期刊文献+
共找到852篇文章
< 1 2 43 >
每页显示 20 50 100
IoT data analytic algorithms on edge-cloud infrastructure:A review
1
作者 Abel E.Edje M.S.Abd Latiff Weng Howe Chan 《Digital Communications and Networks》 SCIE CSCD 2023年第6期1486-1515,共30页
The adoption of Internet of Things(IoT)sensing devices is growing rapidly due to their ability to provide realtime services.However,it is constrained by limited data storage and processing power.It offloads its massiv... The adoption of Internet of Things(IoT)sensing devices is growing rapidly due to their ability to provide realtime services.However,it is constrained by limited data storage and processing power.It offloads its massive data stream to edge devices and the cloud for adequate storage and processing.This further leads to the challenges of data outliers,data redundancies,and cloud resource load balancing that would affect the execution and outcome of data streams.This paper presents a review of existing analytics algorithms deployed on IoT-enabled edge cloud infrastructure that resolved the challenges of data outliers,data redundancies,and cloud resource load balancing.The review highlights the problems solved,the results,the weaknesses of the existing algorithms,and the physical and virtual cloud storage servers for resource load balancing.In addition,it discusses the adoption of network protocols that govern the interaction between the three-layer architecture of IoT sensing devices enabled edge cloud and its prevailing challenges.A total of 72 algorithms covering the categories of classification,regression,clustering,deep learning,and optimization have been reviewed.The classification approach has been widely adopted to solve the problem of redundant data,while clustering and optimization approaches are more used for outlier detection and cloud resource allocation. 展开更多
关键词 Internet of things Cloud platform Edge analytic algorithms Processes Network communication protocols
下载PDF
Dosimetric Comparison of Integral Radiation Dose: Anisotropic Analytical Algorithm and Acuros XB in Breast Radiotherapy 被引量:2
2
作者 Aydin Cakir Zuleyha Akgun 《International Journal of Medical Physics, Clinical Engineering and Radiation Oncology》 2019年第2期57-67,共11页
The impact of the difference between Anisotropic Analytical Algorithm (AAA) and Acuros XB (AXB) in breast radiotherapy is not clearly due to different uses and further research is required to explain this effect. The ... The impact of the difference between Anisotropic Analytical Algorithm (AAA) and Acuros XB (AXB) in breast radiotherapy is not clearly due to different uses and further research is required to explain this