Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction acc...Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.展开更多
As an important part of future 5G wireless networks,a vehicular network demands safety,reliability and connectivity.In this context,networking survivability is usually considered an important metric to evaluate networ...As an important part of future 5G wireless networks,a vehicular network demands safety,reliability and connectivity.In this context,networking survivability is usually considered an important metric to evaluate network performance.In this paper,we propose a survivability model for vehicle communication networking based on dual cluster heads,wherein a backup cluster head(CH)will be activated if the primary CH fails,thereby effectively enhancing the network lifetime.Additionally,we introduce a software rejuvenation strategy for the prime CH to further improve the survivability of the entire network.Using the Probabilistic Symbolic Model Checker(PRISM),we verify and discuss the proposed survivability model via numerical simulations.The results show that network survivability can be effectively improved by introducing an additional CH and further enhanced by adopting the software rejuvenation technique.展开更多
目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的...目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的空间特征;然后利用基于多头注意力的递归神经网络生成多上下文向量进行高层抽象特征提取;最后利用全连接层进行情感分类。在DEAP(Database for Emotion Analysis using Physiological signals)数据集上进行实验,CR-MCV在唤醒和效价维度上分类准确率分别为88.09%和89.30%。实验结果表明,CR-MCV在利用电极空间位置信息和不同时段情感状态显著性特征基础上,能够自适应地分配特征的注意力并强化情感状态显著性信息。展开更多
文摘Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.
基金supported by the National Natural Science Foundation of China (No. 61971245 and 61801249 )Nantong University-Nantong Joint Research Center for Intelligent Information Technology (No. KFKT2016A01)
文摘As an important part of future 5G wireless networks,a vehicular network demands safety,reliability and connectivity.In this context,networking survivability is usually considered an important metric to evaluate network performance.In this paper,we propose a survivability model for vehicle communication networking based on dual cluster heads,wherein a backup cluster head(CH)will be activated if the primary CH fails,thereby effectively enhancing the network lifetime.Additionally,we introduce a software rejuvenation strategy for the prime CH to further improve the survivability of the entire network.Using the Probabilistic Symbolic Model Checker(PRISM),we verify and discuss the proposed survivability model via numerical simulations.The results show that network survivability can be effectively improved by introducing an additional CH and further enhanced by adopting the software rejuvenation technique.
文摘目前的脑电(EEG)情感识别模型忽略了不同时段情感状态的差异性,未能强化关键的情感信息。针对上述问题,提出一种多上下文向量优化的卷积递归神经网络(CR-MCV)。首先构造脑电信号的特征矩阵序列,通过卷积神经网络(CNN)学习多通道脑电的空间特征;然后利用基于多头注意力的递归神经网络生成多上下文向量进行高层抽象特征提取;最后利用全连接层进行情感分类。在DEAP(Database for Emotion Analysis using Physiological signals)数据集上进行实验,CR-MCV在唤醒和效价维度上分类准确率分别为88.09%和89.30%。实验结果表明,CR-MCV在利用电极空间位置信息和不同时段情感状态显著性特征基础上,能够自适应地分配特征的注意力并强化情感状态显著性信息。
