电力系统的安全稳定运行是保障国家能源安全和经济发展的关键,而这在很大程度上依赖于对电力物联设备故障的准确预测。当前,随着电力物联网技术的发展,大量的数据被采集,但这些数据的潜在价值尚未得到充分挖掘,这在一定程度上限制了故...电力系统的安全稳定运行是保障国家能源安全和经济发展的关键,而这在很大程度上依赖于对电力物联设备故障的准确预测。当前,随着电力物联网技术的发展,大量的数据被采集,但这些数据的潜在价值尚未得到充分挖掘,这在一定程度上限制了故障预测的准确性,影响了电力系统的可靠运行。针对这一问题,该文提出了一种创新的基于GraphSAGE(Graph Sample and Aggregate)算法的电力物联设备故障预测。该方法通过PowerGraph数据集,将电力物联设备故障场景细分为四类,利用GraphSAGE模型的特性,深入学习和分析节点特征与边特征,从而实现对物联设备故障的有效预测。实验结果表明,该方法准确率达到97.5%,相较于其它传统方法,准确率提高了0.39%~6.21%,同时GraphSAGE模型实现了快速训练。该方法为电力物联设备安全稳定运行提供重要决策支持,能够对动态和相互联系的复杂系统进行更精细的分析,并增强电力系统运营部门对潜在干扰的预见和应对能力。展开更多
环状RNA (circRNA)是一类内源性的非编码RNA,许多研究表明circRNA在复杂疾病中发挥着重要作用。然而,由于circRNA的功能复杂性和实验验证的高成本,传统的实验方法难以高效挖掘circRNA与疾病的关联关系,因此迫切需要高效的计算方法来揭示...环状RNA (circRNA)是一类内源性的非编码RNA,许多研究表明circRNA在复杂疾病中发挥着重要作用。然而,由于circRNA的功能复杂性和实验验证的高成本,传统的实验方法难以高效挖掘circRNA与疾病的关联关系,因此迫切需要高效的计算方法来揭示circRNA与疾病的关联关系。在现有数据库的基础上,本文提出了一种基于GraphSAGE模型的circRNA与疾病关联预测方法,通过整合circRNA相似性、疾病相似性以及已知的circRNA-disease关联数据构建异质图,随后借助GraphSAGE模型获得异质图中节点对应特征的高阶聚合表示,从而有效预测circRNA-disease关联。实验结果表明,GraphSAGE模型的AUC值为0.921,F1-score为0.865,Precision为0.879,Recall为0.852,以上四个评估指标均优于现有的DWNN-RLS和RWR模型。总之,GraphSAGE是预测circRNA-disease关联的有效方法。Circular RNA (circRNA) is a class of endogenous non-coding RNAs. Many studies have shown that circRNA plays an important role in complex diseases. However, due to the functional complexity of circRNA and the high cost of experimental verification, it is difficult for traditional experimental methods to efficiently mine the association between circRNA and disease, so efficient computational methods are urgently needed to reveal the association between circRNA and disease. Based on the existing database, this paper proposed a method for predicting the association between circRNA and disease based on GraphSAGE model. By integrating circRNA similarity, disease similarity and known circRNA-disease association data, a heterogeneous graph network was constructed, and then a high-level aggregated representation of the corresponding features of nodes in the heterogeneous graph network was obtained by GraphSAGE model, so as to effectively predict the circRNA-disease association. The experimental results demonstrate that the GraphSAGE model achieves an AUC of 0.921, F1-score of 0.865, Precision of 0.879 and Recall of 0.852, all of which were better than the existing DWNN-RLS and RWR models. In conclusion, GraphSAGE is an effective method to predict the association of circRNA-disease.展开更多
当前Web追踪领域主要使用浏览器指纹对用户进行追踪。针对浏览器指纹追踪技术存在指纹随时间动态变化、不易长期追踪等问题,提出一种关注节点和边缘特征的改进图采样聚合算法(An Improved Graph SAmple and AGgregatE with Both Node an...当前Web追踪领域主要使用浏览器指纹对用户进行追踪。针对浏览器指纹追踪技术存在指纹随时间动态变化、不易长期追踪等问题,提出一种关注节点和边缘特征的改进图采样聚合算法(An Improved Graph SAmple and AGgregatE with Both Node and Edge Features,NE-GraphSAGE)用于浏览器指纹追踪。首先以浏览器指纹为节点、指纹之间特征相似度为边构建图数据。其次对图神经网络中的GraphSAGE算法进行改进使其不仅能关注节点特征,而且能捕获边缘信息并对边缘分类,从而识别指纹。最后将NE-GraphSAGE算法与Eckersley算法、FPStalker算法和LSTM算法进行对比,验证NE-GraphSAGE算法的识别效果。实验结果表明,NE-GraphSAGE算法在准确率和追踪时长上均有不同程度的提升,最大追踪时长可达80天,相比其他3种算法性能更优,验证了NE-GraphSAGE算法对浏览器指纹长期追踪的能力。展开更多
Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for...Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for new biomarkers to enable early detection of DKD. In this study, we modeled publicly available transcriptome datasets as a graph problem and used GraphSAGE Neural Networks (GNNs) to identify potential biomarkers. The GraphSAGE model effectively learned representations that captured the intricate interactions, dependencies among genes, and disease-specific gene expression patterns necessary to classify samples as DKD and Control. We finally extracted the features of importance;the identified set of genes exhibited an impressive ability to distinguish between healthy and unhealthy samples, even though these genes differ from previous research findings. The unexpected biomarker variations in this study suggest more exploration and validation studies for discovering biomarkers in DKD. In conclusion, our study showcases the effectiveness of modeling transcriptome data as a graph problem, demonstrates the use of GraphSAGE models for biomarker discovery in DKD, and advocates for integrating advanced machine-learning techniques in DKD biomarker research, emphasizing the need for a holistic approach to unravel the intricacies of biological systems.展开更多
