全国博士生学术会议10月举办

由教育部学位管理与研究生教育司、国务院学位委员会办公室主办的2009全国博士生学术会议系列会议将于10月举行。其中，计算机视觉与人工智能学术研讨会由天津大学承办，于10月14日在天津大学举行。会议内容包括：计算机视觉（视觉理论及算法、视觉认知机理与建模、视觉中的统计与学习方法、视觉照明与反射建模、图像／视频数据库及检索、图形学与可视化、立体视觉、智能视频监控、计算机视觉典型应用等）和人工智能（智能图像处理、模式识别、数据挖掘和知识发现，智能传感器网络，智能控制和智能管理、人工智能应用等）。     

基于知识模型的控制阀选型

根据用户需求变化带来的控制阀特点多样性和高参数化，以及相应的控制阀选型模式的改变，构建基于知识模型的控制阀智能选型系统，提高选型效率和质量，为用户提供高效优质的控制阀选型技术服务，推介适合生产系统工艺流程控制要求的产品。     

矿井提升设备的计算与选型

本文以某矿实例为基础详细论述了煤矿主斜井带式输送机以及副井提升设备的计算与选型方法,对今后该类矿井提升设备的设计选型工作具有一定的借鉴意义。     

BP神经元网络算法在高新技术产品评价中的应用

将人工神经元网络中的BP算法应用于高新技术产品评价，阐述了指标的选定方法，BP网络结构及网络训练过程，并给出了一个实例计算结果。     

基于改进算法的煤矿隐患关联性分析

文章简述了一种适合煤矿隐患数据的Apriori改进算法,然后根据煤矿作业场所安全隐患数据信息的特点进行数据预处理,包括数据的导入和提取,将算法嵌入到某煤矿的隐患排查系统,在此之后是基于Apriori改进算法的煤矿隐患数据关联规则挖掘的实现,得到煤矿隐患内部有价值的关联规则,为企业在隐患管理和预防方面提供改进建议,从而最终对防止事故的发生、降低事故损失有着重要的实际意义。     

基于模糊综合评判法的设备选型方法

根据设备选型工作中存在的片面性，应用模糊综合评判的知识建立了设备评价工作的一种模糊综合评判的数学模型。用此种模糊综合评判方法，使设备评价工作更加公正、合理、科学，从而实现设备选型的科学化。     

车载背光源AOI检测设备的研究开发

车载背光源产品AOI智能检测设备的开发背景,设备的工作原理,设备结构、选型特点、核心优势,以及该设备的研发对车载背光行业的意义和影响。     

龙门同步双交流伺服实验系统设计

为了研究龙门结构同步驱动算法，设计满足龙门结构高精度协调驱动性能等要求的双轴交流伺服实验系统。该系统采用双轴丝杆滑台机构设计方案，包括控制器模块、驱动器模块、伺服电机、编码器、丝杆滑台及人机界面等，并且进行元件的选型与参数计算；采用西门子控制器和电液伺服控制技术，实现模拟实际龙门结构运动控制。研究结果表明该实验系统具有结构简单、运行平稳、精度符合要求、传递效率高等特点，能够较好地解决龙门同步驱动的问题。     

关联规则挖掘算法在教学管理上的应用

介绍了关联规则挖掘的基本概念,分析了经典的Apriori算法,提出一种改进的关联规则挖掘算法,在系统中永久保留支持度为0的候选1项集和候选2项集,当系统需要运行时,先采用数据库的过滤技术,可以很快得到频繁2项集。采用新算法在教学数据库中搜索所有的关联规则,从而得到课程与课程之间的关联关系,对教学管理具有一定的辅助决策意义。     

成人大学生智能结构的培养初探

成人高等教育的关键是对其智能结构的构建与培养，对于智能结构构建的好坏、智能结构构建过程中所面临的问题以及如何培养，是成人学生在将来的工作中能否发挥所学、是否富于创新的关键。所以，大学生智能结构的培养是我们成人教育工作者的重中之重，应该在这方面多做一些研究与探讨。     

