基于一乘准则的LMR在声音转换中的应用

线性多变量回归中聚类数的选择对转换效果有很大影响,通过研究聚类数与类内均方差、类间均方差的关系确定最佳聚类数。针对传统二乘规则的 LMR 的转换语音在听觉上自然度较差的缺陷,提出了基于一乘规则的 LMR,采用遗传算法解决绝对值条件下转换矩阵的求解问题,实验仿真表明,基于一乘规则的 LMR 的转换语音在主观听觉上优于基于二乘规则的 LMR,ABX 测试识别率平均提高了12.5%,MOS 分提高了0.24。     

基于均分簇算法的战争Ad Hoc网络广播风暴抑制

网络广播是维持网络正常运作的基本手段,但Ad Hoc网络拓朴的频繁变化,将使网络广播无法进行收敛,形成广播最终会使本来就受限的资源趋于濒绝,网络无法通信而瘫痪.为此,提出了一种自适应均分簇理论SACA,通过分层虚拟子网的过滤与阻隔算法,有效地抑制网络广播风暴.     

基于模糊聚类的多目标跟踪算法

提出了一种新的基于模糊聚类的多目标跟踪算法,该算法通过一种改进的模糊聚类算法,首先得到可能的目标数和测量点迹与目标预测位置之间的隶属度,然后结合Kalman滤波将隶属度作为权值系数对预测新息向量进行加权,来实现目标状态估计的更新。仿真结果表明,传统数据融合多目标跟踪算法,一般需要假定目标数并且在多目标密集时易产生关联错误而导致跟踪发散,新算法通过模糊聚类客观有效地确定了目标数并且通过加权过程保证了对多目标密集时的高精度。     

基于蚁群算法的图像边缘检测研究

将蚁群算法应用于图像分割领域,提出了一种新的基于蚁群算法的图像边缘检测方法。详细阐述了蚁群算法与该方法的基本原理和具体实现过程。为了提高算法效率,进行两处改进,第一将蚂蚁初始位置由随机放置修改为放置在图像边缘附近,可取一图像灰度梯度阈值来实现,第二将信息激素强度和启发式引导函数值均定义为像素点灰度梯度值的函数。大量实验结果证明了该算法能有效地检测出图像边缘,而且具有适应性强、效率高等特点。     

防空体系作战能力灰色聚类评估

从分析现代防空体系的组成出发,建立了较完备的防空体系作战能力评估指标体系,提出了一种基于灰色定权聚类和三角白化权函数的防空体系作战能力灰色聚类评估方法,并通过算例对方法的有效性进行了检验。结果表明该方法用于防空体系作战能力的评估是切实可行的。     

未知数量稀疏源盲分离的一种新方法

提出了一种新的用于未知数量稀疏源盲分离的统一方法。为了改善聚类分离的精度,该方法选取混合空间中半径给定的、中心位于原点的超球面以外的所有数据点,然后将这些数据点映射到中心位于原点的单位超球面上以得到集合Cy。由此,原来的聚类变为致密聚类,各聚类互相重叠的现象几乎消失。随后,先通过关于Cy的聚类分离来估计混合矩阵,再根据混合矩阵估计源,其中最佳不相似阈值和相应的聚类数量是自动生成的。计算机仿真结果验证了该方法对具有不同程度稀疏性源的有效性。当源充分稀疏时,重构信噪比大约是300 dB。因此,该方法精确、便利。     

Complexity and workload considerations in product mix decisions under the theory of constraints

The literature on the product mix decision (or master production scheduling) under the Theory of Constraints (TOC), which was developed in the past two decades, has addressed this problem as a static operational decision. Consequently, the developed solution techniques do not consider the system's dynamism and the associated challenges arising from the complexity of operations during the implementation of master production schedules. This paper aims to address this gap by developing a new heuristic approach for master production scheduling under the TOC philosophy that considers the main operational factors that influence actual throughput after implementation of the detailed schedule. We examine the validity of the proposed heuristic by comparison to Integer Linear Programming and two heuristics in a wide range of scenarios using simulation modelling. Statistical analyses indicate that the new algorithm leads to significantly enhanced performance during implementation for problems with setup times. The findings show that the bottleneck identification approach in current methods in the TOC literature is not effective and accurate for complex operations in real‐world job shop systems. This study contributes to the literature on master production scheduling and product mix decisions by enhancing the likelihood of achieving anticipated throughput during the implementation of the detailed schedule. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 357–369, 2015     

区域物资动员潜力的多元统计分析

为分析不同区域物资动员潜力差异,并对其进行分类,从总体实力和产值结构两方面出发,建立了区域物资动员潜力指标体系。以我国行政区域为研究样本,通过SPSS18软件,结合年度统计数据进行分析。采用主成分分析法对方案层指标进行简化,将形成的综合得分标准化并分析主成分上的载荷,然后采用层次分析法得到总体实力得分。再将研究对象按照总体实力与产值结构进行ward聚类分析,得到6个区域类别,分析其特点,提出动员建议。     

基于雷达网拓扑特征的雷达目标编群算法

为有效评估战场电磁态势和实施雷达网对抗,研究雷达目标编群算法十分必要。提出了一种基于拓扑特征分析的雷达目标编群算法,在分析雷达网拓扑结构及其特征基础上,利用拓扑特征实现雷达目标群的建立和更新,完成雷达目标编群。仿真实例表明算法具有可行性和有效性,为电磁态势评估和雷达网对抗奠定了基础。     

Efficient algorithms for flexible job shop scheduling with parallel machines

Job shop scheduling with a bank of machines in parallel is important from both theoretical and practical points of view. Herein we focus on the scheduling problem of minimizing the makespan in a flexible two-center job shop. The first center consists of one machine and the second has k parallel machines. An easy-to-perform approximate algorithm for minimizing the makespan with one-unit-time operations in the first center and k-unit-time operations in the second center is proposed. The algorithm has the absolute worst-case error bound of k − 1 , and thus for k = 1 it is optimal. Importantly, it runs in linear time and its error bound is independent of the number of jobs to be processed. Moreover, the algorithm can be modified to give an optimal schedule for k = 2 .