基于多维分段和动态权重DTW的多元时间序列相似性度量方法

针对常用方法无法准确度量多元时间序列相似程度的问题,提出一种基于多维分段和动态权重动态时间弯曲距离的多元时间序列相似性度量方法.首先对多元时间序列进行多维分段拟合,选取拟合段的斜率、均值和时间跨度作为每一段的特征,在对多元时间序列降维的同时也保留了变量之间的相关性;然后提出一种动态权重动态时间弯曲距离度量方法计算多元时间序列特征矩阵之间的距离,避免了直接使用动态时间弯曲距离造成的畸形匹配问题.最终实验结果也验证了该方法在多种类型的数据集上都能取得较高的度量精度,表明了该方法的有效性.     

新型粒子群算法在多元方程组求解中的应用

介绍了求解多元方程组的一种新型粒子群算法。通过引入多路并行的粒子群与可变异惯性权重,有效地增加了算法种群的多样性,提高了算法的整体寻优能力,使传统粒子群算法容易陷入局部最优解的问题得到了有效解决。最后通过求解运算,与传统粒子群算法进行比较,验证了该算法在求解多元方程组问题上的优越性。     

改进型灰狼算法在热电偶动态补偿中的应用

为解决热电偶传感器在瞬态温度测试过程中因传感器动态性能不足引入动态误差影响测试精度的问题,提出基于改进型灰狼优化算法的热电偶传感器动态补偿方法.通过改变候选解产生策略和引入动态权重因子,对灰狼优化算法(GWO)进行改进,从而进一步提高了热电偶传感器的时间常数.根据热电偶传感器水浴法校准数据寻优获得补偿系统传递函数,并对实测火焰数据进行实验.实验结果表明,水浴法校准数据经补偿后时间常数由0.0685s提升为0.0147s,动态误差减小了近75%.经IGWO寻优获得的动态补偿系统,可有效地改善热电偶传感器的动态特性,减小热电偶传感器的动态误差.     

动态模糊综合评判在教学质量评价中的应用

根据教学质量评价的特点,针对传统模糊综合评判的不足,主要是针对其评价结果不能很好地反映评价目标的动态发展趋势的问题,提出了基于动态模糊理论的教学质量综合评判方法,给出了一种基于群体可拓层次分析法的动态模糊权重确定方法和动态模糊关系矩阵的确定方法,并结合一个具体的评价实例,验证了所提方法的科学性和客观性。     

多元SPA动态聚类统计分析及其应用

提出了一种动态聚类统计分析方法,该方法融合了集对理论中的多元联系数的不确定性和聚类分析的思想,通过计算模糊相似矩阵和传递闭包,选取λ进行模糊聚类,并可针对不确定值的变化分析对其进行动态调整.将该方法应用于高校相近专业课程的集对聚类,按照教师工作量均衡的原则,构建了高校相近专业师资配置优化模型,给出了一套师资优化策略,依照动态调整的原则对各相近专业的师资进行整合,达到高校相近专业师资共享的目的.     

标志在视像设计中的动态演绎

在品牌的视像媒体宣传中,标志的动态设计无疑是至关重要的环节,对此课题的研究与探讨也日益受到业界的关注。文章从时空关系、辅助图形的衬托、声音切入、表现手法这四个方面进行分析,阐述标志在视像设计中动态演绎的特点,并指出其形式为图形内涵延伸提供广阔空间的实质。     

演绎机制在DOOD中的实现

利用原有的OODBBMS构造演绎面向对象的核心技术是演绎机制的设计与实现。本文介绍了演绎机制在DOOD中的设计与实现原理,并通过实例进一步说明了其解析和实现过程。     

多元分析法在沉淀滴定中的应用

将多元分析法应用于沉淀滴定之中 ,提出固定电位的方法 ,建立了沉淀滴定中各组分浓度与体积之间关系的数学模型 ,对卤素和硫氰酸盐混合体系进行了测定。     

逆演绎学习算法在智能通信网中的应用

在智能通信网的学习过程中,针对传统归纳演绎学习的困难,提出一种逆演绎的学习算法。从学习任务和逻辑程序角度出发,研究逆演绎学习算法的规则、霍恩状态函子和激励信息等问题,并利用逆演绎的学习算法实现了智能通信网的学习推理系统。测试结果表明,该算法能高效地归纳出逻辑程序。     

多元绑定技术在校园网安全策略中的应用

随着校园网应用不断地发展、用户数量的不断增加、地址盗用等安全问题严重威胁着校园网的安全。本文分析了目前常用的地址盗用技术,提出了几种多元绑定技术安全策略,实现对校园网用户进行有效访问控制,以保障校园网安全。     

Hierarchical deduction

This paper describes an hierarchical deduction proof procedure. This procedure proves a theorem by searching for a proof acceptable to an hierarchical deduction structire; those derivations which are irrelevant to this proof are limited by means of a set of completeness-preserving refinements of the basic procedure, such as constraints on framed literals and on common tails, a proper reduction refinement, a global subsumption constraint, and a level subgoal reordering refinement, etc. In addition to this basic algorithm, we will present a partial set of support strategy and a semantically guided hierarchical deduction for the incorporation of semantics and human factors. The paper concludes with proofs concerning the completeness of the basic algorithm and the results of a computer implementation applied to some nontrivial problems.This work was supported in part by NSF grant MCS-8313499.     

