目的评价决策辅助工具在乳房重建患者中的应用效果。方法计算机检索Cochrane Library、PubMed、Web of Science、Embase、中国生物医学文献数据库、中国知网、维普、万方数据库中有关决策辅助工具在乳房重建患者中应用效果的随机对照试...目的评价决策辅助工具在乳房重建患者中的应用效果。方法计算机检索Cochrane Library、PubMed、Web of Science、Embase、中国生物医学文献数据库、中国知网、维普、万方数据库中有关决策辅助工具在乳房重建患者中应用效果的随机对照试验,检索时间为从建库至2021年9月。2名研究者独立筛选文献、提取资料及评价文献质量,并用RevMan 5.4软件分析。结果共纳入10篇研究,包括950例研究对象。Meta分析结果显示:决策辅助工具可改善乳房重建患者决策冲突[SMD=-0.30,95%CI(-0.59,-0.01),P=0.04]及决策后悔[MD=-8.78,95%CI(-16.38,1.17),P=0.02],但对决策知识[SMD=0.55,95%CI(-0.09,1.19),P=0.09]、决策满意度[SMD=0.73,95%CI(-0.08,1.54),P=0.08]和焦虑[SMD=0.03,95%CI(-0.18,0.23),P=0.80]无明显作用。结论决策辅助工具可减少乳房重建患者决策冲突和决策后悔,但对决策知识、决策满意度和焦虑无显著影响。展开更多
The article discusses the application of artificial intelligence (AI) and automation in marine conservation, specifically in relation to the protection of marine ecosystems and the definition of marine protected areas...The article discusses the application of artificial intelligence (AI) and automation in marine conservation, specifically in relation to the protection of marine ecosystems and the definition of marine protected areas (MPAs). It highlights the threats that marine ecosystems face due to human activities and emphasizes the importance of effective management and conservation efforts. By improving data gathering, processing, monitoring, and analysis, artificial intelligence, and automation, they can revolutionize marine research. In conclusion, this study emphasizes the importance of AI and automation in marine conservation responsibly and ethically. In order to integrate these technologies into decision-making processes, stakeholders and marine conservation professionals must collaborate. Through the use of artificial intelligence and automation, marine conservation efforts can be transformed by establishing new methods of collecting and analyzing data, making informed decisions, and managing marine ecosystems.展开更多
Most existing studies of consumer search behaviour focus on page-level analysis,and some scholars start to examine the effect of refinement tools and characteristics in terms of products.However,it still remains undev...Most existing studies of consumer search behaviour focus on page-level analysis,and some scholars start to examine the effect of refinement tools and characteristics in terms of products.However,it still remains undeveloped on the product-level.To fill this gap,we reproduced the consumer shopping process in accordance with the topology of the Taobao platform from where we collected the clickstream data.We modelled consumers’sequential decision-making behaviour based on the taxonomy with Bayesian approach and found that not all the refinement tools are utilised for optimising decisions by users and it’s surprising that there exists no significant impact of all sorting tools.Besides,consumers are highly concerned with the characteristics of products.On the basis of the findings,platform function announcement and platform design suggestions were provided for improving platform functionality and optimising consumer decision-making,which also points out the direction of future research.展开更多
Background:Diabetes and hypertension are two of the commonest diseases in the world.As they unfavorably affect people of different age groups,they have become a cause of concern and must be predicted and diagnosed wel...Background:Diabetes and hypertension are two of the commonest diseases in the world.As they unfavorably affect people of different age groups,they have become a cause of concern and must be predicted and diagnosed well in advance.Objective:This research aims to determine the effectiveness of artificial neural networks(ANNs)in predicting diabetes and blood pressure diseases and to point out the factors which have a high impact on these diseases.Sample:This work used two online datasets which consist of data collected from 768 individuals.We applied neural network algorithms to predict if the individuals have those two diseases based on some factors.Diabetes prediction is based on five factors:age,weight,fat-ratio,glucose,and insulin,while blood pressure prediction is based on six factors:age,weight,fat-ratio,blood pressure,alcohol,and smoking.Method:A model based on the Multi-Layer Perceptron Neural Network(MLP)was implemented.The inputs of the network were the factors for each disease,while the output was the prediction of the disease’s occurrence.The model performance was compared with other classifiers such as Support Vector Machine(SVM)and K-Nearest Neighbors(KNN).We used performance metrics measures to assess the accuracy and performance of MLP.Also,a tool was implemented to help diagnose the diseases and to understand the results.Result:The model predicted the two diseases with correct classification rate(CCR)of 77.6%for diabetes and 68.7%for hypertension.The results indicate that MLP correctly predicts the probability of being diseased or not,and the performance can be significantly increased compared with both SVM and KNN.This shows MLPs effectiveness in early disease prediction.展开更多