effect. The aim of this study is to investigate the contribution of calculation differences between AAA and AXB to the integral radiation dose (ID) on critical organs. Seven field intensity modulated radiotherapy (IMRT) plans were generated using with AAA and AXB algorithms for twenty patients with early stage left breast cancer after breast conserving surgery. Volumetric and dosimetric differences, as well as, the Dmean, V5, V20 doses of the left and right-sided lung, the Dmean, V10, V20, V30 doses of heart and the Dmean, V5, V10 doses of the contralateral breast were investigated. The mean dose (Dmean), V5, V20 doses of the left-sided lung, the Dmean, V5, V10 doses of right-sided lung, the Dmean, V10, V20, V30 doses of heart and the Dmean, V5, V10 doses of the contralateral breast were found to be significantly higher with AAA. In this research integral dose was also higher in the AAA recalculated plan and the AXB plan with the average dose as follows left lung 2%, heart 2%, contralateral breast 8%, contralateral lung 4% respectively. Our study revealed that the calculation differences between Acuros XB (AXB) and Anisotropic Analytical Algorithm (AAA) in breast radiotherapy caused serious differences on the stored integral doses on critical organs. In addition, AXB plans showed significantly dosimetric improvements in multiple dosimetric parameters. 展开更多
关键词 ANISOTROPIC analytical algorithm Acuros XB BREAST RADIOTHERAPY INTEGRAL Radiation DOSE
下载PDF
TWO TYPES OF NEW ALGORITHMS FOR FINDING EXPLICIT ANALYTICAL SOLUTIONS OF NONLINEAR DIFFERENTIAL EQUATIONS
3
作者 张鸿庆 闫振亚 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI 2000年第12期1423-1431,共9页
The idea of AC = BD was applied to solve the nonlinear differential equations. Suppose that Au = 0 is a given equation to he solved and Dv = 0 is an equation to be easily solved. If the transformation u = Cv is obtain... The idea of AC = BD was applied to solve the nonlinear differential equations. Suppose that Au = 0 is a given equation to he solved and Dv = 0 is an equation to be easily solved. If the transformation u = Cv is obtained so that v satisfies Dv = 0, then the solutions for Au = 0 can be found. In order to illustrate this approach, several examples about the transformation C are given. 展开更多
关键词 nonlinear differential equations transformation algorithm analytical solution
下载PDF
Process analytical technologies and self-optimization algorithms in automated pharmaceutical continuous manufacturing 被引量:1
4
作者 Peiwen Liu Hui Jin +5 位作者 Yan Chen Derong Wang Haohui Yan Mingzhao Wu Fang Zhao Weiping Zhu 《Chinese Chemical Letters》 SCIE CAS CSCD 2024年第3期87-95,共9页
