研究模型选择对支持向量机(SVM)的泛化性能有着重要影响。针对传统梯度算法对初始值敏感及网格搜索法计算复杂的缺点,为了提高全面优化能力和分类精度,提出了一种基于协方差矩阵自适应进化策略(CMA-ES)的支持向量机(SVM)模型优化算法,...研究模型选择对支持向量机(SVM)的泛化性能有着重要影响。针对传统梯度算法对初始值敏感及网格搜索法计算复杂的缺点,为了提高全面优化能力和分类精度,提出了一种基于协方差矩阵自适应进化策略(CMA-ES)的支持向量机(SVM)模型优化算法,通过对SVM泛化性能界(Bounds on Generalization Performance)的优化求解,实现了基于CMA-ES算法的SVM模型选择。在标准数据集上的实验结果表明:相比遗传算法和梯度算法,上述方法能够在较小计算代价下得到更优的超参数,提高支持向量机的预测精度稳定性,尤其适合大样本数据条件下的模型选择。展开更多
介绍了旋转体时域有限差分法(BOR-FDTD),导出了电磁场迭代计算公式。给出了自适应协方差矩阵进化策略(CMA-ES)的基本原理和步骤。提出了一种基于BOR-FDTD和CMA-ES的波纹喇叭优化设计技术,并将该项技术用于平方公里阵(Square Kilometre A...介绍了旋转体时域有限差分法(BOR-FDTD),导出了电磁场迭代计算公式。给出了自适应协方差矩阵进化策略(CMA-ES)的基本原理和步骤。提出了一种基于BOR-FDTD和CMA-ES的波纹喇叭优化设计技术,并将该项技术用于平方公里阵(Square Kilometre Array,SKA)望远镜天线Band 4(2.8~5.18 GHz)波纹喇叭馈源的优化设计。计算结果表明,该馈源在工作频带内反射损耗基本在-20 d B以下,天线口径效率均优于86.5%,且口径效率随频率的变化较小。展开更多
针对平方公里阵(Square Kilometre Array,SKA)天线对高灵敏度的需求,利用基于旋转体时域有限差分法(BOR-FDTD)和自适应协方差矩阵进化策略(CMA-ES)的波纹喇叭优化设计技术,提出了以灵敏度为目标的大张角波纹喇叭优化设计方法。分别以天...针对平方公里阵(Square Kilometre Array,SKA)天线对高灵敏度的需求,利用基于旋转体时域有限差分法(BOR-FDTD)和自适应协方差矩阵进化策略(CMA-ES)的波纹喇叭优化设计技术,提出了以灵敏度为目标的大张角波纹喇叭优化设计方法。分别以天线口径效率和灵敏度为优化目标对工作于4.6~8.51 GHz的大张角波纹喇叭进行优化设计。计算结果表明,以灵敏度为优化目标所设计的波纹喇叭综合性能更优,其交叉极化和反射损耗均优于-20 d B,用于SKA天线的口径效率在85.1%以上,灵敏度优于7.68 m^2/K。展开更多
为了解决目前水质预测中未考虑局部无知性这一问题,提出一种基于幂集置信规则库(Belief rule base with power set,PBRB)的水质预测模型。该模型能够有效融合专家知识与定量数据,并能在描述多种不确定性的同时,将传统的辨识框架扩展到幂...为了解决目前水质预测中未考虑局部无知性这一问题,提出一种基于幂集置信规则库(Belief rule base with power set,PBRB)的水质预测模型。该模型能够有效融合专家知识与定量数据,并能在描述多种不确定性的同时,将传统的辨识框架扩展到幂集,使其能够很好地表达无知性从而提高水质预测精度。此外,利用协方差矩阵自适应进化策略(Covariance matrix adaptive evolution strategy,CMA-ES)算法对PBRB模型进行优化。仿真结果表明:PBRB模型能准确预测一段时间内水质变化趋势,预测精度高于其他传统方法。展开更多
Cloud computing, a recently emerged paradigm faces major challenges in achieving the privacy of migrated data, network security, etc. Too many cryptographic technologies are raised to solve these issues based on ident...Cloud computing, a recently emerged paradigm faces major challenges in achieving the privacy of migrated data, network security, etc. Too many cryptographic technologies are raised to solve these issues based on identity, attributes and prediction algorithms yet;these techniques are highly prone to attackers. This would raise a need of an effective encryption technique, which would ensure secure data migration. With this scenario, our proposed methodology Efficient Probabilistic Public Key Encryption(EPPKE) is optimized with Covariance Matrix Adaptation Evolution