针对数据挖掘结果集数量巨大的特点,基于Focus+Context人机交互可视化技术实现结果集的B roadV iew and D etail on D em and导航可以有效帮助对挖掘结果的聚焦与探询,进而帮助用户快速找到所需要的信息。给出了基于规则层次凝聚类与Foc...针对数据挖掘结果集数量巨大的特点,基于Focus+Context人机交互可视化技术实现结果集的B roadV iew and D etail on D em and导航可以有效帮助对挖掘结果的聚焦与探询,进而帮助用户快速找到所需要的信息。给出了基于规则层次凝聚类与Focus+Context技术的可视化系统方法与原形系统,有效地解决了巨量规则的有效浏览与可视化问题,避免了直接对规则元素图形显示效果不佳的问题,从而有利于挖掘的应用。展开更多
Objective:Analyze the research hotspots and frontiers of shared outpatient service,and provide a reference for researchers in this field to carry out follow-up research.Methods:Search the Web of Science core collectio...Objective:Analyze the research hotspots and frontiers of shared outpatient service,and provide a reference for researchers in this field to carry out follow-up research.Methods:Search the Web of Science core collection database until 2022 and visually analyzekeywords in this field through CiteSpace5.8.R3 software,Results:A total of 261 iteratures were included.The research focuses mainly on advanced care planning,diabetes care,andgroup prenatal care,The research trend tends to be telemedicine and nursing provided by specialized nurses.Conclusion:Scholars can learn from the research hotspots of foreign shared medical appointments,pay attention to the research trend,expand its application scope in combination with China's national conditions,and further promote thedevelopment of shared medical appointments in China.展开更多
基金SuppoSed by the National Natural Science Foundation of China under Grant Nos.6067319560703078(国家自然科学基金)+2 种基金the National High-Tech Research and Development Plan of China under Grant No.2007AA04Z113(国家高技术研究发展计划(863))the National Basic Research Program of China under Grant No.2006CB303105(国家重点基础研究发展规划(973))the National Key Technology R&D Program of China under Grant No.2006BAF01A17(国家科技支撑计划)
文摘针对数据挖掘结果集数量巨大的特点,基于Focus+Context人机交互可视化技术实现结果集的B roadV iew and D etail on D em and导航可以有效帮助对挖掘结果的聚焦与探询,进而帮助用户快速找到所需要的信息。给出了基于规则层次凝聚类与Focus+Context技术的可视化系统方法与原形系统,有效地解决了巨量规则的有效浏览与可视化问题,避免了直接对规则元素图形显示效果不佳的问题,从而有利于挖掘的应用。
文摘Objective:Analyze the research hotspots and frontiers of shared outpatient service,and provide a reference for researchers in this field to carry out follow-up research.Methods:Search the Web of Science core collection database until 2022 and visually analyzekeywords in this field through CiteSpace5.8.R3 software,Results:A total of 261 iteratures were included.The research focuses mainly on advanced care planning,diabetes care,andgroup prenatal care,The research trend tends to be telemedicine and nursing provided by specialized nurses.Conclusion:Scholars can learn from the research hotspots of foreign shared medical appointments,pay attention to the research trend,expand its application scope in combination with China's national conditions,and further promote thedevelopment of shared medical appointments in China.
文摘识别非驾驶行为是提高驾驶安全性的重要手段之一。目前基于骨架序列和图像的融合识别方法具有计算量大和特征融合困难的问题。针对上述问题,本文提出一种基于多尺度骨架图和局部视觉上下文融合的驾驶员行为识别模型(skeleton-image based behavior recognition network,SIBBR-Net)。SIBBR-Net通过基于多尺度图的图卷积网络和基于局部视觉及注意力机制的卷积神经网络,充分提取运动和外观特征,较好地平衡了模型表征能力和计算量间的关系。基于手部运动的特征双向引导学习策略、自适应特征融合模块和静态特征空间上的辅助损失,使运动和外观特征间互相引导更新并实现自适应融合。最终在Drive&Act数据集进行算法测试,SIBBR-Net在动态标签和静态标签条件下的平均正确率分别为61.78%和80.42%,每秒浮点运算次数为25.92G,较最优方法降低了76.96%。