Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of...Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of the existing studies are based on graph neural networks that model traffic flow graphs and try to use fixed graph structure to deal with the relationship between nodes.However,due to the time-varying spatial correlation of the traffic network,there is no fixed node relationship,and these methods cannot effectively integrate the temporal and spatial features.This paper proposes a novel temporal-spatial dynamic graph convolutional network(TSADGCN).The dynamic time warping algorithm(DTW)is introduced to calculate the similarity of traffic flow sequence among network nodes in the time dimension,and the spatiotemporal graph of traffic flow is constructed to capture the spatiotemporal characteristics and dependencies of traffic flow.By combining graph attention network and time attention network,a spatiotemporal convolution block is constructed to capture spatiotemporal characteristics of traffic data.Experiments on open data sets PEMSD4 and PEMSD8 show that TSADGCN has higher prediction accuracy than well-known traffic flow prediction algorithms.展开更多
为了提高实时性和准确性,提出一种改进的动态时间规整算法(Dynamic Time Warping-DTW),用于度量手势运动轨迹的相似性,实现了快速的精确动态手势识别.首先,通过Kinect2传感器实时地获取人体骨架的关节点坐标和手部的形状数据,然后构造...为了提高实时性和准确性,提出一种改进的动态时间规整算法(Dynamic Time Warping-DTW),用于度量手势运动轨迹的相似性,实现了快速的精确动态手势识别.首先,通过Kinect2传感器实时地获取人体骨架的关节点坐标和手部的形状数据,然后构造矢量特征描述手的运动轨迹,运用动态时间规整方法进行模板匹配,并对特殊手势进行精确的二次分类,实现了基于轨迹匹配的快速动态手势识别.实验证明:该方法识别准确度高,实时性好,对光照强度和复杂背景干扰有很强的鲁棒性.展开更多
绕组变形是导致变压器故障的主要原因之一,频率响应分析法是一种常用的检测绕组变形故障的方法。文中针对实际应用中,因频率响应数据解释不足导致的绕组故障诊断效果不佳、抗噪性能差和故障程度指标与实际故障程度的单调性不良等问题,...绕组变形是导致变压器故障的主要原因之一,频率响应分析法是一种常用的检测绕组变形故障的方法。文中针对实际应用中,因频率响应数据解释不足导致的绕组故障诊断效果不佳、抗噪性能差和故障程度指标与实际故障程度的单调性不良等问题,提出了基于动态时间DTW(dynamic time warping)规整路径与K最邻近算法(KNN,K⁃nearest neighbor)的变压器绕组状态判别法、基于DTW偏离度的变压器绕组故障程度表征法。通过在一台实际变压器及一台模型变压器上的运用,验证了其在绕组状态判别及绕组故障程度表征方面的性能。通过对比实验,分析了该方法在绕组状态判别中的准确性,抗噪性,以及在故障程度表征上的灵敏性与线性相关性。结果表明,在这两个案例中,与现行变压器绕组故障诊断标准相比,文中方法有更高的准确率,更能反映变压器绕组变形故障的程度,有着更好的抗噪性能。展开更多
针对大多数手势识别算法对于形状变化较大的手势鲁棒性不强的现状,提出了一种基于DTW(Dynamic Time Warping)的手势识别算法。论文采用ASL手势数据集作为实验数据,通过图像预处理得到手势的轮廓,再对手势轮廓中心点到轮廓点的距离和轮...针对大多数手势识别算法对于形状变化较大的手势鲁棒性不强的现状,提出了一种基于DTW(Dynamic Time Warping)的手势识别算法。论文采用ASL手势数据集作为实验数据,通过图像预处理得到手势的轮廓,再对手势轮廓中心点到轮廓点的距离和轮廓曲率等特征进行提取,最后利用DTW算法寻找规整路径的方法进行识别。实验结果表明,利用DTW算法进行手势识别具有较高的准确率和鲁棒性,识别一幅图像中的手势平均时间小于0.1s,适合于实时手势识别。展开更多
基金supported by the National Natural Science Foundation of China(Grant:62176086).
文摘Traffic flow prediction plays a key role in the construction of intelligent transportation system.However,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very challenging.Most of the existing studies are based on graph neural networks that model traffic flow graphs and try to use fixed graph structure to deal with the relationship between nodes.However,due to the time-varying spatial correlation of the traffic network,there is no fixed node relationship,and these methods cannot effectively integrate the temporal and spatial features.This paper proposes a novel temporal-spatial dynamic graph convolutional network(TSADGCN).The dynamic time warping algorithm(DTW)is introduced to calculate the similarity of traffic flow sequence among network nodes in the time dimension,and the spatiotemporal graph of traffic flow is constructed to capture the spatiotemporal characteristics and dependencies of traffic flow.By combining graph attention network and time attention network,a spatiotemporal convolution block is constructed to capture spatiotemporal characteristics of traffic data.Experiments on open data sets PEMSD4 and PEMSD8 show that TSADGCN has higher prediction accuracy than well-known traffic flow prediction algorithms.
文摘为了提高实时性和准确性,提出一种改进的动态时间规整算法(Dynamic Time Warping-DTW),用于度量手势运动轨迹的相似性,实现了快速的精确动态手势识别.首先,通过Kinect2传感器实时地获取人体骨架的关节点坐标和手部的形状数据,然后构造矢量特征描述手的运动轨迹,运用动态时间规整方法进行模板匹配,并对特殊手势进行精确的二次分类,实现了基于轨迹匹配的快速动态手势识别.实验证明:该方法识别准确度高,实时性好,对光照强度和复杂背景干扰有很强的鲁棒性.
文摘绕组变形是导致变压器故障的主要原因之一,频率响应分析法是一种常用的检测绕组变形故障的方法。文中针对实际应用中,因频率响应数据解释不足导致的绕组故障诊断效果不佳、抗噪性能差和故障程度指标与实际故障程度的单调性不良等问题,提出了基于动态时间DTW(dynamic time warping)规整路径与K最邻近算法(KNN,K⁃nearest neighbor)的变压器绕组状态判别法、基于DTW偏离度的变压器绕组故障程度表征法。通过在一台实际变压器及一台模型变压器上的运用,验证了其在绕组状态判别及绕组故障程度表征方面的性能。通过对比实验,分析了该方法在绕组状态判别中的准确性,抗噪性,以及在故障程度表征上的灵敏性与线性相关性。结果表明,在这两个案例中,与现行变压器绕组故障诊断标准相比,文中方法有更高的准确率,更能反映变压器绕组变形故障的程度,有着更好的抗噪性能。
文摘针对大多数手势识别算法对于形状变化较大的手势鲁棒性不强的现状,提出了一种基于DTW(Dynamic Time Warping)的手势识别算法。论文采用ASL手势数据集作为实验数据,通过图像预处理得到手势的轮廓,再对手势轮廓中心点到轮廓点的距离和轮廓曲率等特征进行提取,最后利用DTW算法寻找规整路径的方法进行识别。实验结果表明,利用DTW算法进行手势识别具有较高的准确率和鲁棒性,识别一幅图像中的手势平均时间小于0.1s,适合于实时手势识别。