Strategies(CMA-ES). It ensures data integrity through the Luhn algorithm with BLAKE 2b encapsulation. This enables an optimized security to the data which is migrated through cloud. The proposed methodology is implemented in Open Stack with Java Language. It achieves better results by providing security compared to other existing techniques like RSA, IBA, ABE, PBE, etc.展开更多
文摘研究模型选择对支持向量机(SVM)的泛化性能有着重要影响。针对传统梯度算法对初始值敏感及网格搜索法计算复杂的缺点,为了提高全面优化能力和分类精度,提出了一种基于协方差矩阵自适应进化策略(CMA-ES)的支持向量机(SVM)模型优化算法,通过对SVM泛化性能界(Bounds on Generalization Performance)的优化求解,实现了基于CMA-ES算法的SVM模型选择。在标准数据集上的实验结果表明:相比遗传算法和梯度算法,上述方法能够在较小计算代价下得到更优的超参数,提高支持向量机的预测精度稳定性,尤其适合大样本数据条件下的模型选择。
文摘介绍了旋转体时域有限差分法(BOR-FDTD),导出了电磁场迭代计算公式。给出了自适应协方差矩阵进化策略(CMA-ES)的基本原理和步骤。提出了一种基于BOR-FDTD和CMA-ES的波纹喇叭优化设计技术,并将该项技术用于平方公里阵(Square Kilometre Array,SKA)望远镜天线Band 4(2.8~5.18 GHz)波纹喇叭馈源的优化设计。计算结果表明,该馈源在工作频带内反射损耗基本在-20 d B以下,天线口径效率均优于86.5%,且口径效率随频率的变化较小。
文摘针对平方公里阵(Square Kilometre Array,SKA)天线对高灵敏度的需求,利用基于旋转体时域有限差分法(BOR-FDTD)和自适应协方差矩阵进化策略(CMA-ES)的波纹喇叭优化设计技术,提出了以灵敏度为目标的大张角波纹喇叭优化设计方法。分别以天线口径效率和灵敏度为优化目标对工作于4.6~8.51 GHz的大张角波纹喇叭进行优化设计。计算结果表明,以灵敏度为优化目标所设计的波纹喇叭综合性能更优,其交叉极化和反射损耗均优于-20 d B,用于SKA天线的口径效率在85.1%以上,灵敏度优于7.68 m^2/K。
文摘为了解决目前水质预测中未考虑局部无知性这一问题,提出一种基于幂集置信规则库(Belief rule base with power set,PBRB)的水质预测模型。该模型能够有效融合专家知识与定量数据,并能在描述多种不确定性的同时,将传统的辨识框架扩展到幂集,使其能够很好地表达无知性从而提高水质预测精度。此外,利用协方差矩阵自适应进化策略(Covariance matrix adaptive evolution strategy,CMA-ES)算法对PBRB模型进行优化。仿真结果表明:PBRB模型能准确预测一段时间内水质变化趋势,预测精度高于其他传统方法。
文摘Cloud computing, a recently emerged paradigm faces major challenges in achieving the privacy of migrated data, network security, etc. Too many cryptographic technologies are raised to solve these issues based on identity, attributes and prediction algorithms yet;these techniques are highly prone to attackers. This would raise a need of an effective encryption technique, which would ensure secure data migration. With this scenario, our proposed methodology Efficient Probabilistic Public Key Encryption(EPPKE) is optimized with Covariance Matrix Adaptation Evolution Strategies(CMA-ES). It ensures data integrity through the Luhn algorithm with BLAKE 2b encapsulation. This enables an optimized security to the data which is migrated through cloud. The proposed methodology is implemented in Open Stack with Java Language. It achieves better results by providing security compared to other existing techniques like RSA, IBA, ABE, PBE, etc.
