared with non-GAN-based methods.This has a high potential for wide application in earthquake early warning systems.展开更多
人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗...人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗网络(CTGAN)的混合生成模型(VCTGAN),用于合成高质量平衡数据集。通过VAE中的隐变量学习真实数据的关键特征和潜在分布,生成结构化隐变量作为原始CTGAN的输入;在数据生成器中引入自注意力机制用于更好地捕捉不平衡数据的突出特征;在判别器中加入对比损失模块来增强生成数据的类别间差异,达到提高生成数据质量的目的。通过在Taiwan Credit和Give Me Some Credit两个基准数据集上的系统实验验证,分别取得了89.91%和96.89%的最佳分类准确率,结果表明这种改进方法在处理信用数据不平衡方面明显优于传统方法。消融实验进一步验证了各组件对性能的贡献,证实了所提方法的合理性和有效性。它不仅生成高质量的平衡数据集,而且提高模型识别少数类别的能力,为解决金融领域的数据不平衡问题提供了新的技术方案。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related to grant PM-31-22-626-414 from the Prime Minister's Research Fellows(PMRF)of the Indian Institute of Technology Roorkee。
文摘The earthquake early warning(EEW)system provides advance notice of potentially damaging ground shaking.In EEW,early estimation of magnitude is crucial for timely rescue operations.A set of thirty-four features is extracted using the primary wave earthquake precursor signal and site-specific information.In Japan's earthquake magnitude dataset,there is a chance of a high imbalance concerning the earthquakes above strong impact.This imbalance causes a high prediction error while training advanced machine learning or deep learning models.In this work,Conditional Tabular Generative Adversarial Networks(CTGAN),a deep machine learning tool,is utilized to learn the characteristics of the first arrival of earthquake P-waves and generate a synthetic dataset based on this information.The result obtained using actual and mixed(synthetic and actual)datasets will be used for training the stacked ensemble magnitude prediction model,MagPred,designed specifically for this study.There are 13295,3989,and1710 records designated for training,testing,and validation.The mean absolute error of the test dataset for single station magnitude detection using early three,four,and five seconds of P wave are 0.41,0.40,and 0.38 MJMA.The study demonstrates that the Generative Adversarial Networks(GANs)can provide a good result for single-station magnitude prediction.The study can be effective where less seismic data is available.The study shows that the machine learning method yields better magnitude detection results compared with the several regression models.The multi-station magnitude prediction study has been conducted on prominent Osaka,Off Fukushima,and Kumamoto earthquakes.Furthermore,to validate the performance of the model,an inter-region study has been performed on the earthquakes of the India or Nepal region.The study demonstrates that GANs can discover effective magnitude estimation compared with non-GAN-based methods.This has a high potential for wide application in earthquake early warning systems.
文摘人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗网络(CTGAN)的混合生成模型(VCTGAN),用于合成高质量平衡数据集。通过VAE中的隐变量学习真实数据的关键特征和潜在分布,生成结构化隐变量作为原始CTGAN的输入;在数据生成器中引入自注意力机制用于更好地捕捉不平衡数据的突出特征;在判别器中加入对比损失模块来增强生成数据的类别间差异,达到提高生成数据质量的目的。通过在Taiwan Credit和Give Me Some Credit两个基准数据集上的系统实验验证,分别取得了89.91%和96.89%的最佳分类准确率,结果表明这种改进方法在处理信用数据不平衡方面明显优于传统方法。消融实验进一步验证了各组件对性能的贡献,证实了所提方法的合理性和有效性。它不仅生成高质量的平衡数据集,而且提高模型识别少数类别的能力,为解决金融领域的数据不平衡问题提供了新的技术方案。
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.
