Alzheimer’s disease(AD)is an intensifying disorder that causes brain cells to degenerate early and destruct.Mild cognitive impairment(MCI)is one of the early signs of AD that interferes with people’s regular functio...Alzheimer’s disease(AD)is an intensifying disorder that causes brain cells to degenerate early and destruct.Mild cognitive impairment(MCI)is one of the early signs of AD that interferes with people’s regular functioning and daily activities.The proposed work includes a deep learning approach with a multimodal recurrent neural network(RNN)to predict whether MCI leads to Alzheimer’s or not.The gated recurrent unit(GRU)RNN classifier is trained using individual and correlated features.Feature vectors are concate-nated based on their correlation strength to improve prediction results.The feature vectors generated are given as the input to multiple different classifiers,whose decision function is used to predict the final output,which determines whether MCI progresses onto AD or not.Our findings demonstrated that,compared to individual modalities,which provided an average accuracy of 75%,our prediction model for MCI conversion to AD yielded an improve-ment in accuracy up to 96%when used with multiple concatenated modalities.Comparing the accuracy of different decision functions,such as Support Vec-tor Machine(SVM),Decision tree,Random Forest,and Ensemble techniques,it was found that that the Ensemble approach provided the highest accuracy(96%)and Decision tree provided the lowest accuracy(86%).展开更多
With projections indicating an increase in mobility over the next few decades andannual flight departures expected to rise to over 16 billion by 2050,there is a demand for theaviation industry and associated stakehold...With projections indicating an increase in mobility over the next few decades andannual flight departures expected to rise to over 16 billion by 2050,there is a demand for theaviation industry and associated stakeholders to consider new forms of aircraft and technology.Customer requirements are recognized as a key driver in business.The airline is the principalcustomer for the aircraft manufacture.The passenger is,in turn,the airline's principal customerbut they are just one of several stakeholders that include aviation authorities,airport operators,air-traffic control and security agencies.The passenger experience is a key differentiator usedby airlines to attract and retain custom and the fuselage that defines the cabin envelope for thein-flight passenger experience and cabin design therefore receives significant attention for newaircraft,service updates and refurbishments.Decision making in design is crucial to arrivingat viable and worthwhile cabin formats.Too litle innovation will result in an aircraftmanufacturer and airlines using its products falling behind its competitors.Too much mayresult in an over-extension with,for example,use of immature technologies that do not havethe necessary reliability for a safety critical industry or sufficient value to justify the develop-ment effort.The multiple requirements associated with cabin design,can be viewed as an area for optimisation,accepting trade-offs between the various parameters.Good design,however,is often defined as developing a concept that resolves the contradictions and takes the solutiontowards a win-win scenario.Indeed our understanding and practice of design allows forbehaviors that enhance design thinking through divergence and convergence,the use ofabductive reasoning,experimentation and systems thinking.This paper explores and definesthe challenges of designing the aireraft cabin of the future that will deliver on the multiplerequirements using experiences from the A350 XWB and future cabin design concepts.Inparticular the paper explores the va展开更多
Aiming at the dynamic multi-attribute decision making problem where the weight of each decision stage and attribute weight are completely unknown and the attribute value is unknown distributed three-parameter interval...Aiming at the dynamic multi-attribute decision making problem where the weight of each decision stage and attribute weight are completely unknown and the attribute value is unknown distributed three-parameter interval grey number,a threeparameter interval grey number dynamic multiattribute grey target decision making method with attribute value following quasi-normal distribution is proposed.Firstly,the position relationship between the“center of gravity”point and the kernel of the threeparameter interval grey number is discussed.According to the characteristicthat the attribute value obeys the quasi-normal distribution,anew weight isgiventothe“centerof gravity”point,and a new distance measure formula of the three-parameter interval grey number is defined.Secondly,according to the principle of maximum entropy,the objective programming model is constructed to determine the stage weight and attributeweight.Then,the schemes aresorted according to thesize of the comprehensive bull's-eye distance Finally an example is given to illustrate the effectiveness of the decision model.展开更多
文摘为实现某铅锌矿山无底柱深孔后退式崩矿法安全高效开采,开展采场结构参数优化研究.实测-650 m中段原岩应力,运用Surpac-FLAC3D模型生成技术构建数值分析模型,进而采用多元应力回归方法反演初始地应力场.通过弹性力学小薄板理论分析得到顶板稳定性随采场结构参数的变化关系,结合实际采准条件,提出采场结构参数初选方案.基于反演地应力场,进行初选方案开采数值分析,获得各方案力学响应指标.引入多目标理想点法决策,考虑安全和经济指标,计算方案评价指标集与理想解的向量近似度,优化确定该矿无底柱深孔后退式崩矿法采场结构参数为矿房采场宽10 m,矿柱采场宽8 m.
