无界报酬向量值折扣马氏决策规划—最优平稳策略及算法

本文主要讨论了无界报酬向量模型的平稳策略问题，给出了改进平稳策略的方法，建立起向量模型的最优方程，获得平稳策略为强最优策略的充要条件．指出最优平稳策略的期望报酬函数必为极大不动点，最后提出一种寻求最优平稳策略的策略迭代算法．     

课表的多指标数学模型及解决方法

课程表问题又称时间表问题(timetable problem)，是一个多指标的优化决策问题，也是组合规划中的典型问题．对已有的时间表问题进行探讨，并研究其数学模型及解决方法．     

煤炭燃前脱硫技术评价体系

煤炭脱硫为洁净煤技术的优先发展技术.通过对影响燃前脱硫技术的诸因素分析和项目技术经济比较,构筑了煤炭燃前脱硫技术评价体系.评价体系中采用模糊数学等有关理论提出了模糊综合评价法.评价示例表明在采用多种燃前技术脱硫时,综合评价指数最高的方法为重介旋流器脱硫法.     

基于决策树方法的银行客户信用评估

分析了传统银行客户信用评估方法存在的问题,针对ID3算法存在的不足,提出了一种改进的ID3算法.实验结果表明,改进后的ID3算法分类正确率有所提高,所生成的决策树较为健壮、简洁,可以减少计算代价,提高计算效率.     

决策树在文本分类中的应用

介绍了文本分类的思想,探讨了通过决策树学习来对文本进行有效分类的过程。     

受托责任论与决策有用论的影响——我国会计目标的现实选择

会计目标关系到会计基本理论框架的构建以及会计实务的拓展。美国会计界关于会计目标的研究形成两个主要流派——受托责任学派和决策有用学派。探讨了这两种观点对会计理论和实务的影响,以构建出真正符合我国现阶段经济环境的会计目标理论。     

基于模糊数学的计算机性能评价和销售预测的研究

根据模糊数学理论,运用模糊意见集中评价和模糊综合评价方法,计算机性能评价和销售预测进行研究,为评价差别不是很明显和含有多种因素的事物,提供了科学有效的方法.     

Decision Support Systems (DSS) development using a model of user inquiry types: Methodological proposals and a case study

A study of the DSS implementation area reveals an increased emphasis on methodologies for DSS development. As the DSS field matures, a larger number of methodological options are becoming available to the DSS developer. Existing methodologies have adopted various methods for performing the important task of DSS requirements analysis and specification. In envisaging a hierarchy of requirements analysis methods, a method for improved requirements analysis is proposed to remedy observed deficiencies within it. This method is based on a view of generic types of inquiries or solicitations made by the DSS user during decision-making. This formalism constitutes the basis of a proposed DSS development methodology that offers several benefits to DSS development. The intended benefits include a sharper and more focused requirements analysis to improve the DSS development process. This paper describes the model and methodology, alongside details of a real-world example of their use in developing a Marketing Decision Support System (MKDSS) for the support of marketing decision-making.     

基于OBDD时序电路设计的验证

依据有序二叉判定图（OBDD）和计算树逻辑（或称分支时态逻辑）CTL（Computational Tree Logic)的基本原理，分析了基于OBDD和CTL的验证数据电路设计的基本原理，并在此基础上，给出了时序电路等价验证的方法。     

MARKOV DECISION PROGRAMMING-THE FIRST PASSAGE MODEL WITH DENUMERABLE STATE SPACE

In this paper,we discuss MDP with discrete time parameter-the firstpassage model with denumerable state space.Under assumption A in this paper,we prove that an ε(>0)-optimal stationary policy exists.To find an ε-optimalstationary policy,an algorithm of policy improvement iteration and a method ofsuccessive approximations are given.