Data-driven prediction of time series is significant in many scientific research fields such as global climate change and weather forecast.For global monthly mean temperature series,considering the strong potential of...Data-driven prediction of time series is significant in many scientific research fields such as global climate change and weather forecast.For global monthly mean temperature series,considering the strong potential of deep neural network for extracting data features,this paper proposes a data-driven model,ResGraphNet,which improves the prediction accuracy of time series by an embedded residual module in GraphSAGE layers.The experimental results of a global mean temperature dataset,HadCRUT5,show that compared with 11 traditional prediction technologies,the proposed ResGraphNet obtains the best accuracy.The error indicator predicted by the proposed ResGraphNet is smaller than that of the other 11 prediction models.Furthermore,the performance on seven temperature datasets shows the excellent generalization of the ResGraphNet.Finally,based on our proposed ResGraphNet,the predicted 2022 annual anomaly of global temperature is 0.74722℃,which provides confidence for limiting warming to 1.5℃ above pre-industrial levels.展开更多
文摘电力系统的安全稳定运行是保障国家能源安全和经济发展的关键,而这在很大程度上依赖于对电力物联设备故障的准确预测。当前,随着电力物联网技术的发展,大量的数据被采集,但这些数据的潜在价值尚未得到充分挖掘,这在一定程度上限制了故障预测的准确性,影响了电力系统的可靠运行。针对这一问题,该文提出了一种创新的基于GraphSAGE(Graph Sample and Aggregate)算法的电力物联设备故障预测。该方法通过PowerGraph数据集,将电力物联设备故障场景细分为四类,利用GraphSAGE模型的特性,深入学习和分析节点特征与边特征,从而实现对物联设备故障的有效预测。实验结果表明,该方法准确率达到97.5%,相较于其它传统方法,准确率提高了0.39%~6.21%,同时GraphSAGE模型实现了快速训练。该方法为电力物联设备安全稳定运行提供重要决策支持,能够对动态和相互联系的复杂系统进行更精细的分析,并增强电力系统运营部门对潜在干扰的预见和应对能力。
文摘环状RNA (circRNA)是一类内源性的非编码RNA,许多研究表明circRNA在复杂疾病中发挥着重要作用。然而,由于circRNA的功能复杂性和实验验证的高成本,传统的实验方法难以高效挖掘circRNA与疾病的关联关系,因此迫切需要高效的计算方法来揭示circRNA与疾病的关联关系。在现有数据库的基础上,本文提出了一种基于GraphSAGE模型的circRNA与疾病关联预测方法,通过整合circRNA相似性、疾病相似性以及已知的circRNA-disease关联数据构建异质图,随后借助GraphSAGE模型获得异质图中节点对应特征的高阶聚合表示,从而有效预测circRNA-disease关联。实验结果表明,GraphSAGE模型的AUC值为0.921,F1-score为0.865,Precision为0.879,Recall为0.852,以上四个评估指标均优于现有的DWNN-RLS和RWR模型。总之,GraphSAGE是预测circRNA-disease关联的有效方法。Circular RNA (circRNA) is a class of endogenous non-coding RNAs. Many studies have shown that circRNA plays an important role in complex diseases. However, due to the functional complexity of circRNA and the high cost of experimental verification, it is difficult for traditional experimental methods to efficiently mine the association between circRNA and disease, so efficient computational methods are urgently needed to reveal the association between circRNA and disease. Based on the existing database, this paper proposed a method for predicting the association between circRNA and disease based on GraphSAGE model. By integrating circRNA similarity, disease similarity and known circRNA-disease association data, a heterogeneous graph network was constructed, and then a high-level aggregated representation of the corresponding features of nodes in the heterogeneous graph network was obtained by GraphSAGE model, so as to effectively predict the circRNA-disease association. The experimental results demonstrate that the GraphSAGE model achieves an AUC of 0.921, F1-score of 0.865, Precision of 0.879 and Recall of 0.852, all of which were better than the existing DWNN-RLS and RWR models. In conclusion, GraphSAGE is an effective method to predict the association of circRNA-disease.