The pharmaceutical industry is now paying increased attention to continuous manufacturing.While the revolution to continuous and automated manufacturing is deepening in most of the top pharma companies in the world,th... The pharmaceutical industry is now paying increased attention to continuous manufacturing.While the revolution to continuous and automated manufacturing is deepening in most of the top pharma companies in the world,the advancement of automated pharmaceutical continuous manufacturing in China is relatively slow due to some key challenges including the lack of knowledge on the related technologies and shortage of qualified personnels.In this review,emphasis is given to two of the crucial technologies in automated pharmaceutical continuous manufacturing,i.e.,process analytical technology(PAT)and self-optimizing algorithm.Research work published in recent 5 years employing advanced PAT tools and self-optimization algorithms is introduced,which represents the great progress that has been made in automated pharmaceutical continuous manufacturing. 展开更多
关键词 Pharmaceutical continuous manufacturing AUTOMATION Process analytical technology Self-optimization algorithm
原文传递
A Genetic Fuzzy Analytical Hierarchy Process Based Projection Pursuit Method for Selecting Schemes of Water Transportation Projects 被引量:1
5
作者 JIN Juliang LI Lei +1 位作者 WANG Wensheng ZHANG Ming 《Journal of Ocean University of China》 SCIE CAS 2006年第4期289-294,共6页
The optimal selection of schemes of water transportation projects is a process of choosing a relatively optimal scheme from a number of schemes of water transportation programming and management projects, which is of ... The optimal selection of schemes of water transportation projects is a process of choosing a relatively optimal scheme from a number of schemes of water transportation programming and management projects, which is of importance in both theory and practice in water resource systems engineering. In order to achieve consistency and eliminate the dimensions of fuzzy qualitative and fuzzy quantitative evaluation indexes, to determine the weights of the indexes objectively, and to increase the differences among the comprehensive evaluation index values of water transportation project schemes, a projection pursuit method, named FPRM-PP for short, was developed in this work for selecting the optimal water transportation project scheme based on the fuzzy preference relation matrix. The research results show that FPRM-PP is intuitive and practical, the correction range of the fuzzy rained is both stable and accurate; preference relation matrix A it produces is relatively small, and the result obtherefore FPRM-PP can be widely used in the optimal selection of different multi-factor decision-making schemes. 展开更多