Highway agencies have been using many of the elements of asset management with the support of various decision-making tools.To determine the most effective investment strategy with scarce resources,the integration,and...Highway agencies have been using many of the elements of asset management with the support of various decision-making tools.To determine the most effective investment strategy with scarce resources,the integration,and hence better utilization,of existing tools and practices across asset classes is generally lacking.This paper applies data envelopment analysis(DEA)to benchmark different highway investment scenarios using existing data or data readily available through existing models.Three asset types,pavements,bridges,and traffic signage,are investigated.Asset investment analysis results from the Highway Economic Requirements System State Version(HERS-ST)application,the PONTIS bridge management system software,and purpose-built traffic signage spreadsheet are obtained to capture the changes of performance measures under various budget scenarios and are further used as the inputs for the DEA process to benchmark investment scenarios for each individual asset.Subsequently,the performance measures and budget levels are assembled in the Asset Manager-NT software,whose results are input into DEA to benchmark cross-assets resource allocation scenarios.Planning for the management of highway network is addressed via case studies in a systematic manner that recognizes the tradeoffs among different funding periods and objectives such as preserving existing investments,safety,roughness and user costs.This study has established a preliminary implementable framework of highway asset management by linking DEA approach and current widely used decision-making tools for more efficient investments within and cross assets,and better understand of the tradeoffs,costs and consequences of various asset management decisions.展开更多
Reservoirs play an important role in water management and are key elements for water supply.Monitoring is needed in order to guarantee the quantity and quality of stored water.However,this task is sometimes not easy.T...Reservoirs play an important role in water management and are key elements for water supply.Monitoring is needed in order to guarantee the quantity and quality of stored water.However,this task is sometimes not easy.The objective of this study was to develop a procedure for predicting volume of stored water with remote sensing in water bodies under Mediterranean climate conditions.To achieve this objective,multispectral Landsat 7 and 8 images(NASA)were analyzed for the following five reservoirs:La Serena,La Pedrera,Beniarrés,Cubillas and Negratín(Spain).Reservoirs water surface was computed with the spectral angle mapper(SAM)algorithm.After that,cross-validation regression models were computed in order to assess the capability of water surface estimations to predict stored water in each of the reservoirs.The statistical models were trained with Landsat 7 images and were validated by using Landsat 8 images.Our results suggest a good capability of water volume prediction from free satellite imagery derived from surface water estimations.Combining free remote sensing images and open source GIS algorithms can be a very useful tool for water management and an integrated and efficient way to control water storage,especially in low accessible sites.展开更多
文摘目的评价决策辅助工具在乳房重建患者中的应用效果。方法计算机检索Cochrane Library、PubMed、Web of Science、Embase、中国生物医学文献数据库、中国知网、维普、万方数据库中有关决策辅助工具在乳房重建患者中应用效果的随机对照试验,检索时间为从建库至2021年9月。2名研究者独立筛选文献、提取资料及评价文献质量,并用RevMan 5.4软件分析。结果共纳入10篇研究,包括950例研究对象。Meta分析结果显示:决策辅助工具可改善乳房重建患者决策冲突[SMD=-0.30,95%CI(-0.59,-0.01),P=0.04]及决策后悔[MD=-8.78,95%CI(-16.38,1.17),P=0.02],但对决策知识[SMD=0.55,95%CI(-0.09,1.19),P=0.09]、决策满意度[SMD=0.73,95%CI(-0.08,1.54),P=0.08]和焦虑[SMD=0.03,95%CI(-0.18,0.23),P=0.80]无明显作用。结论决策辅助工具可减少乳房重建患者决策冲突和决策后悔,但对决策知识、决策满意度和焦虑无显著影响。
文摘The article discusses the application of artificial intelligence (AI) and automation in marine conservation, specifically in relation to the protection of marine ecosystems and the definition of marine protected areas (MPAs). It highlights the threats that marine ecosystems face due to human activities and emphasizes the importance of effective management and conservation efforts. By improving data gathering, processing, monitoring, and analysis, artificial intelligence, and automation, they can revolutionize marine research. In conclusion, this study emphasizes the importance of AI and automation in marine conservation responsibly and ethically. In order to integrate these technologies into decision-making processes, stakeholders and marine conservation professionals must collaborate. Through the use of artificial intelligence and automation, marine conservation efforts can be transformed by establishing new methods of collecting and analyzing data, making informed decisions, and managing marine ecosystems.
