专家系统FRES 2.0在聚合物阻燃材料设计中的应用

本文应用聚合物阻燃材料设计专家系统软件ＦＲＥＳ２．０对一个１２组分的实际聚合物阻燃配方进行了优化设计和分析。所得到的优化配方和配方组成对性能影响规律很好地与实验数据相吻合。应用结果表明,以三层ＢＰ网络为基础的聚合物阻燃配方模型中以很好地解决聚合物阻燃配方知识获取中的严重非线性问题,同时也证明ＦＲＥＳ２．０软运行可靠,适用于聚合物阻燃料材料方的优化设计和分析。     

汽车制动复合材料智能设计系统研制

将人工神经网络的知识获取和表现方法引入专家系统,结合遗传算法,研制智能化的汽车制动材料计算机辅助设计系统。该系统能够从已有的试验数据中获取知识,利用基于人工神经网络的知识系统来模拟制动材料配方组分和摩擦学性能之间的映射关系,利用模糊匹配的方法实现新开发的配方和知识库中已有配方的匹配,利用遗传算法实现配方寻优过程,能够快速有效地设计符合用户要求的新型汽车制动材料配方。整个系统在Windows环境运行,具有良好的人机交互界面,便于调试、维护和移植。     

PVPEC：PTC和V－PTC材料优化设计专家系统

在用模式识别、人工神经网络法总结ＰＴＣ和Ｖ－ＰＴＣ材料诸性能与其配方及工艺间关系基础上，建立了能检索和预报ＰＴＣ和Ｖ－ＰＴＣ材料性能与其配方及工艺间双向关系的专家系统ＰＶＰＥＣ。该系统将为ＰＴＣ和Ｖ－ＰＴＣ材料优化设计提供有效的辅助手段。     

人工神经网络用于高分子材料的性能预测与优化设计的研究进展

论述了人工神经网络预测聚合物、复合材料的性能及聚合物组成的方法和效果,总结了人工神经网络用于高分子材料成型加工的质量控制与条件优化的研究状况,讨论了人工神经网络用于高分子 性能预测与优化设计的优缺点,指出了人工神经网络在高分子科学领域中应用的发展方向和需要解决的问题。     

PVPEC：PTC和V—PTC材料优化设计专家系统

在用模式识别，人工神经网络法总结了ＰＴＣ和Ｖ－ＰＴＣ材料诸性能与其配方及工艺间关系基础上，建立了能检索和预报ＰＴＣ和Ｖ－ＰＴＣ材料性能与其配方及工艺间双向关系的专家系统ＰＶＰＥＣ，该系统将为ＰＴＣ和Ｖ－ＰＴＣ材料优化设计提供有效的辅助手段。     

基于专家—神经网的递阶智能控制系统

本文介绍了专家系统与人工神经网络技术相结合的一些方法，提出了联合使用专家系统与人工神经网络的递阶智能控制系统结构，其组成为：监督控制专家系统，数据处理与故障诊断神经网络，常规分布式控制系统。其中的监督控制专家系统又由人工神经网络模拟实现。由于本系统吸取了专家系统技术及人工神经网络技术两者的长处，克服了各自的缺点，使得系统的性能大为提高。     

专家系统与人工神经网络在决策支持系统中的集成

该文介绍专家系统和人工神经网络在决策支持系统中的集成的合理性、机理和应用方法。综合应用专家系统、人工神经网络、数学模型和一般的决策方法，可以使复杂问题的决策变得较为容易和可行。该文也为计算机仿真技术在智能决策支持系统中的应用提供了一种方法，并揭示了对有关经济决策问题进行计算机仿真的特点。     

知识管理在磁性材料行业的应用

为了对磁性材料行业的材料配方和性能配方之间的知识进行有效管理,和准确预测材料配方和性能之间的变化趋势,提出了一个基于神经网络的磁性材料设计方法,并在此基础上实现了磁性材料设计专家系统.首先对配方和性能的基础数据进行了管理,然后通过生产实验数据训练神经网络,实现了性能和配方的相互推导,最后对配方或性能的变化趋势进行了准确预测.实验结果表明,专家设计系统的趋势预测具有极高的精确性.企业实施该系统后较大幅度的提高了新产品的开发速度,提高了企业的市场竞争力.     