关键词 water transportation project optimal selection of schemes fuzzy analytical hierarchy process projection pursuit genetic algorithm
下载PDF
SUBSTRUCTURE COMPUTATIONAL ALGORITHM FOR EXACT ANALYTIC METHOD
6
作者 纪振义 叶开沅 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI 1990年第10期913-919,共7页
In[1], the exact analytic method for the solution of differential equation with variable coefficients was suggested and an analytic expression of solution was given by initial parameter algorithm. But to some problems... In[1], the exact analytic method for the solution of differential equation with variable coefficients was suggested and an analytic expression of solution was given by initial parameter algorithm. But to some problems such as the bending, free vibration and buckling of nonhomogeneous long cylinders, it is difficult to obtain their solutions by the initial parameter algorithm on computer. In this paper, the substructure computational algorithm for the exact analytic method is presented through the bending of non-homogeneous long cylindrical shell. This substructure algorithm can he applied to solve the problems which can not he calculated by the initial parameter algorithm on computer. Finally, the problems can he reduced to solving a low order system of algehraic equations like the initial parameter algorithm Numerical examples are given and compared with the initial para-algorithm at the end of the paper, which confirms the correctness of the substructure computational algorithm. 展开更多
关键词 substructure computational algorithm exact analytic method long cylindrical shell
下载PDF
A Novel Analytical Model of Brain Tumor Based on Swarm Robotics
7
作者 Mohamed Abbas 《Proceedings of Anticancer Research》 2022年第4期11-20,共10页
A tumor is referred to as“intracranial hard neoplasm”if it grows near the brain or central spinal vessel(neoplasm).In certain cases,it is possible that the responsible cells are neurons situated deep inside the brai... A tumor is referred to as“intracranial hard neoplasm”if it grows near the brain or central spinal vessel(neoplasm).In certain cases,it is possible that the responsible cells are neurons situated deep inside the brain’s structure.This article discusses a strategy for halting the progression of brain tumor.A precise and accurate analytical model of brain tumors is the foundation of this strategy.It is based on an algorithm known as kill chain interior point(KCIP),which is the result of a merger of kill