文摘当前Web追踪领域主要使用浏览器指纹对用户进行追踪。针对浏览器指纹追踪技术存在指纹随时间动态变化、不易长期追踪等问题,提出一种关注节点和边缘特征的改进图采样聚合算法(An Improved Graph SAmple and AGgregatE with Both Node and Edge Features,NE-GraphSAGE)用于浏览器指纹追踪。首先以浏览器指纹为节点、指纹之间特征相似度为边构建图数据。其次对图神经网络中的GraphSAGE算法进行改进使其不仅能关注节点特征,而且能捕获边缘信息并对边缘分类,从而识别指纹。最后将NE-GraphSAGE算法与Eckersley算法、FPStalker算法和LSTM算法进行对比,验证NE-GraphSAGE算法的识别效果。实验结果表明,NE-GraphSAGE算法在准确率和追踪时长上均有不同程度的提升,最大追踪时长可达80天,相比其他3种算法性能更优,验证了NE-GraphSAGE算法对浏览器指纹长期追踪的能力。
文摘Diabetic Kidney Disease (DKD) is a common chronic complication of diabetes. Despite advancements in accurately identifying biomarkers for detecting and diagnosing this harmful disease, there remains an urgent need for new biomarkers to enable early detection of DKD. In this study, we modeled publicly available transcriptome datasets as a graph problem and used GraphSAGE Neural Networks (GNNs) to identify potential biomarkers. The GraphSAGE model effectively learned representations that captured the intricate interactions, dependencies among genes, and disease-specific gene expression patterns necessary to classify samples as DKD and Control. We finally extracted the features of importance;the identified set of genes exhibited an impressive ability to distinguish between healthy and unhealthy samples, even though these genes differ from previous research findings. The unexpected biomarker variations in this study suggest more exploration and validation studies for discovering biomarkers in DKD. In conclusion, our study showcases the effectiveness of modeling transcriptome data as a graph problem, demonstrates the use of GraphSAGE models for biomarker discovery in DKD, and advocates for integrating advanced machine-learning techniques in DKD biomarker research, emphasizing the need for a holistic approach to unravel the intricacies of biological systems.
基金Supported by the National Natural Science Foundation of China under Grant 41974137.
文摘Data-driven prediction of time series is significant in many scientific research fields such as global climate change and weather forecast.For global monthly mean temperature series,considering the strong potential of deep neural network for extracting data features,this paper proposes a data-driven model,ResGraphNet,which improves the prediction accuracy of time series by an embedded residual module in GraphSAGE layers.The experimental results of a global mean temperature dataset,HadCRUT5,show that compared with 11 traditional prediction technologies,the proposed ResGraphNet obtains the best accuracy.The error indicator predicted by the proposed ResGraphNet is smaller than that of the other 11 prediction models.Furthermore,the performance on seven temperature datasets shows the excellent generalization of the ResGraphNet.Finally,based on our proposed ResGraphNet,the predicted 2022 annual anomaly of global temperature is 0.74722℃,which provides confidence for limiting warming to 1.5℃ above pre-industrial levels.