智能计算在中医诊断系统中的应用研究

主要讨论智能计算方法在中医诊断中的应用。分析中医诊断的特点。介绍了包括专家系统、人工神经网络、模糊聚类以及集成人工神经网络和专家系统等在内的中医诊断系统实现方案,并讨论了这些方案的优点和不足。     

智能计算在中医诊断系统中的应用研究

主要讨论智能计算方法在中医诊断中的应用。分析中医诊断的特点。介绍了包括专家系统、人工神经网络、模糊聚类以及集成人工神经网络和专家系统等在内的中医诊断系统实现方案,并讨论了这些方案的优点和不足。     

The correctness problem: evaluating the ordering of binary features in rankings

In machine learning, feature ranking (FR) algorithms are used to rank features by relevance to the class variable. FR algorithms are mostly investigated for the feature selection problem and less studied for the problem of ranking. This paper focuses on the latter. A question asked about the problem of ranking given in the terminology of FR is: as different FR criteria estimate the relationship between a feature and the class variable differently on a given data, can we determine which criterion better captures the “true” feature-to-class relationship and thus generates the most “correct” order of individual features? This is termed as the “correctness” problem. It requires a reference ordering against which the ranks assigned to features by a FR algorithm are directly compared. The reference ranking is generally unknown for real-life data. In this paper, we show through theoretical and empirical analysis that for two-class classification tasks represented with binary data, the ordering of binary features based on their individual predictive powers can be used as a benchmark. Thus, allowing us to test how correct is the ordering of a FR algorithm. Based on these ideas, an evaluation method termed as FR evaluation strategy (FRES) is proposed. Rankings of three different FR criteria (relief, mutual information, and the diff-criterion) are investigated on five artificially generated and four real-life binary data sets. The results indicate that FRES works equally good for synthetic and real-life data and the diff-criterion generates the most correct orderings for binary data.     

Watershed Forest Management Information System (WFMIS)

Maintenance of a sustainable clean water supply is critical for our future. However, watershed degradation is a common phenomenon around the world that leads to poor water quality. In order to protect water resources, the Watershed Forest Management Information System (WFMIS), was developed as an extension of ArcGIS^® and is described in this paper. There are three submodels to address nonpoint source pollution mitigation, road system management, and silvicultural operations, respectively. The Watershed Management Priority Indices (WMPI) is a zoning approach to prioritize critical areas for conservation and restoration management. It meets the critical need to spatially differentiate land cover and site characteristics within a watershed to quantify their relative influence on overall water quality. The Forest Road Evaluation System (FRES) is a module to evaluate road networks in order to develop preventive management strategies. The Harvest Schedule Review System (HSRS) is a module to analyze and evaluate multi-year and multi-unit forest harvesting to assist in the reduction of impact on water yield and associated changes in water quality. The WFMIS utilizes commonly available spatial data and has user friendly interfaces to assist foresters and planners to manage watersheds in an environmentally healthy way. Application examples of each submodel are presented.     

Interactive hybrid (symbolic-numeric) system approach to near optimal design of mechanical components

A hybrid symbolic-numeric system, referred to as OPTDEX, (Optimal Design Expert) for the optimal design of mechanical components and systems has been developed. The system is written in Golden Common LISP and IBM Professional (Ryan-McFarland) FORTRAN for execution on the IBM PC/AT microcomputer. Graphical output has been implemented using the Graphical Kernal System (GKS) standard. This microcomputer-based implementation makes the system particularly attractive as an easily accessible, low-cost engineering analysis and design tool.Experience with the system indicates that the time required to achieve, at least partially optimized engineering design solutions, is similar to that which may be expected with standard, nonoptimization-based microcomputer computation. Any added computational time may be justified and subsequently offset by increased long-term design efficacy.The OPTDEX protocol (Fig. 1) assumes a modular form, whereby each level can be modified, updated, and enhanced independently of the others to accommodate various design philosophies and the subdivision of large-scale design problems. A design cell approach has been adopted that has the capability of addressing the design of various mechanical components and systems. The current version of the OPTDEX design cell library, which is undergoing revision and expansion, includes speed reducer, bearing, coupling, and shaft design capabilities.This modular structure and generalized design cell approach, which underlies the OPTDEX system, establishes the basis of a formalized methodology for mechanical engineering design, which may be extended to include other design-related disciplines as well. For example, with the addition of appropriate design cells, the system can be configured for VLSI circuit design in electrical engineering, scheduling, and job routing in industrial engineering, and structural design in civil engineering.     