chain and interior point algorithms,as well as a precise and accurate analytical model of brain tumors.The inability to obtain a clear picture of tumor cell activity is the biggest challenge in this endeavor.Based on the motion of swarm robots,which are considered a subset of artificial intelligence,this article proposes a new notion of this kind of behavior,which may be used in various situations.The KCIP algorithm that follows is used in the analytical model to limit the development of certain cell types.According to the findings,it seems that different KCIP speed ratios are beneficial in preventing the development of brain tumors.It is hoped that this study will help researchers better understand the behavior of brain tumors,so as to develop a new drug that is effective in eliminating the tumor cells. 展开更多
关键词 Swarm robots Brain tumor analytical computation Kill chain Interior point algorithm
下载PDF
Adaptive Kernel Firefly Algorithm Based Feature Selection and Q-Learner Machine Learning Models in Cloud
8
作者 I.Mettildha Mary K.Karuppasamy 《Computer Systems Science & Engineering》 SCIE EI 2023年第9期2667-2685,共19页
CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferrin... CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferring information.A dynamic strategy,DevMLOps(Development Machine Learning Operations)used in automatic selections and tunings of MLTs result in significant performance differences.But,the scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.RFEs(Recursive Feature Eliminations)are computationally very expensive in its operations as it traverses through each feature without considering correlations between them.This problem can be overcome by the use of Wrappers as they select better features by accounting for test and train datasets.The aim of this paper is to use DevQLMLOps for automated tuning and selections based on orchestrations and messaging between containers.The proposed AKFA(Adaptive Kernel Firefly Algorithm)is for selecting features for CNM(Cloud Network Monitoring)operations.AKFA methodology is demonstrated using CNSD(Cloud Network Security Dataset)with satisfactory results in the performance metrics like precision,recall,F-measure and accuracy used. 展开更多
关键词 Cloud analytics machine learning ensemble learning distributed learning clustering classification auto selection auto tuning decision feedback cloud DevOps feature selection wrapper feature selection Adaptive Kernel Firefly algorithm(AKFA) Q learning
下载PDF
正交实验结合AHP和GA-BP神经网络优化益黄散醇提工艺 被引量:1
9
作者 王巍 杨武杰 +4 位作者 韩宇 安悦言 郝季 张强 鞠成国 《中国药房》 CAS 北大核心 2024年第3期327-332,共6页