文摘Alzheimer’s disease(AD)is an intensifying disorder that causes brain cells to degenerate early and destruct.Mild cognitive impairment(MCI)is one of the early signs of AD that interferes with people’s regular functioning and daily activities.The proposed work includes a deep learning approach with a multimodal recurrent neural network(RNN)to predict whether MCI leads to Alzheimer’s or not.The gated recurrent unit(GRU)RNN classifier is trained using individual and correlated features.Feature vectors are concate-nated based on their correlation strength to improve prediction results.The feature vectors generated are given as the input to multiple different classifiers,whose decision function is used to predict the final output,which determines whether MCI progresses onto AD or not.Our findings demonstrated that,compared to individual modalities,which provided an average accuracy of 75%,our prediction model for MCI conversion to AD yielded an improve-ment in accuracy up to 96%when used with multiple concatenated modalities.Comparing the accuracy of different decision functions,such as Support Vec-tor Machine(SVM),Decision tree,Random Forest,and Ensemble techniques,it was found that that the Ensemble approach provided the highest accuracy(96%)and Decision tree provided the lowest accuracy(86%).
文摘With projections indicating an increase in mobility over the next few decades andannual flight departures expected to rise to over 16 billion by 2050,there is a demand for theaviation industry and associated stakeholders to consider new forms of aircraft and technology.Customer requirements are recognized as a key driver in business.The airline is the principalcustomer for the aircraft manufacture.The passenger is,in turn,the airline's principal customerbut they are just one of several stakeholders that include aviation authorities,airport operators,air-traffic control and security agencies.The passenger experience is a key differentiator usedby airlines to attract and retain custom and the fuselage that defines the cabin envelope for thein-flight passenger experience and cabin design therefore receives significant attention for newaircraft,service updates and refurbishments.Decision making in design is crucial to arrivingat viable and worthwhile cabin formats.Too litle innovation will result in an aircraftmanufacturer and airlines using its products falling behind its competitors.Too much mayresult in an over-extension with,for example,use of immature technologies that do not havethe necessary reliability for a safety critical industry or sufficient value to justify the develop-ment effort.The multiple requirements associated with cabin design,can be viewed as an area for optimisation,accepting trade-offs between the various parameters.Good design,however,is often defined as developing a concept that resolves the contradictions and takes the solutiontowards a win-win scenario.Indeed our understanding and practice of design allows forbehaviors that enhance design thinking through divergence and convergence,the use ofabductive reasoning,experimentation and systems thinking.This paper explores and definesthe challenges of designing the aireraft cabin of the future that will deliver on the multiplerequirements using experiences from the A350 XWB and future cabin design concepts.Inparticular the paper explores the va
基金Supported by Humanities and Social Science Project of Henan Colleges and Universities(2022-ZZJH-067)。
文摘Aiming at the dynamic multi-attribute decision making problem where the weight of each decision stage and attribute weight are completely unknown and the attribute value is unknown distributed three-parameter interval grey number,a threeparameter interval grey number dynamic multiattribute grey target decision making method with attribute value following quasi-normal distribution is proposed.Firstly,the position relationship between the“center of gravity”point and the kernel of the threeparameter interval grey number is discussed.According to the characteristicthat the attribute value obeys the quasi-normal distribution,anew weight isgiventothe“centerof gravity”point,and a new distance measure formula of the three-parameter interval grey number is defined.Secondly,according to the principle of maximum entropy,the objective programming model is constructed to determine the stage weight and attributeweight.Then,the schemes aresorted according to thesize of the comprehensive bull's-eye distance Finally an example is given to illustrate the effectiveness of the decision model.