Tangible products: redressing the balance between appearance and action

Over the past decade, our group has approached interaction design from an industrial design point of view. In doing so, we focus on a branch of design called formgiving. Traditionally, formgiving has been concerned with such aspects of objects as form, colour, texture and material. In the context of interaction design, we have come to see formgiving as the way in which objects appeal to our senses and motor skills. In this paper, we first describe our approach to interaction design of electronic products. We start with how we have been first inspired and then disappointed by the Gibsonian perception movement [1], how we have come to see both appearance and actions as carriers of meaning, and how we see usability and aesthetics as inextricably linked. We then show a number of interaction concepts for consumer electronics with both our initial thinking and what we learnt from them. Finally, we discuss the relevance of all this for tangible interaction. We argue that, in addition to a data-centred view, it is also possible to take a perceptual-motor-centred view on tangible interaction. In this view, it is the rich opportunities for differentiation in appearance and action possibilities that make physical objects open up new avenues to meaning and aesthetics in interaction design.     

Evaluation of the basic remote backup and replication methods for high availability databases

In this paper, we describe the properties of two 0‐safe backup/replication methods and compare them with the traditional 1‐safe and 2‐safe backup/replication methods. The 1‐safe and 2‐safe backup/replication methods have been analyzed for many years, and their problems are well known. The properties of the 0‐safe designs have not yet been analyzed. The basic 2‐safe, 1‐safe and 0‐safe backup designs all use two copies of the database. However, under normal operation the database copies of the 2‐safe backup design are both consistent and up‐to‐date, whereas the 1‐safe backup design only uses one up‐to‐date copy of the database. In the 0‐safe backup design none of the databases are consistent and up‐to‐date. Therefore, this backup design is named 0‐safe. However, in the 0‐safe design the two inconsistent copies converge towards the same consistent state. In a 0‐safe design transactions update and commit the nearest database copy first and, therefore, the database copies are normally inconsistent. The inconsistency between the 0‐safe database copies must be managed by using countermeasures, which will reduce the problems of the missing distributed isolation property. We will also describe and evaluate a mixture of the 0‐safe and the 1‐safe designs, which in certain situations may have more interesting properties than the original designs. The backup/replication designs will among other things be compared with respect to their disaster recoverability, availability, performance, implementation problems and ACID properties. The largest bank in Denmark, Den Danske Bank, has converted all its important database systems from using the 1‐safe design to using the 0‐safe design. We have been cooperating with one of the major ERP (Enterprise Resource Planning) software companies in designing a distributed version of their financial management and accounting system by using the techniques described in this paper. We have now started to implement a prototype of the system. Copyright © 1999 John Wiley & Sons, Ltd.     

Determinants of e-consumer productivity in product retrieval on a commercial website: An experimental approach

This article investigates what determines e-consumer productivity, in the specific case of product retrieval, on a commercial website. With a 2 × 2 × 2 factorial design on 292 participants, an online experiment reveals that productivity in product retrieval (measured in terms of effectiveness, efficiency, and time) relates to website design (e.g., abstraction level of labels, animation), user characteristics (e.g., Internet experience, product category familiarity, cognitive absorption), and situational characteristics (e.g., task nature). The results also confirm interactive effects among the type of strategy used, the nature of the task, and the website design. These findings have notable implications for both research and practice.     

新型国家标准件零件CAD库建立

本文介绍了一种新型的国家标准件零件CAD库，具体描述了其系统结构、数据结构和主要的实现技术。该系统融合了数据库和计算机辅助设计等多种技术，具有灵活的输入手段，自行建立本部门常用零件库的能力和友好的人机界面，实现了机械设计过程中快速查阅零件参数、自动生成零件各向视图的二维图形和三维模型，提高了设计工作的质量和效率。     

Computer-mediated persuasion in online reviews: Statistical versus narrative evidence

The current study examined the effects of online product reviews on individuals’ credibility perceptions of the reviews and their attitudes about the product targeted in the reviews. Study 1 used a 2 (review type: statistical and narrative) × 2 (review valence: negative and positive) design, and study 2 used a 2 (statistical review valence: positive and negative) × 2 (narrative review valence: positive and negative) design. The findings of study 1 were consistent with those of study 2 and indicated that negative statistical reviews were perceived as more credible than negative narrative reviews, while the credibility of positive statistical reviews did not differ from that of positive narrative reviews. On the other hand, statistical reviews and narrative reviews did not differ in terms of affecting individuals’ attitudes about the product. The current study also found that the vividness and valence of each review type had varying effects on review credibility and attitudes about the product. The implications of these and other findings are discussed in detail in the paper.