一种用于模式识别的多色Voronoi图

提出了一种新的Voronoi图———多色Voronoi图 ,并证明了它的一些重要性质。多色Voronoi图是在Voronoi图的构造过程中 ,根据数据集的特性给Voronoi图染色的结果。用多色Voronoi图概念设计的模式分类器(MCVC)是一种非线性多类别最优分类器 ,可以解决线性可分和线性不可分问题 ,同时MCVC对新增加的训练样本具有快速局部学习能力 ,这种局部学习能力克服了神经网络方法常出现的过学习问题 ,很类似于人对概念的学习。将多色Voronoi图概念用于支撑矢量机的构造中 ,进行支撑矢量的预选取 ,可以提高支撑矢量机的学习速度     

ORGANIZATIONAL LEARNING AND VENDOR SUPPORT QUALITY BY THE USAGE OF APPLICATION SOFTWARE PACKAGES： A STUDY OF ASIAN ENTREPRENEURS

In this paper we study how organizational learning impacts organizational behavior, and howvendor support quality enhances product adoption and usage behavior.These constructs were verifiedusing Application Software Packages(ASP)-a prewritten, precoded, commercially available set ofprograms that eliminates the need for individuals or organizations to write their own softwareprograms for certain functions. The relationship between ASP usage, usage outcomes and useprocesses were also investigated. Two hundred and ninety-five Chinese, Indian, and Malayentrepreneurships were studied. It was found that usage outcome strongly determines usage, while useprocess has only an indirect relationship (via outcome) on usage. The impact of organizational learningand vendor service quality on usage, usage outcome, and use process were robust. Theoretical andpractical implications of the research are discussed.     

SCHEDULING PROBLEMS - AN OVERVIEW

There seems to be a significant gap between the theoretical and the practical aspects of scheduling problems in the job shop environment. Theoretically, scheduling systems are designed on the basis of an optimum approach to the scheduling model. However in the practice, the optimum that is built into the scheduling applications seems to face some challenges when dealing with the dynamic character of a scheduling system, for instance machine breakdown or change of orders. Scheduling systems have become quite complex in the past few years. Competitive business environments and shorter product life cycles are the imminent challenges being faced by many companies these days. These challenges push companies to anticipate a demand driven supply chain in their business environment. A demand-driven supply chain incorporates the customer view into the supply chain processes. As a consequence of this, scheduling as a core process of the demand-driven supply chain must also reflect the customer view. In addition,     

基于支持向量机的非线性系统辨识

支持向量机（SVM）是一种基于结构风险最小化原理的学习技术，也是一种新的具有很好泛化性能的回归方法，该文利用支持向量机对非线性系统进行黑箱建模，介绍了V-SVR的基本理论，并进行了仿真实验，结果验证了所提出的方法的正确性和有效性。     

基于修正核函数SVM的网络入侵检测

支持向量机分类方法在小样本、非线性情况下具有较好的泛化性能,在入侵检测系统中有着广泛的应用。针对入侵检测过程中可能出现的由两类样本不平衡造成的分离超平面偏移现象,以核函数所蕴含的黎曼几何为依据,引入一个伪一致性变换函数,对核函数进行修改,提高支持向量机的分类泛化能力,建立基于支持向量机的网络入侵检测系统,并对系统总体结构和运行机制进行了详细的描述。实验仿真表明,该系统可有效地提高入侵检测的准确率,改善由于数据集不平衡造成的支持向量机分类偏移的情况。     

Improved adaptive pruning algorithm for least squares support vector regression

As the solutions of the least squares support vector regression machine(LS-SVRM) are not sparse,it leads to slow prediction speed and limits its applications.The defects of the existing adaptive pruning algorithm for LS-SVRM are that the training speed is slow,and the generalization performance is not satisfactory,especially for large scale problems.Hence an improved algorithm is proposed.In order to accelerate the training speed,the pruned data point and fast leave-one-out error are employed to validate the temporary model obtained after decremental learning.The novel objective function in the termination condition which involves the whole constraints generated by all training data points and three pruning strategies are employed to improve the generalization performance.The effectiveness of the proposed algorithm is tested on six benchmark datasets.The sparse LS-SVRM model has a faster training speed and better generalization performance.     

通用综合评价支持系统的可配置评价模型研究

针对综合评价支持系统的通用性问题,给出了一种可配置评价模型的设计思想与实现方法。首先分析了综合评价的关键要素及其过程,定义了通用综合评价支持系统(UCESS)的数学模型,据此提出基于AOV(Activity on Vertex Network)网的评价模型构建方法,即通过AOV网描述评价模型的拓扑结构,并根据其拓扑排序来控制评价模型的执行过程,最后给出了采用组件技术的模型设计与实现策略。应用所提出的方法,UCESS能够实现自由意义上的评价模型动态配置,具备良好的灵活性和开放性。     

舰艇编队保障系统的备件短缺风险研究

针对舰艇编队存在备件短缺风险的问题,提出舰艇编队保障系统的概念,给出舰艇编队使用可用度的计算方法,讨论三者之间的关系并建立数学模型。考虑实际中,执行复杂任务的舰艇编队其部件具有不同的寿命分布,替换时间差别大,不少备件维修后能够继续使用以及备件可修次数受限的情况,建立多可修备件的短缺风险计算模型及其与舰艇编队使用可用度的关系模型。最后通过实例对模型进行仿真,对降低备件短缺风险,提高舰船装备使用可用度有一定的参考价值。     

面向多极值质量特性的全局式序贯性实验设计方法

针对多极值质量特性的全局性建模和参数优化问题, 为降低实验设计样本量, 提高模型预测性能, 提出一种全局式序贯性设计方法. 首先在一定的初始实验设计方式下, 建立过程粗略的SVR模型; 而后根据模型中支持向量的分布, 在支持向量样本各维度的45度角或轴向方向同步地增加实验点, 再拟合过程新的SVR模型; 如此迭代进行, 当模型精度达到要求或样本量达到上限时终止序贯性设计. 仿真与实证研究表明, 该方法能够在可行域全局的范围内将实验点合理地分配在质量特性的多个极值附近, 避免了传统的单路径式序贯性设计只能发现单个极值的不足, 充分提高了实验效率; 与均匀空间网格设计、 拉丁超立方设计和均匀设计相比, 在样本量接近的情况下, 基于全局式序贯性设计的SVR 模型的预测均方误差至少降低了30%; 而在预测误差较为接近的情况下, 全局式序贯性设计的样本量至少降低了12%.     

多准则、多目标决策评价系统的设计与实现

以导弹系统设计方案评应用为背景,针对多准则、多目标的决策问题,研究和设计系统化的决策评价体系,完成具有核心功能的,通用性、实用性较好的多准则、多目标决策评价工具,对复杂的决策问题提供决策支持。