目的 优化益黄散的醇提工艺。方法 采用回流提取法,以乙醇体积分数、液料比、提取时间为考察因素设计正交实验,以橙皮苷、川陈皮素、橘皮素、没食子酸、诃黎勒酸、诃子酸、甘草苷、甘草酸、丁香酚含量和干浸膏得率为指标,采用层次分析法... 目的 优化益黄散的醇提工艺。方法 采用回流提取法,以乙醇体积分数、液料比、提取时间为考察因素设计正交实验,以橙皮苷、川陈皮素、橘皮素、没食子酸、诃黎勒酸、诃子酸、甘草苷、甘草酸、丁香酚含量和干浸膏得率为指标,采用层次分析法(AHP)进行赋权并计算综合评分。通过验证正交实验和遗传算法(GA)-反向传播神经网络(BP神经网络)所预测的结果确定益黄散最佳醇提工艺参数。结果 正交实验优选的最佳醇提工艺参数为乙醇体积分数60%、液料比14∶1(mL/g)、提取时间90 min、提取2次,验证所得综合评分为79.19分;GA-BP神经网络优选的最佳醇提工艺参数为乙醇体积分数65%、液料比14∶1(mL/g)、提取时间60 min、提取2次,验证所得综合评分为85.30分,高于正交实验所得结果。结论 采用正交实验结合GA-BP神经网络的寻优方法较传统的正交实验寻优方法效果更佳,其优选出的益黄散最佳醇提工艺稳定可靠。 展开更多
关键词 益黄散 醇提工艺 正交实验 遗传算法 BP神经网络 层次分析法
下载PDF
考虑碳排放的分布式电源优化配置 被引量:1
10
作者 杨胡萍 占建建 +2 位作者 曹正东 李向军 徐丕立 《南昌大学学报(理科版)》 CAS 2024年第1期87-94,共8页
对分布式电源接入配电网进行合理的优化配置,能在兼顾运营商和用户利益的同时,改善系统整体电压分布。建立了综合考虑分布式电源投资成本、用户购电成本、网损费用和碳排放费用的多目标优化模型。利用改进层次分析法确定各目标的权重,... 对分布式电源接入配电网进行合理的优化配置,能在兼顾运营商和用户利益的同时,改善系统整体电压分布。建立了综合考虑分布式电源投资成本、用户购电成本、网损费用和碳排放费用的多目标优化模型。利用改进层次分析法确定各目标的权重,进而转化为单目标函数规划问题。针对天牛须算法个体单一性在解决高维复杂问题时精度低,优化效果不佳的问题,提出了一种改进天牛须粒子群算法,利用混沌映射对参数进行调整,引入动态惯性权重、莱维飞行机制,提高了收敛速度。以IEEE33节点系统为例,将改进天牛须粒子群算法与粒子群算法及天牛须粒子群算法的效果对比,验证改进算法对分布式电源优化配置问题的可行性,有效降低了碳排放费用、用户购电费用,减少了系统网损,改善了系统整体电压分布。 展开更多
关键词 分布式电源 优化配置 多目标优化 改进层次分析法 改进天牛须粒子群算法
下载PDF
高校大学生实验室安全意识评价模型的构建 被引量:1
11
作者 王坚 王清清 +1 位作者 啜鹏杰 黄富贵 《实验室研究与探索》 CAS 北大核心 2024年第4期203-208,共6页
为减少实验室安全事故的发生和提高大学生的实验室安全意识,设计了实验室安全意识影响因素调查问卷和大学生实验室安全意识评价调查问卷,利用层次分析法—熵权法(AHP-EWM)主客观相结合的方法建立高校大学生实验室安全意识评价体系。通... 为减少实验室安全事故的发生和提高大学生的实验室安全意识,设计了实验室安全意识影响因素调查问卷和大学生实验室安全意识评价调查问卷,利用层次分析法—熵权法(AHP-EWM)主客观相结合的方法建立高校大学生实验室安全意识评价体系。通过主成分分析法(PCA)处理,再选取累计贡献率超过95%的评价指标进行布谷鸟搜索(Cuckoo Search, CS),最后结合混合优化支持向量机(SVM)建立PCA-CS-SVM大学生实验室安全意识评价模型。验证结果表明,与PCA-LS-SVM和PCA-GA-SVM模型相比,PCA-CS-SVM模型的预测值与实际值的误差较小且评价等级与实际值保持一致,具有较高的准确性和可靠性,可用于高校大学生实验室安全意识评价。 展开更多
关键词 实验室安全意识 层次分析法—熵权法 布谷鸟搜索算法 预测模型 PCA-GA-SVM评价模型
下载PDF
基于P波到时拾取的分析法与遗传算法联合定位方法与应用
12
作者 肖晓春 丁振 +3 位作者 丁鑫 徐军 樊玉峰 李子阳 《岩土力学》 EI CAS CSCD 北大核心 2024年第7期2195-2207,共13页
针对岩石力学震源定位问题,提出了一种在P波到时精确拾取的基础上通过分析法过滤异常到达传感器和遗传算法(genetic algorithms,简称GA)求解联合定位方法,并将其应用于岩石材料的破裂面定位以及采矿工程中。为了消除传感器到时精度、传... 针对岩石力学震源定位问题,提出了一种在P波到时精确拾取的基础上通过分析法过滤异常到达传感器和遗传算法(genetic algorithms,简称GA)求解联合定位方法,并将其应用于岩石材料的破裂面定位以及采矿工程中。为了消除传感器到时精度、传统迭代法及迭代初值选择对定位的影响,基于时频分析的改进长短时窗(short-term average/long-term average,简称STA/LTA)法拾取P波到时,求解不同传感器组合分析解的逻辑概率密度函数过滤异常到达,引入遗传算法对到达清晰的震源进行定位。通过断铅、含夹层组合煤岩单轴压缩试验及定点爆破试验对该方法进行验证。结果表明:在对信号预先带通滤波后进行变分模态分解(variational mode decomposition,简称VMD)精确滤波的基础上结合改进STA/LTA法可以大幅提升到时拾取精度;通过分析法过滤异常到达对定位精度的影响,结合具有全局性、不受初值影响的遗传算法对震源定位,应用于岩石材料试验以及采矿工程中可以较准确的对震源进行定位,该方法较传统迭代法、线性定位法等更具有工程实际应用价值。 展开更多
关键词 滤波 改进STA/LTA法 到时拾取 声发射震源定位 分析法―遗传算法
原文传递
多轴线运输车的模块化设计方法研究
13
作者 罗澄清 赵登标 +1 位作者 张瑞亮 范政武 《机械设计与制造》 北大核心 2024年第7期310-316,共7页
