数据可视化的完整流程包括数据采集、数据处理、数据分析及数据可视化4个环节。该文展示使用Power BI Desktop对豆瓣电影TOP250评分数据,进行多页面Web获取、处理及可视化展示的应用案例。首先,使用Power BI Desktop的M语言创建查询函数...数据可视化的完整流程包括数据采集、数据处理、数据分析及数据可视化4个环节。该文展示使用Power BI Desktop对豆瓣电影TOP250评分数据,进行多页面Web获取、处理及可视化展示的应用案例。首先,使用Power BI Desktop的M语言创建查询函数,通过添加列选择调用自定义函数,实现多页面Web数据源的连接与获取。接着,通过数据转换功能执行字段提取与数据类型转换,最终得到包含电影排名、名称、评分和上映年份等关键字段的数据表。最后,基于250部电影的评分数据创建数据可视化内容,包括柱形图、电影得分切片器及影片信息矩阵表格,根据电影评分数据为柱形图设置颜色递进效果,对切片器和影片信息矩阵表格添加联动效应,达到交互式的效果。展开更多
In order to make an intensive study of the development of smart power distribution and utilization technology in China, their research hotspots and frontier technology are selected out through combining the informatic...In order to make an intensive study of the development of smart power distribution and utilization technology in China, their research hotspots and frontier technology are selected out through combining the informatics method, and using the CiteSpace which can take keyword cooccurrence analysis and draw the visualization graph. According to this result, we can infer the development trend of smart power distribution and utilization in the future, and providing reference for the researcher whose engage in this domain. The electric related literature was collected from the CNKI database in China. Under the smart power distribution and utilization domain, we also analyze the development of the power quality and the energy internet in detail.展开更多
The visualization techniques were explored for power quality monitoring.And remote visualization solutions were proposed for highspeed rail power quality monitoring.Taking the Beijing-Shanghai highspeed rail power mon...The visualization techniques were explored for power quality monitoring.And remote visualization solutions were proposed for highspeed rail power quality monitoring.Taking the Beijing-Shanghai highspeed rail power monitoring as a study case,a remote visualization client,based on our proposed solutions,was developed for high-speed rail power quality monitoring to efficiently support power quality data analysis of the electricity business.The solutions collected data from monitoring stations deployed along the high-speed rail route and visualized the data set with a variety of visualization technologies to alert the specific stations of catastrophic events.The proposed solutions have been proved to be effective in supporting decision-making for the railway power scheduling and providing diagnosis information for quickly spotting any possible runtime failure in operation.展开更多
目的利用Power BI Desktop对医院DIP分组明细进行多维度对比分析及数据可视化,寻找医院DIP亏损原因。方法提取某三甲肿瘤专科医院2022年度部分出院结算DIP入组明细数据,通过数据导入、数据类型转换、建立数据关系、数据建模、数据可视...目的利用Power BI Desktop对医院DIP分组明细进行多维度对比分析及数据可视化,寻找医院DIP亏损原因。方法提取某三甲肿瘤专科医院2022年度部分出院结算DIP入组明细数据,通过数据导入、数据类型转换、建立数据关系、数据建模、数据可视化等方法,建立全院、科室、病种等多个维度的可视化动态分析报表。结果Power BI Desktop能有效提升DIP精细化管理水平,提升工作效率,精准分析亏损原因,指导科室进行改进,有效减少医院DIP医保资金亏损。结论Power BI Desktop具有成本低廉,定制化、可视化、自动化程度高,用户界面友好等特点,值得在各医院尤其是信息化程度低、专科运营人员不足、资金预算不足的医院DIP精细化管理中进行推广。展开更多
目的电力设备巡检影像缺陷检测对于提高电力传输的安全性和电网运行的可靠性具有重要作用。但由于相应训练数据集的构造成本高昂,传统的监督学习方法难以适应电力设备巡检影像缺陷检测。同时电力设备巡检影像中通常含有复杂多样的背景,...目的电力设备巡检影像缺陷检测对于提高电力传输的安全性和电网运行的可靠性具有重要作用。但由于相应训练数据集的构造成本高昂,传统的监督学习方法难以适应电力设备巡检影像缺陷检测。同时电力设备巡检影像中通常含有复杂多样的背景,严重干扰了模型对缺陷的检测。方法基于视觉语言模型并结合文本提示,提出了电力设备巡检影像零样本缺陷检测模型。模型中含有多个双专家模块,在由视觉语言模型获得文本特征和视觉特征后,经多个双专家模块处理并融合,得到像素级的缺陷检测结果。同时,构建了具有像素级掩码标注的电力设备巡检影像数据集对模型性能进行全面评测。结果在本文构建的电力设备巡检影像测试数据集上与SAA+(segment any anomaly+)、AnomalyGPT、WinCLIP(window-based CLIP)、PaDiM(patch distribution modeling)和PatchCore进行比较,在像素级的缺陷分割性能表现上,AUROC(area under the receiver operating characteristic curve)平均提升18.1%,F1-max(F1 score at optimal threshold)平均提升26.1%;在图像级的缺陷分类性能表现上,AUROC平均提升20.2%,AP(average precision)平均提升10.0%。具体到数据集中的各个电力设备,模型在像素级缺陷分割性能表现上,均获得最好结果。同时进行了消融实验,证明了双专家模块对提升模型缺陷检测精度的显著效果。结论本文模型以零样本的方式,避免了构造电力设备巡检影像数据集的高昂成本。同时提出的双专家模块,使模型减少了受巡检影像复杂背景区域的干扰。展开更多