温室智能控制关键技术研究动向

温室环境智能控制系统将成为现代农业发展的重要手段和措施,因而建立基于作物生长模型、温室综合环境预测分析模型和栽培专家系统知识库,温室环境复杂系统的建模与专家决策支持系统研究,温室环境智能控制系统技术研究与系统开发等将成为今后主要研究内容。     

面向EDA主动知识辅助基础原型的研究

随着EDA技术的飞速发展,电子自动化行业对设计师设置了较高的知识门槛,对此开发了面向EDA技术的主动知识辅助系统的基础原型,实现其在领域机理层次上的主动知识辅助。系统具备主动判断电子设计工程师知识缺陷并提供相应辅助的智能机制,从而对不同知识结构的电子设计工程师提供有针对性的快速辅助,实现真正意义上的人机协作,达到其在高端设计中的低起点应用的目的。目前该系统运行良好,基础原型有望形成电子自动化行业的伴侣软件。     

电厂生产系统经济性能的实用性算法

介绍了以燃料成本确定电厂生产系统经济性能的实用性算法、对电厂经营性能计算方法的分析,实用性算法的建立、实用性算法的分析、实用算法的应用作了较详细的阐述.     

基于机器学习的妊娠期糖尿病智能预测系统设计与实现

为帮助有效识别患有妊娠期糖尿病的孕妇,提前干预治疗,降低其潜在风险,设计并开发了妊娠期糖尿病智能预测系统。首先,在对比10种机器学习模型的基础上对临床数据集进行数据归一化和特征筛选,减少模型计算复杂度和一些使模型不稳定的特征;其次,使用Stacking算法对10种不同的机器学习模型进行集成,分别搭建2个集成模型Stacking1和Stacking2,比较集成模型的性能;最后,基于PyQt5设计妊娠期糖尿病智能预测系统,预测孕妇患妊娠期糖尿病的风险,并给出建议。结果表明：使用10个机器学习模型以及2个集成模型对GDM进行预测,发现GBDT的预测结果高于其他机器学习模型,集成模型 Stacking2将多个异质学习器相结合表现出较高的准确性和可靠性,且评价指标Accuracy、Precision、Recall、AUC分别为0.900 9、0.901 2、0.900 7、0.900 7,均高于同类模型。智能预测系统能有效预测妊娠期糖尿病的风险,能够及早发现易患病人群,并提供妊娠期糖尿病的科普知识,从而加强对易患病人群的健康管理,降低妊娠期糖尿病发生的风险。     

Unsupervised KDD to creatively support managers' decision making with fuzzy association rules: A distribution channel application

To be competitive in contemporary turbulent environments, firms must be capable of processing huge amounts of information, and effectively convert it into actionable knowledge. This is particularly the case in the marketing context, where problems are also usually highly complex, unstructured and ill-defined. In recent years, the development of marketing management support systems has paralleled this evolution in informational problems faced by managers, leading to a growth in the study (and use) of artificial intelligence and soft computing methodologies. Here, we present and implement a novel intelligent system that incorporates fuzzy logic and genetic algorithms to operate in an unsupervised manner. This approach allows the discovery of interesting association rules, which can be linguistically interpreted, in large scale databases (KDD or Knowledge Discovery in Databases.) We then demonstrate its application to a distribution channel problem. It is shown how the proposed system is able to return a number of novel and potentially-interesting associations among variables. Thus, it is argued that our method has significant potential to improve the analysis of marketing and business databases in practice, especially in non-programmed decisional scenarios, as well as to assist scholarly researchers in their exploratory analysis.     

