一类大时滞网络控制系统的H_∞鲁棒控制

研究一类大时滞不确定网络控制系统的输出反馈H∞鲁棒控制问题。将具有随机大时滞的网络控制系统模型化为具有不确定系数的离散时间系统模型,然后利用构造的Lyapunov函数和线性矩阵不等式,证明并给出了输出反馈H∞鲁棒控制问题有解的充分条件。所设计的控制器使系统具有鲁棒性,能满足所给H∞范数指标。最后通过算例验证结果的有效性。     

基于径向基神经网络的波达方向估计算法

针对传统的波达方向（DOA）估计算法在实际应用中普遍存在计算量较大,无法实时地跟踪期望信号且无法处理信号源数大于天线阵元数的问题,提出了一种在智能天线中基于径向基神经网络的波达方向估计算法.该算法利用神经网络进行多信号源跟踪（MUST）来完成信号源侦测和DOA估计.通过建立神经网络DOA估计算法模型,并对所建立的神经网络进行训练.通过仿真将该算法与传统的DOA估计算法进行比对的结果表明,基于径向基神经网络的波达方向估计算法能够快速准确的检测到信号源,响应时间明显快于传统的算法.     

Logistic回归和T检验在基因特征提取中的应用

针对基因表达谱数据特有的维数高、样本小、非线性的特点,对基因特征提取和分类进行研究,提出将Logistic回归和T检验方法引入基因的特征提取过程,通过Logistic回归初步筛选基因,T-test检验二次筛选特征基因,针对提取的特征构建分类器,得到提取的特征最少、分类效果最好的判别模型.建立分类模型的方法取得良好的癌症分类效果,具有很好的生物解释意义,为寻找致病基因提供了重要依据.     

两类误差下回归函数估计的收敛速度

在收敛系统和混合序列情形下,研究了固定设计下非参数回归模型中的回归函数估计。在误差为收敛系统时,得到了较弱矩条件下该估计的收敛速度;在误差为同分布混合序列时,得到了该估计的收敛速度。     

张量线性判别分析算法的脑灰质MRI结像分析

大脑结构MRI数据本质上是三维张量数据,而传统机器学习方法在提取大脑结构特性信息时,需要将其展开为一维向量,破坏了数据的内在结构信息.为了克服数据向量化带来的缺点,提出使用张量线性判别分析算法,用于大脑结构MRI数据分析.并对比基于向量的主成分线性判别分析算法,对20个正常人和20个精神病患者的脑灰质MRI结像进行分类.结果表明张量线性判别分析算法的最高识别率达到95%,其总体识别率、鲁棒性都要优于主成分线性判别分析算法.张量线性判别分析算法在大脑MRI数据分类上要优于传统基于向量的机器学习方法.     

基于有限障碍的全牛顿步内点算法

针对线性规划问题,文中引入了一种与传统障碍函数不同的新的障碍函数,其在可行域边界上的取值是有限的.沿此有限障碍函数所确定的新的搜索方向,给出了短步长全牛顿步内点算法,结果证明该算法具有目前求解线性规划问题最好的复杂性界.     

基于ARM的无人机真空速测量系统设计

设计了以ARM微处理器为核心的中央控制处理单元,用于无人机真空速测量系统中。通过公式分解,并采用线性低次插值算法,有效解决了真空速解算公式复杂的缺点;同时利用ARM的UART串口总线,实现了传感器输出特性曲线、真空速的上位机实时显示,使系统相对误差控制在2.5%以内。测试结果证明了该系统具有良好的实效性和稳定性、精度高,优于传统的测量装置。     

Type II robotic assembly line balancing problem: An evolution strategies algorithm for a multi-objective model

In this paper a different type II robotic assembly line balancing problem (RALB-II) is considered. One of the two main differences with the existing literature is objective function which is a multi-objective one. The aim is to minimize the cycle time, robot setup costs and robot costs. The second difference is on the procedure proposed to solve the problem. In addition, a new mixed-integer linear programming model is developed. Since the problem is NP-hard, three versions of multi-objective evolution strategies (MOES) are employed. Numerical results show that the proposed hybrid MOES is more efficient.     

Feature selection for classification of oscillating time series

We propose a forward sequential feature selection scheme based on k‐means clustering algorithm to derive the feature subset that classifies best the time series data base, according to the criterion of the corrected Rand index. Moreover, we investigate the effect of the standardization scheme on the feature selection and propose a standardization given by the transform to standard Gaussian distribution. Our interest in this work is in classification of oscillating dynamical systems on the basis of measures computed on time series from these systems. The features to be selected are measures of linear and non‐linear analysis of time series, such as auto‐correlation and Lyapunov exponents, as well as oscillation characteristics, such as the mean magnitude of peaks. Simulations on known oscillating deterministic and stochastic systems showed that, for repeated realizations of the same classification task, the proposed feature selection scheme selected very often the same best feature subset, giving high classification accuracy for any standardization. We found that, regardless of the standardization, the highest classification accuracy could be obtained with a small feature subset, containing most frequently an oscillating‐related feature. The same setting was applied to records of epileptic electroencephalogram signals, giving varying results and dependent on the standardization.