授权管理中的权限衍生计算方法

权限之间的衍生关系简化了授权管理,同时也增加了权限判决的难度,准确、高效地计算权限衍生对授权和访问控制具有重要意义。在给出基于资源和操作层次的权限衍生规则基础上,针对授权管理中权限查询较频繁而权限更新较少的特点,设计了一种新的基于可达矩阵的权限衍生计算方法,并研究了权限衍生关系动态调整的算法步骤。仿真实验表明,当权限的数量较大时,该新方法比基于权限衍生规则的直接计算方法具有较高的计算效率。     

Parallelization of deduction strategies: An analytical study

In this paper we present a general analysis of the parallelization of deduction strategies. We classify strategies assubgoal-reduction strategies, expansion-oriented strategies, andcontraction-based strategies. For each class we analyze how and what types of parallelism can be utilized. Since the operational semantics of deduction-based programming languages can be construed as subgoal-reduction strategies, our analysis encompasses, at the abstract level, both strategies for deduction-based programming and those for theorem proving. We distinguish different types of parallel deduction based on the granularity of parallelism. These two criteria — the classification of strategies and of types of parallelism — provide us with a framework to treat problems and with a grid to classify approaches to parallel deduction. Within this framework, we analyze many issues, including the dynamicity and size of the database of clauses during the derivation, the possibility of conflicts between parallel inferences, and duplication versus sharing of clauses. We also suggest the type of architectures that may be suitable for each class of strategies. We substantiate our analysis by describing existing methods, emphasizing parallel expansion-oriented strategies and parallel contraction-based strategies for theorem proving. The most interesting and least explored by existing approaches are the contraction-based strategies. The presence of contraction rules — rules that delete clauses — and especially the application ofbackward contraction, emerges as a key issue for parallelization of these strategies. Backward contraction is the main reason for the impressive experimental success of contraction-based strategies. Our analysis shows that backward contraction makes efficient parallelization much more difficult. In our analysis, coarse-grain parallelism appears to be the best choice for parallelizing contraction-based reasoning. Accordingly, we propose a notion ofparallelism at the search level as coarse-grain parallelism for deduction.Supported by the GE Foundation Faculty Fellowship to the University of Iowa and by the National Science Foundation with grant CCR-94-08667.Supported by grant NSC 83-0408-E-002-012T of the National Science Council of the Republic of China.     

Disjunctive partial deduction of a right-to-left string-matching algorithm

In spite of its practical importance, the Boyer-Moore string-matching algorithm has hardly been studied in the context of partial evaluation. We show how to derive the search stage of a variant of this algorithm using “disjunctive” partial deduction.     

命题演算两个推理系统的等价性

首先介绍命题演算的Gentzen型系统G,然后给出一个命题演算的永真推理系统H,最后证明一个命题在G中可证当且仅当它在H中可证,从而G与H是等价的.     

Intelligent backtracking in deduction systems by means of extended unification graphs

A method for unification as the basis for intelligent backtracking in deduction systems is described. This method is based on the unification graphs introduced by Cox. In this paper, unification graphs are used in an extended form such that they represent all the information which can be gained from the unification constraints, i.e., the expression to be unified, their subterms which, as a consequence, are to be unified, the number of deduction steps which cause the unification of two terms, and the term-subterm relation as far as necessary. If a unification conflict occurs from this information, the deduction steps which have led to these conflicts can be determined and reset. This is done by searching for loop-free paths or loops with certain properties in the extended unification graph, according to the type of unification conflict. Algorithms for the handling of the unification graph and for the extraction information from it are described and proved as correct.     

相干命题逻辑自然推理系统NR的自动证明*

给出了相干命题逻辑自然推理系统NR的自动证明算法。首先将待证命题公式A的子公式组成一个初始集合P,对其中的元素采用系统NR的推理规则得到新的命题公式加入P,当得到秩为0的A时命题得证;然后对A的证明树进行整理即得到演绎序列。对系统NR的大部分定理证明取得了良好的效果,算法生成的演绎序列清晰可读,接近手工推理。     

动态二进制翻译中数据预取优化研究*

动态优化是动态二进制翻译研究中一个十分重要的课题,数据预取优化能提高现代处理器体系结构应用程序性能。基于超级块(Superblock)的动态数据预取优化采用软件插桩方式收集应用程序的load访存延迟信息并构造Superblock;然后根据延迟信息以及Superblock数据流分析得出的寄存器定值引用关系,对延迟load指令进行预取优化。通过在龙芯DigitalBridge动态二进制翻译系统上实验验证,数据预取优化可以提高翻译后SPEC2000浮点测试程序代码的平均性能3.3%,开销远小于0.5%。