Gestational Diabetes Mellitus (GDM) is a significant health concern affecting pregnant women worldwide. It is characterized by elevated blood sugar levels during pregnancy and poses risks to both maternal and fetal he...Gestational Diabetes Mellitus (GDM) is a significant health concern affecting pregnant women worldwide. It is characterized by elevated blood sugar levels during pregnancy and poses risks to both maternal and fetal health. Maternal complications of GDM include an increased risk of developing type 2 diabetes later in life, as well as hypertension and preeclampsia during pregnancy. Fetal complications may include macrosomia (large birth weight), birth injuries, and an increased risk of developing metabolic disorders later in life. Understanding the demographics, risk factors, and biomarkers associated with GDM is crucial for effective management and prevention strategies. This research aims to address these aspects comprehensively through the analysis of a dataset comprising 600 pregnant women. By exploring the demographics of the dataset and employing data modeling techniques, the study seeks to identify key risk factors associated with GDM. Moreover, by analyzing various biomarkers, the research aims to gain insights into the physiological mechanisms underlying GDM and its implications for maternal and fetal health. The significance of this research lies in its potential to inform clinical practice and public health policies related to GDM. By identifying demographic patterns and risk factors, healthcare providers can better tailor screening and intervention strategies for pregnant women at risk of GDM. Additionally, insights into biomarkers associated with GDM may contribute to the development of novel diagnostic tools and therapeutic approaches. Ultimately, by enhancing our understanding of GDM, this research aims to improve maternal and fetal outcomes and reduce the burden of this condition on healthcare systems and society. However, it’s important to acknowledge the limitations of the dataset used in this study. Further research utilizing larger and more diverse datasets, perhaps employing advanced data analysis techniques such as Power BI, is warranted to corroborate and expand upon the findings of this research. This underscores the ongoing need for continued investigation into GDM to refine our understanding and improve clinical management strategies.展开更多
文摘数据可视化的完整流程包括数据采集、数据处理、数据分析及数据可视化4个环节。该文展示使用Power BI Desktop对豆瓣电影TOP250评分数据,进行多页面Web获取、处理及可视化展示的应用案例。首先,使用Power BI Desktop的M语言创建查询函数,通过添加列选择调用自定义函数,实现多页面Web数据源的连接与获取。接着,通过数据转换功能执行字段提取与数据类型转换,最终得到包含电影排名、名称、评分和上映年份等关键字段的数据表。最后,基于250部电影的评分数据创建数据可视化内容,包括柱形图、电影得分切片器及影片信息矩阵表格,根据电影评分数据为柱形图设置颜色递进效果,对切片器和影片信息矩阵表格添加联动效应,达到交互式的效果。
文摘In order to make an intensive study of the development of smart power distribution and utilization technology in China, their research hotspots and frontier technology are selected out through combining the informatics method, and using the CiteSpace which can take keyword cooccurrence analysis and draw the visualization graph. According to this result, we can infer the development trend of smart power distribution and utilization in the future, and providing reference for the researcher whose engage in this domain. The electric related literature was collected from the CNKI database in China. Under the smart power distribution and utilization domain, we also analyze the development of the power quality and the energy internet in detail.