目前多轴线运输车存在设计周期长、生产制造困难等问题。为了对此类轴线车进行快速开发,在分析现有模块划分方法的基础上,引入复杂网络理论,开展针对多轴线运输车的模块化设计方法研究。首先从零部件间的几何、功能及设计变更三个角度... 目前多轴线运输车存在设计周期长、生产制造困难等问题。为了对此类轴线车进行快速开发,在分析现有模块划分方法的基础上,引入复杂网络理论,开展针对多轴线运输车的模块化设计方法研究。首先从零部件间的几何、功能及设计变更三个角度分析评价多轴线运输车零部件之间的关联强度,然后采用基于七标度法则的区间层析分析法(IAHP)确定三个相关属性权重大小,并建立产品零部件综合复杂网络模型。在此基础上,采用Louvain算法进行该网络的社区发现,从而得到多轴线运输车模块划分方案,与GN算法、LPA算法、FCM算法相比,采用Louvain算法能更有效地对轴线车进行模块划分。基于模块化理论对多轴线运输车的设计进行研究,能够实现此轴线车的快速设计,为轴线车的优化升级奠定了基础。 展开更多
关键词 多轴线运输车 模块划分 区间层次分析法 Louvain算法
下载PDF
基于能量均衡的非均匀分簇调度算法
14
作者 崔颖 李巧珏 +1 位作者 高山 陈立伟 《哈尔滨工程大学学报》 EI CAS CSCD 北大核心 2024年第9期1834-1839,共6页
针对无线传感器网络节点能量有限且不可充电的问题,本文提出基于能量均衡的非均匀分簇调度算法(EBNC_CHES)延长网络寿命。EBNC_CHES在麻雀搜索算法的基础上,引入时间竞争机制减少冗余信息获取和能耗传递的同时,采取K-means非均匀分簇均... 针对无线传感器网络节点能量有限且不可充电的问题,本文提出基于能量均衡的非均匀分簇调度算法(EBNC_CHES)延长网络寿命。EBNC_CHES在麻雀搜索算法的基础上,引入时间竞争机制减少冗余信息获取和能耗传递的同时,采取K-means非均匀分簇均衡簇间网络能量消耗,引入改进的麻雀搜索在簇头选举中均衡簇内能耗。仿真结果表明:该算法与LEACH、EECHS_ISSADE和EESSTBRP相比,冗余信息降低了81%、80%、55%,能耗利用率提高了133%、50%、11.4%,寿命延长了52.8%、43.5%、12.2%。此算法能减少冗余信息,降低网络能耗、延长网络寿命。 展开更多
关键词 麻雀搜索算法 时间竞争调度 K-MEANS算法 网络能耗 非均匀分簇 层次分析法 簇头选举 能量均衡
下载PDF
基于AMOWOA的区域综合能源系统运行优化调度
15
作者 韩永明 王新鲁 +3 位作者 耿志强 朱群雄 毕帅 张红斌 《自动化学报》 EI CAS CSCD 北大核心 2024年第3期576-588,共13页
目前,智能优化算法已广泛应用于工程优化中,在当前多能耦合与互补的能源发展趋势下,仅考虑系统经济指标的单目标优化模式已经不再适用于目前区域综合能源系统(Integrated energy system, IES)的运行优化调度,需要研究一种多目标运行策... 目前,智能优化算法已广泛应用于工程优化中,在当前多能耦合与互补的能源发展趋势下,仅考虑系统经济指标的单目标优化模式已经不再适用于目前区域综合能源系统(Integrated energy system, IES)的运行优化调度,需要研究一种多目标运行策略来解决区域综合能源系统的运行优化调度问题.首先综合考虑经济与能源利用两个指标并结合商业住宅区域的特性,以系统日运行收益和一次能源利用率为优化目标构建商业住宅区域综合能源系统多目标运行优化调度模型.其次由于传统多目标智能优化算法缺乏一种最优解综合评价方法,基于非支配排序以及拥挤度计算的多目标算法框架,提出一种利用模糊一致矩阵选取全局最优解的多目标鲸鱼优化算法(A multi-objective whale optimization algorithm, AMOWOA),并将提出算法对商住区域综合能源系统多目标运行优化调度模型进行求解.最后以华东某商业住宅区域综合能源系统为例进行仿真,验证了该方法的有效性和可行性. 展开更多
关键词 多目标优化 综合能源系统 动态层次分析 鲸鱼优化算法
下载PDF
多场景下基于AHP-EWM的人体健康状态评估模型研究 被引量:1
16
作者 火久元 王虹阳 +1 位作者 巨涛 胡军 《计算机工程》 CAS CSCD 北大核心 2024年第7期372-380,共9页
为解决人体健康评估方法个性化监测不足的问题以及在满足不同场景下健康状态精细化评估的需求,需要一种基于多场景的人体健康状态评估方法来实现长期自动化监测。提出一种基于层次分析法(AHP)和熵权法(EWM)组合的多场景人体健康状态评... 为解决人体健康评估方法个性化监测不足的问题以及在满足不同场景下健康状态精细化评估的需求,需要一种基于多场景的人体健康状态评估方法来实现长期自动化监测。提出一种基于层次分析法(AHP)和熵权法(EWM)组合的多场景人体健康状态评估模型。首先采集人体在运动、休息、工作/学习和娱乐等4种不同场景下的健康监测指标数据,构建相应的评估指标体系。然后分别根据评估指标计算出AHP和EWM权重,再采用量子粒子群优化(QPSO)算法对AHP和EWM中的主客观权重进行分配,以确保评价指标占比的客观性。最后通过模糊综合评价法对人体健康状态进行评估和量化,并利用实际监测数据对方法的可靠性和稳定性进行验证。实验结果表明,在4种场景下所提方法的综合得分分别为63.78、59.83、58.71和59.21,表明在不同场景下该模型都具有较好的准确性和稳定性。根据评估结果,对测试者的身体状态评价结果进行分析,并给出一些健康建议。所提模型可全面了解人体在不同场景下的健康状况,并为人们提供科学的健康指导,从而为健康管理和疾病预防提供科学依据。 展开更多
关键词 健康状态 多重场景 层次分析法 熵权法 量子粒子群优化算法 模糊综合评价法
下载PDF
面向个性化需求的燃料电池测试台价值评估方法
17
作者 钟频 闫浩鹏 +1 位作者 袁小芳 谭伟华 《湖南大学学报(自然科学版)》 EI CAS CSCD 北大核心 2024年第8期91-100,共10页
