配送中心选址的遗传算法研究

针对配送中心的选址问题,将遗传算法这一全局搜索优化技术运用其中,通过建立选址的遗传算法模型,研究了算法设计,分析了其特点,并与传统的混合整数规划解法进行了分析比较。     

基于WOA-LSTM的窄带通信网网络时延预测算法

为了给窄带通信网的链路选择及协议的智能切换提供实时参考,设计了 一种基于鲸鱼优化算法(WOA)和长短期记忆神经网络(LSTM)的窄带通信网网络时延预测算法.首先对实测数据样本进行标准化处理,以LSTM神经网络算法的均方根误差函数的倒数作为适应度函数;其次采用鲸鱼优化算法对LSTM神经网络的学习率、隐含层神经元个数进行优...     

一种改进的数字同频直放站自适应反馈干扰抑制算法

基于数字地面电视广播(Digital Terrestrial Televisi on Broa dcasting,DTTB)同频直放站的回波干扰抑制,提出了一种变步长块LMS(Variable Step-siz e Block Normalized Least Mean Square,VSSBNLMS)自适应算法。此算法的目的是为了提 高传统回波干扰抑制的自适应算法的收敛速度和降低计算复杂度。其将输入信号分为长度相 等的块,在每一个数据块内,权值向量只更新一次,有效地降低了计算复杂度。〖JP2〗另 外,该算 法通过输出误差控制更新步长的变化,与传统的归一化LMS (NLMS)和块LMS (BLMS)算法相比 ,提高了收敛速度。仿真结果表明,该算法具有良好的收敛速度和回波干扰抑制性能。     

基于量子遗传算法的航空通信频率动态分配

为了更加有效地对航空通信频率进行分配,提出了一种基于量子遗传算法的航空通信频率动态分配方法。通过对频率动态分配思路进行分析,建立了频率动态分配框架,给出了频率动态分配的具体流程。在此基础上,讨论了航空通信频率动态分配问题,定义了航空通信频率动态分配约束条件,建立了航空通信频率动态分配模型。最后,运用量子遗传算法和遗传算法对算例进行仿真对比。结果表明：量子遗传算法在种群适应度和收敛速度上具备明显的优越性,频率动态分配模型能够根据不同种群数量条件动态调整适应度,能够较好满足航空通信频率分配问题动态性、准确性、时效性等实践运用要求。     

基于干扰抑制的恒模波束跟踪新算法

当干扰信号强度不小于期望信号时,常规恒模算法（CMA）会错误跟踪到干扰信号;期望信 号导向矢量线性约束恒模算法（LSCCMA）通过对期望信号来波方向约束,可正确跟踪到期望 信号,但是算法在干扰信号来波方向上不能形成明显的零陷。为此,提出了基于干扰约束的 恒模算法（LICCMBTA）。理论分析和仿真结果证明,该算法不仅可以正确跟踪到期望信号, 并且可实现在多个强干扰信号来波方向上形成深度可调的干扰零陷,从而提高了常规恒模算 法波束跟踪的稳健性。     

改进Adaboost算法对县域粮食作物产量的预测

Adaboost算法是一种典型的机器学习算法,但其算法在训练过程中用时较长.针对这个问题,采用改进的机器学习DWTAdaboost算法与Adaboost算法对1950—2012年内蒙古自治区扎兰屯地区的各项经济统计数据进行分析,比较两种算法模型对数据分析的优劣.结果表明DWTAdaboost算法在保证准确率不变的前提下效率更高.     

Is it China that leads the Asian stock market contagion in 2015?

This article examines the influence of China B-share aggregates on major Asian stock market aggregates during 2015 China crash. Results indicate the China market shows strong negative impact and is highly responsible for leading most markets down during the crash.     

A firefly algorithm modified support vector machine for the credit risk assessment of supply chain finance

PurposeNowadays, Supply Chain Finance (SCF) has been developing rapidly since the emergence of credit risk. Therefore, this paper used SVM optimized by the firefly algorithm, which is called firefly algorithm support vector machine (FA-SVM), and applied it to SCF evaluation with a different indicator selection.Design/methodology/approachIn this paper, we used FA-SVM to assess the credit risk of supply chain finance with extracted index through correlation and appraisal analysis, and finally determined 3 first-level indicators and 15 third-level indicators. Through the application analysis, 39 SMEs (117 sample data) were selected from the Computer and Electronic Communications Manufacturing Industry as the characteristics for the input variables, to verify the improvement effect of the method relative to the LIBSVM and the classification pretest effect in the credit risk assessment of the SCF.FindingsThe results showed that FA-SVM could improve the accuracy of classification prediction compared with LIBSVM, and decrease the error rate of falseness recognize credible enterprise to untrusted enterprise.Originality/valueThis paper appliedthe firefly support vector machine in the supply chain financial evaluation for the first time. The output variable was described in a more detailed manner during the index define, and the random selection set in the process of FA-SVM data training.     

基于光子计数探测器的CT系统在蒙特卡罗模拟平台的实现

为了解决利用Matlab,C++等软件对投影图像、重建算法的模拟无法真实反映CT系统的成像过程的问题,在研究模拟理论的基础上,首先利用Geant4和Gate数据包搭建蒙特卡罗模拟平台;然后通过光子计数探测器模拟多能谱CT成像,同时分析在不同标准下的阈值划分对重建图像的影响,利用光子计数探测器同时扫描出多个不同能段下的投影图像,并对比出各个能段下的投影效果;其次,根据不同能段的划分,选取每个能段的360度下的投影数据,利用FBP算法重建投影切片图像;最后,对所得到的切片图像进行材料区分,得到硫和铝的衰减系数曲线。实验结果表明,模拟方法对光子计数探测器的成像过程做出了模拟,得到了较好的模拟图像,并给出了相关阈值的划分依据,可为其他CT成像研究提供参考。     

Traces of the Iron Curtain: A multivariate analysis of regional cohesion in Europe

The present study aims to test relative welfare differences among regions in Europe, so as to examine whether the post-communist era has led to more socio-economic cohesion in Europe. The performance of European regions is analysed, compared, and assessed by using the Regional Competitiveness Index (RCI) and stylised fixed nominal categories. The current status of regional cohesion is tested on the basis of detailed data on 268 NUTS 2 European regions by using a robust methodology oriented towards univariate comparison of location parameters, multivariate classification by the decision tree and CHAID algorithm, and comparison of nominal variables with four values based on density plots.Multivariate classification appears to offer statistically excellent results with an overall correct prediction rate for post-socialist and capitalist regions in Europe of 99.6%. The research results from the Higher education and Innovation pillars, reveal a convergence of capitalist and post-socialist regions with capital cities and a divergence of regions with administrative capitals and other regions. Relatively, the two groups which perform best are both groups with capitals, while the group of capitalist regions with a capital city is significantly better in almost all pillars.The key message is that the transition of post-socialist regions is not yet over. Capitalist regions in Europe perform better than post-socialist regions in eight of the nine pillars of regional competitiveness. Our research results also reveal that the group of post-socialist regions without capital cities are significantly lagging behind the rest of the regions in Europe, and thus form the most vulnerable group of European regions. As there is data continuity in the official RCI classification and measurement, policy makers will be able to compare the performance of their own regions over time and to design appropriate concerted strategies accordingly. From this perspective, our study draws several interesting lessons and results for policy makers at various levels. Place-based regional planning and policy based on our analysis framework may be helpful in developing effective measures to cope with the socio-economic legacy of the “Iron Curtain” and get closer to regional cohesion in Europe.