To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to imp...To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to improve its information management and increase the availability of accurate, real-time data for disaster and humanitarian response teams, significant gaps persist. There are inefficiencies in the emergency management of data at every stage of its lifecycle: collection, processing, analysis, distribution, storage, and retrieval. Disaster risk reduction and disaster risk management are the two main tenets of the United Nations’ worldwide plan for disaster management. Information systems are crucial because of the crucial roles they play in capturing, processing, and transmitting data. The management of information is seldom discussed in published works. The goal of this study is to employ qualitative research methods to provide insight by facilitating an expanded comprehension of relevant contexts, phenomena, and individual experiences. Humanitarian workers and OCHA staffers will take part in the research. The study subjects will be chosen using a random selection procedure. Online surveys with both closed- and open-ended questions will be used to compile the data. UN OCHA offers a structure for the handling of information via which all humanitarian actors may contribute to the overall response. This research will enable the UN Office for OCHA better gather, process, analyze, disseminate, store, and retrieve data in the event of a catastrophe or humanitarian crisis.展开更多
目的:构建基于人工智能的高血压性脑出血医疗文本信息自动识别系统,快速识别和分析患者临床信息,高效地输出正确的诊疗方案。方法:基于国内外最新高血压性脑出血诊疗指南,经多位高年资神经外科医生和专业人工智能团队共同讨论,构建基于...目的:构建基于人工智能的高血压性脑出血医疗文本信息自动识别系统,快速识别和分析患者临床信息,高效地输出正确的诊疗方案。方法:基于国内外最新高血压性脑出血诊疗指南,经多位高年资神经外科医生和专业人工智能团队共同讨论,构建基于语言表征模型和专家模块的高血压性脑出血医疗文本信息自动识别及决策系统(即H系统)。随后将收集到的高血压性脑出血病例分为训练集、测试集和验证集,以数据库中病例的真实治疗方案为金标准,先总体评价H系统的准确性,再将其与神经外科医生进行对比,分析H系统的判读效率。结果:在测试集中,H系统所输出的治疗方案的准确率为94.0%(91.5%~96.5%),特异度为91.8%(86.3%~97.3%),灵敏度为95.5%(89.3%~98.2%),曲线下面积(area under the curve,AUC)值为0.936(0.922~0.950)(P=0.000);在验证集中,H系统所输出的治疗方案的准确率为93.3%(89.5%~97.1%),特异度为89.9%(83.4%~96.4%),灵敏度为95.8%(92.3%~99.3%),AUC值为0.928(0.891~0.966)(P=0.000)。在处理同样的70例病例时,H系统用时(334.60±4.46)s,而神经外科医生用时(12 550.28±95.45)s;在50 min内,H系统处理的病例数为(383±3)例,而神经外科医生处理的病例数为(11±4)例。结论:本研究所构建的H系统能够对高血压性脑出血患者的急诊病例进行自动识别和分析,并快速输出准确的诊疗方案,可协助医生对高血压脑出血进行急诊诊疗。展开更多
为使水量水质模型标准化、模块化,更方便、快捷地跟地理信息系统耦合,提出一种以DEM为计算网格,纳入对DEM进行前处理的GIS(Geographic Information System)算法,采用同位网格布置变量,使用有限体积法离散方程,SIMPLEC法求解运动方程的...为使水量水质模型标准化、模块化,更方便、快捷地跟地理信息系统耦合,提出一种以DEM为计算网格,纳入对DEM进行前处理的GIS(Geographic Information System)算法,采用同位网格布置变量,使用有限体积法离散方程,SIMPLEC法求解运动方程的新水量水质模型算法,并详细论述了该算法在使用DEM后,在水体识别、边界生成、初边条件、动边界处理和代数方程组求解等方面的处理方法.最后,将该算法应用于三峡水库突发性水污染事件应急响应系统的水量水质模型模块,证明该算法准确可靠,可与GIS系统从网格层次无缝耦合,在资料输入时能省略前处理步骤,系统能快速移用于不同的水域,具有较大的实用价值.展开更多
文摘To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to improve its information management and increase the availability of accurate, real-time data for disaster and humanitarian response teams, significant gaps persist. There are inefficiencies in the emergency management of data at every stage of its lifecycle: collection, processing, analysis, distribution, storage, and retrieval. Disaster risk reduction and disaster risk management are the two main tenets of the United Nations’ worldwide plan for disaster management. Information systems are crucial because of the crucial roles they play in capturing, processing, and transmitting data. The management of information is seldom discussed in published works. The goal of this study is to employ qualitative research methods to provide insight by facilitating an expanded comprehension of relevant contexts, phenomena, and individual experiences. Humanitarian workers and OCHA staffers will take part in the research. The study subjects will be chosen using a random selection procedure. Online surveys with both closed- and open-ended questions will be used to compile the data. UN OCHA offers a structure for the handling of information via which all humanitarian actors may contribute to the overall response. This research will enable the UN Office for OCHA better gather, process, analyze, disseminate, store, and retrieve data in the event of a catastrophe or humanitarian crisis.
文摘目的:构建基于人工智能的高血压性脑出血医疗文本信息自动识别系统,快速识别和分析患者临床信息,高效地输出正确的诊疗方案。方法:基于国内外最新高血压性脑出血诊疗指南,经多位高年资神经外科医生和专业人工智能团队共同讨论,构建基于语言表征模型和专家模块的高血压性脑出血医疗文本信息自动识别及决策系统(即H系统)。随后将收集到的高血压性脑出血病例分为训练集、测试集和验证集,以数据库中病例的真实治疗方案为金标准,先总体评价H系统的准确性,再将其与神经外科医生进行对比,分析H系统的判读效率。结果:在测试集中,H系统所输出的治疗方案的准确率为94.0%(91.5%~96.5%),特异度为91.8%(86.3%~97.3%),灵敏度为95.5%(89.3%~98.2%),曲线下面积(area under the curve,AUC)值为0.936(0.922~0.950)(P=0.000);在验证集中,H系统所输出的治疗方案的准确率为93.3%(89.5%~97.1%),特异度为89.9%(83.4%~96.4%),灵敏度为95.8%(92.3%~99.3%),AUC值为0.928(0.891~0.966)(P=0.000)。在处理同样的70例病例时,H系统用时(334.60±4.46)s,而神经外科医生用时(12 550.28±95.45)s;在50 min内,H系统处理的病例数为(383±3)例,而神经外科医生处理的病例数为(11±4)例。结论:本研究所构建的H系统能够对高血压性脑出血患者的急诊病例进行自动识别和分析,并快速输出准确的诊疗方案,可协助医生对高血压脑出血进行急诊诊疗。
文摘为使水量水质模型标准化、模块化,更方便、快捷地跟地理信息系统耦合,提出一种以DEM为计算网格,纳入对DEM进行前处理的GIS(Geographic Information System)算法,采用同位网格布置变量,使用有限体积法离散方程,SIMPLEC法求解运动方程的新水量水质模型算法,并详细论述了该算法在使用DEM后,在水体识别、边界生成、初边条件、动边界处理和代数方程组求解等方面的处理方法.最后,将该算法应用于三峡水库突发性水污染事件应急响应系统的水量水质模型模块,证明该算法准确可靠,可与GIS系统从网格层次无缝耦合,在资料输入时能省略前处理步骤,系统能快速移用于不同的水域,具有较大的实用价值.