基金the State Grid Corporation and Computer Science Experimental Center of Beihang University,China
文摘The visualization techniques were explored for power quality monitoring.And remote visualization solutions were proposed for highspeed rail power quality monitoring.Taking the Beijing-Shanghai highspeed rail power monitoring as a study case,a remote visualization client,based on our proposed solutions,was developed for high-speed rail power quality monitoring to efficiently support power quality data analysis of the electricity business.The solutions collected data from monitoring stations deployed along the high-speed rail route and visualized the data set with a variety of visualization technologies to alert the specific stations of catastrophic events.The proposed solutions have been proved to be effective in supporting decision-making for the railway power scheduling and providing diagnosis information for quickly spotting any possible runtime failure in operation.
文摘目的利用Power BI Desktop对医院DIP分组明细进行多维度对比分析及数据可视化,寻找医院DIP亏损原因。方法提取某三甲肿瘤专科医院2022年度部分出院结算DIP入组明细数据,通过数据导入、数据类型转换、建立数据关系、数据建模、数据可视化等方法,建立全院、科室、病种等多个维度的可视化动态分析报表。结果Power BI Desktop能有效提升DIP精细化管理水平,提升工作效率,精准分析亏损原因,指导科室进行改进,有效减少医院DIP医保资金亏损。结论Power BI Desktop具有成本低廉,定制化、可视化、自动化程度高,用户界面友好等特点,值得在各医院尤其是信息化程度低、专科运营人员不足、资金预算不足的医院DIP精细化管理中进行推广。
文摘目的电力设备巡检影像缺陷检测对于提高电力传输的安全性和电网运行的可靠性具有重要作用。但由于相应训练数据集的构造成本高昂,传统的监督学习方法难以适应电力设备巡检影像缺陷检测。同时电力设备巡检影像中通常含有复杂多样的背景,严重干扰了模型对缺陷的检测。方法基于视觉语言模型并结合文本提示,提出了电力设备巡检影像零样本缺陷检测模型。模型中含有多个双专家模块,在由视觉语言模型获得文本特征和视觉特征后,经多个双专家模块处理并融合,得到像素级的缺陷检测结果。同时,构建了具有像素级掩码标注的电力设备巡检影像数据集对模型性能进行全面评测。结果在本文构建的电力设备巡检影像测试数据集上与SAA+(segment any anomaly+)、AnomalyGPT、WinCLIP(window-based CLIP)、PaDiM(patch distribution modeling)和PatchCore进行比较,在像素级的缺陷分割性能表现上,AUROC(area under the receiver operating characteristic curve)平均提升18.1%,F1-max(F1 score at optimal threshold)平均提升26.1%;在图像级的缺陷分类性能表现上,AUROC平均提升20.2%,AP(average precision)平均提升10.0%。具体到数据集中的各个电力设备,模型在像素级缺陷分割性能表现上,均获得最好结果。同时进行了消融实验,证明了双专家模块对提升模型缺陷检测精度的显著效果。结论本文模型以零样本的方式,避免了构造电力设备巡检影像数据集的高昂成本。同时提出的双专家模块,使模型减少了受巡检影像复杂背景区域的干扰。
文摘Gestational Diabetes Mellitus (GDM) is a significant health concern affecting pregnant women worldwide. It is characterized by elevated blood sugar levels during pregnancy and poses risks to both maternal and fetal health. Maternal complications of GDM include an increased risk of developing type 2 diabetes later in life, as well as hypertension and preeclampsia during pregnancy. Fetal complications may include macrosomia (large birth weight), birth injuries, and an increased risk of developing metabolic disorders later in life. Understanding the demographics, risk factors, and biomarkers associated with GDM is crucial for effective management and prevention strategies. This research aims to address these aspects comprehensively through the analysis of a dataset comprising 600 pregnant women. By exploring the demographics of the dataset and employing data modeling techniques, the study seeks to identify key risk factors associated with GDM. Moreover, by analyzing various biomarkers, the research aims to gain insights into the physiological mechanisms underlying GDM and its implications for maternal and fetal health. The significance of this research lies in its potential to inform clinical practice and public health policies related to GDM. By identifying demographic patterns and risk factors, healthcare providers can better tailor screening and intervention strategies for pregnant women at risk of GDM. Additionally, insights into biomarkers associated with GDM may contribute to the development of novel diagnostic tools and therapeutic approaches. Ultimately, by enhancing our understanding of GDM, this research aims to improve maternal and fetal outcomes and reduce the burden of this condition on healthcare systems and society. However, it’s important to acknowledge the limitations of the dataset used in this study. Further research utilizing larger and more diverse datasets, perhaps employing advanced data analysis techniques such as Power BI, is warranted to corroborate and expand upon the findings of this research. This underscores the ongoing need for continued investigation into GDM to refine our understanding and improve clinical management strategies.