基金This work was supported by the National Natural Science Foundation of China[grant number 71671048,71901075]the MOE Layout Foundation of Humanities and Social Sciences the Natural Science Foundation of Guangdong Province[grant number 2020A151501507]Co-Construction Project of Philosophy and Social Science Planning Discipline in Guangdong Planning Office of Philosophy and Social Science[grant number GD18XGL37].
文摘Most existing studies of consumer search behaviour focus on page-level analysis,and some scholars start to examine the effect of refinement tools and characteristics in terms of products.However,it still remains undeveloped on the product-level.To fill this gap,we reproduced the consumer shopping process in accordance with the topology of the Taobao platform from where we collected the clickstream data.We modelled consumers’sequential decision-making behaviour based on the taxonomy with Bayesian approach and found that not all the refinement tools are utilised for optimising decisions by users and it’s surprising that there exists no significant impact of all sorting tools.Besides,consumers are highly concerned with the characteristics of products.On the basis of the findings,platform function announcement and platform design suggestions were provided for improving platform functionality and optimising consumer decision-making,which also points out the direction of future research.
文摘Background:Diabetes and hypertension are two of the commonest diseases in the world.As they unfavorably affect people of different age groups,they have become a cause of concern and must be predicted and diagnosed well in advance.Objective:This research aims to determine the effectiveness of artificial neural networks(ANNs)in predicting diabetes and blood pressure diseases and to point out the factors which have a high impact on these diseases.Sample:This work used two online datasets which consist of data collected from 768 individuals.We applied neural network algorithms to predict if the individuals have those two diseases based on some factors.Diabetes prediction is based on five factors:age,weight,fat-ratio,glucose,and insulin,while blood pressure prediction is based on six factors:age,weight,fat-ratio,blood pressure,alcohol,and smoking.Method:A model based on the Multi-Layer Perceptron Neural Network(MLP)was implemented.The inputs of the network were the factors for each disease,while the output was the prediction of the disease’s occurrence.The model performance was compared with other classifiers such as Support Vector Machine(SVM)and K-Nearest Neighbors(KNN).We used performance metrics measures to assess the accuracy and performance of MLP.Also,a tool was implemented to help diagnose the diseases and to understand the results.Result:The model predicted the two diseases with correct classification rate(CCR)of 77.6%for diabetes and 68.7%for hypertension.The results indicate that MLP correctly predicts the probability of being diseased or not,and the performance can be significantly increased compared with both SVM and KNN.This shows MLPs effectiveness in early disease prediction.
基金supported by the University of DelawareUniversity Transportation Center+1 种基金Delaware Center for TransportationDelaware Department of Transportation。
文摘Highway agencies have been using many of the elements of asset management with the support of various decision-making tools.To determine the most effective investment strategy with scarce resources,the integration,and hence better utilization,of existing tools and practices across asset classes is generally lacking.This paper applies data envelopment analysis(DEA)to benchmark different highway investment scenarios using existing data or data readily available through existing models.Three asset types,pavements,bridges,and traffic signage,are investigated.Asset investment analysis results from the Highway Economic Requirements System State Version(HERS-ST)application,the PONTIS bridge management system software,and purpose-built traffic signage spreadsheet are obtained to capture the changes of performance measures under various budget scenarios and are further used as the inputs for the DEA process to benchmark investment scenarios for each individual asset.Subsequently,the performance measures and budget levels are assembled in the Asset Manager-NT software,whose results are input into DEA to benchmark cross-assets resource allocation scenarios.Planning for the management of highway network is addressed via case studies in a systematic manner that recognizes the tradeoffs among different funding periods and objectives such as preserving existing investments,safety,roughness and user costs.This study has established a preliminary implementable framework of highway asset management by linking DEA approach and current widely used decision-making tools for more efficient investments within and cross assets,and better understand of the tradeoffs,costs and consequences of various asset management decisions.
文摘Reservoirs play an important role in water management and are key elements for water supply.Monitoring is needed in order to guarantee the quantity and quality of stored water.However,this task is sometimes not easy.The objective of this study was to develop a procedure for predicting volume of stored water with remote sensing in water bodies under Mediterranean climate conditions.To achieve this objective,multispectral Landsat 7 and 8 images(NASA)were analyzed for the following five reservoirs:La Serena,La Pedrera,Beniarrés,Cubillas and Negratín(Spain).Reservoirs water surface was computed with the spectral angle mapper(SAM)algorithm.After that,cross-validation regression models were computed in order to assess the capability of water surface estimations to predict stored water in each of the reservoirs.The statistical models were trained with Landsat 7 images and were validated by using Landsat 8 images.Our results suggest a good capability of water volume prediction from free satellite imagery derived from surface water estimations.Combining free remote sensing images and open source GIS algorithms can be a very useful tool for water management and an integrated and efficient way to control water storage,especially in low accessible sites.