针对不同个性化需求的燃料电池测试台(fuel cell test bench,FCTB)难以评价和量化评估的问题,提出一种基于改进和声搜索算法的FCTB价值评估方法.针对不同FCTB的个性化需求,建立了FCTB综合评估指标体系;结合用户的个性化需求,采用模糊层... 针对不同个性化需求的燃料电池测试台(fuel cell test bench,FCTB)难以评价和量化评估的问题,提出一种基于改进和声搜索算法的FCTB价值评估方法.针对不同FCTB的个性化需求,建立了FCTB综合评估指标体系;结合用户的个性化需求,采用模糊层次分析法分配指标权重,构建价值定量评估模型,将权重求取问题转换为约束优化问题;提出一种改进和声搜索算法对问题进行求解,通过设计解向量生成机制和参数自适应调整策略,用于提高传统和声搜索算法的求解效率和搜索能力.仿真结果表明,本文方法在计算效率和精度方面具有优势,并能够根据不同的需求特性实现对FCTB方案做出定量的价值评估. 展开更多
关键词 燃料电池测试台 价值评估 改进和声搜索算法 模糊层次分析法
下载PDF
可信学习分析构建:风险桎梏、理论纾解与实践解蔽
18
作者 武法提 李坦 夏志文 《远程教育杂志》 CSSCI 北大核心 2024年第5期12-22,共11页
可信学习分析技术的发展已成为全球研究者共同关注的焦点。国内外学者已就其内涵意蕴、价值逻辑等开展广泛探讨,但也存在关键问题不明、理论边界不清和实践路径模糊等问题。为此,研究以关键问题提炼和理论框架构建为先导,以实践路径的... 可信学习分析技术的发展已成为全球研究者共同关注的焦点。国内外学者已就其内涵意蕴、价值逻辑等开展广泛探讨,但也存在关键问题不明、理论边界不清和实践路径模糊等问题。为此,研究以关键问题提炼和理论框架构建为先导,以实践路径的探索和实施为主线,对可信学习分析技术的教育应用进行分析。在实践问题方面,研究分析了阻碍可信学习分析实现的关键因素,包括数据漂移现象所导致的算法失准、样本分布失衡现象导致的算法偏见以及算法黑盒现象导致的决策结果失信等一系列问题。在理论研究方面,研究结合理论与实践问题分析,建立起面向学习环境、数据治理、建模分析和干预反馈四要素的可信学习分析理论框架。随后,研究依托该理论框架,结合相关研究方法和技术,构建了可信学习分析的实践路径,如结合价值敏感设计的伦理调适等。研究为可信学习分析研究从理论到实践提供系统化的解决思路。 展开更多
关键词 可信学习分析 可解释人工智能 算法公平
下载PDF
AAA和AXB算法在儿童髓母细胞瘤全脑全脊髓VMAT中的剂量学差异
19
作者 周莉 刘悦 《医疗卫生装备》 CAS 2024年第3期56-60,共5页
目的:从剂量学角度分析各向异性算法(anisotropic analytical algorithm,AAA)和光子剂量(acuros external beam,AXB)算法在儿童髓母细胞瘤全脑全脊髓容积调强放射治疗(volumetric modulated arc therapy,VMAT)中的差异。方法:回顾性选取... 目的:从剂量学角度分析各向异性算法(anisotropic analytical algorithm,AAA)和光子剂量(acuros external beam,AXB)算法在儿童髓母细胞瘤全脑全脊髓容积调强放射治疗(volumetric modulated arc therapy,VMAT)中的差异。方法:回顾性选取2015年2月至2022年8月于某院接受全脑全脊髓放射治疗(craniospinal irradiation,CSI)的35例髓母细胞瘤患儿,采用Varian Eclipse 15.6计划系统对35例患儿分别制订AAA计划和AXB计划,分为AAA计划组和AXB计划组。比较AXB计划组与AAA计划组对计划靶区(planning target volume,PTV)D_(mean)、D2、适形性指数(conformity index,CI)、均匀性指数(homogeneity index,HI)以及危及器官(organ at risk,OAR)双侧眼球、心脏、双侧肾脏、肝脏D_(mean),双侧肺V_(5)、V_(10)、V_(20)和D_(mean),双侧晶体、双侧视神经和小肠Dmax的剂量学影响。结果:AAA计划组的CI低于AXB计划组,差异有统计学意义(P<0.05);AAA计划组的HI、D2和D_(mean)均高于AXB计划组,差异有统计学意义(P<0.05)。AAA计划组的左、右眼D_(mean)均高于AXB计划组,差异有统计学意义(P<0.05);AAA计划组的左肺V_(5)、V_(10)、D_(mean)及右肺V_(5)、V_(10)、D_(mean)均高于AXB计划组,差异有统计学意义(P<0.05)。其他OAR剂量学参数在2个计划组间的差异无统计学意义(P>0.05)。结论:相较于AAA,在CSI计划中使用AXB算法能改善靶区剂量的均匀性,有效降低因放射治疗导致的副反应发生概率,推荐在儿童髓母细胞瘤全脑全脊髓VMAT中使用AXB算法代替AAA。 展开更多
关键词 各向异性算法 光子剂量算法 儿童髓母细胞瘤 全脑全脊髓 容积调强放射治疗
下载PDF
RV减速器的多目标层次优化设计
20
作者 丁国龙 叶梦传 +1 位作者 吴熙 余运清 《机械设计与制造》 北大核心 2024年第3期67-72,共6页
为了使RV减速器的结构更加紧凑、传动效率更高和承载能力更强,提出了一种基于层次分析法(AHP)的RV减速器多目标优化设计方法。以RV减速器的体积、传动效率和摆线轮接触应力为多目标函数,借助层次分析法(AHP)对优化目标进行评估,计算各... 为了使RV减速器的结构更加紧凑、传动效率更高和承载能力更强,提出了一种基于层次分析法(AHP)的RV减速器多目标优化设计方法。以RV减速器的体积、传动效率和摆线轮接触应力为多目标函数,借助层次分析法(AHP)对优化目标进行评估,计算各个目标的权重,将多个目标通过加权法转化为单目标函数,其次建立了包含参数范围、强度校核及结构限制的约束条件。最后利用遗传算法(GA)实现多目标优化设计问题的求解。优化结果表明,优化后的RV减速器体积减小、传动效率更高、承载能力更强,综合性能提高了8.0%。为实际生产应用中减速器的优化设计提供理论和方法指导。 展开更多
关键词 RV减速器 层次分析法(AHP) 多目标优化 优化设计 遗传算法
下载PDF
上一页 1 2 43 下一页 到第
使用帮助 返回顶部