Modelling the incentive to participate in open source biopharmaceutical innovation

The open source model provides a valuable framework for collective knowledge production and dissemination. Open knowledge networks and other cooperative strategies (classified as open source discovery initiatives) are enabling biopharmaceutical companies to access disembodied knowledge‐based resources critical to downstream drug development. The objective of these cooperative strategic alliances is to preserve the downstream technological opportunities for multiple firms. When upstream discovery research cannot yield commercial products and when the costs associated with excessive upstream competition are too high, companies jointly benefit from cooperative knowledge production and open knowledge dissemination. An analysis of 39 open source initiatives (consortia) provides us with information on: the likely participants in such initiatives, the focus of knowledge production activities, the characteristics of the knowledge generated, and the management of joint knowledge assets. Based on this analysis, we use game models to understand the decision to participate in such strategic alliances better. Our game models provide a simple but elegant framework for understanding the impact of changing knowledge structures on the payoffs associated with cooperation and defection in knowledge production, and therefore on behaviour.     

Marketing Intelligent Systems for consumer behaviour modelling by a descriptive induction approach based on Genetic Fuzzy Systems

In its introduction this paper discusses why marketing professionals do not make satisfactory use of the marketing models posed by academics in their studies. The main body of this research is characterised by the proposal of a brand new and complete methodology for knowledge discovery in databases (KDD), to be applied in marketing causal modelling and with utilities to be used as a marketing management decision support tool. Such methodology is based on Genetic Fuzzy Systems, a specific hybridization of artificial intelligence methods, highly suited to the research problem we face. The use of KDD methodologies based on intelligent systems like this can be considered as an avant-garde evolution, exponent nowadays of the so-called knowledge-based Marketing Management Support Systems; we name them as Marketing Intelligent Systems. The most important questions to the KDD process-i.e. pre-processing; machine learning and post-processing-are discussed in depth and solved. After its theoretical presentation, we empirically experiment with it, using a consumer behaviour model of reference. In this part of the paper, we try to offer an overall perspective of how it works. The valuation of its performance and utility is very positive.     

论知识管理研究重心的转移

论证了进入知识经济时代后,经济全球化对知识管理研究的影响。指出知识管理的研究重心必须进行迁移,迁移的方向是由局部隐性知识向全球化显性知识转移,从微观知识向全球化宏观知识转移,从描述性知识向方法论知识转移,同时指出了新一代知识管理的智能化方向。     

基于MA2IDDPG算法的异构多无人机协同突防方法

为了形成智能化异构多无人机协同突防策略，提出了基于多智能体异步模仿深度确定性策略梯度算法的异构多无人机协同突防方法。首先，基于典型DDPG方法，采用异步并行框架进行改进，提高经验的收集效率。其次，分别构建基于专家经验知识的牵引性奖赏函数和基于任务结果的描述性奖赏函数。再次，通过分阶段训练后，使得深度神经网络产生的协同突防策略能够快速达到专家经验知识水平后，进一步提高对抗水平。最后，在仿真实验中，构建了异构多无人机协同突防环境，对改进方法和典型DDPG方法的对抗效果进行了对比。实验结果表明，MA2IDDPG方法能够有效产生多无人机协同突防策略，并且在训练阶段表现更为稳定且对抗效果更优。所设计的创新性MA2IDDPG方法框架可有效应用于无人机群控制领域，特别是对异构无人机群的智能控制方法研究具有重要参考意义。     

The communicative power of expert systems

'Expert Systems' or intelligent knowledge-based computer systems can be expected to have a considerable impact in the near future on the dissemination and use of technical expertise in practical situations. The potential benefits of such an approach to decision-making in applied science domains, for example, in anti-corrosive coating selection, are considerable. This paper argues, therefore, that a premium must be placed on such a system's performance as a communicator.
The structure and behaviour of a classical 'production system' are briefly described, and the communicative ability of such a system is analysed. This critical examination of a production system's question-answering capabilities highlights the inherent restrictions which the structure of this kind of system places on its explanatory and justificatory powers. An outline design for a less inhibitive structure is presented.
It is argued that the form in which the system provides 'answers' after the completion of a problem-solving session, may not yield sufficient appropriate information to the user, and a possible alternative view of a 'solution schema' is proposed.