炼油生产调度专家系统的应用研究

基于知识的优化设计应用于炼油化工厂,采用专家系统技术将生产中成功的经验和领域专家的知识组织起来,协调并参与数学规划建模过程,优化编排调度作业计划,并进行优化控制和管理.文章结合大型炼油厂的生产实际,探索智能化的管控一体化的新模式.     

基于彩色图像的指示标志检测

智能交通系统是近年来国内外广泛关注的研究课题,在基于计算机视觉系统的交通标志识别中,关键步骤之一是如何快速有效地检测并提取交通标志。该文提出了基于色彩的指示标志检测与提取的快速有效方法。它包括：对实景图像进行色调不变的彩色增强,彩色聚类,形态滤波,模板匹配,特征点判别等步骤。最后,由搜索到的特征点从增强后的彩色图像中抽取指示标志。实验显示该方法能快速有效地从实景图像中检测指示标志。     

基于主控流动的多级Multi-Agent系统

从分析人的思维活动着手,提出了模拟人类智能活动过程构筑Ｍｕｌｔｉ－Ａｇｅｎｔ系统的方法,并由该方法构造了基于主控流动的多级Ｍｕｌｔｉ－Ａｇｅｎｔ系统。其主要特点是把小 Ｍｕｌｔｉ－Ａｇｅｎｔ系统视为一个特殊的Ａｇｅｎｔ,并由这种特殊的Ａｇｅｎｔ组成更高一级的Ａｇｅｎｔ系统…从而形成多级Ｍｕｌｔｉ－Ａｇｅｎｔ系统,而且在每一级Ａｇｅｎｔ系统中均采用了主控流动策略,使得整个系统能够把巨量的Ａｇｅｎｔ有效地结合起来。系统效率高,能主动改变和适应环境,为设计具体的大规模Ｍｕｌｔｉ－Ａｇｅｎｔ系统提供了一种可行的解决方案。     

蒙古文整词计算机生成理论研究

采用面向对象方法,模拟传统蒙古文整词各种形式构成机理,提出了几种蒙古语整词计算机生成数据模型。文章主要依据整词计算机生成三种模型,探讨了传统蒙古文整词计算机最优化生成理论所涉及的精确度、时间复杂度、空间复杂度三项基本要素以及最优化生成必须考虑的整词复杂特征载荷与一体化合一计算知识表示方法和计算结构,证明了“B - J - T= W”数据模型是传统蒙古文整词计算与生成最优化对象模型。     

基于工程特征类的预算工程量自适应提取方法研究

提出一种基于施工图的建筑CAD与预算编制集成方法,通过对施工图逻辑结构和反映预算工程量的各类图形信息特点进行分析,提出了工程特征类信息的概念,采用模板和模式识别技术实现了多层构造类预算工程量的自动提取和定额自动套取,并在基于通用设计平台的概预算一体化系统中得到应用。     

基于模式化知识和人工神经网络的智能设计系统框架研究

阐述了将神经网络和模式识别引入智能设计系统的模型－集成转换模型,在该模型中,对智能系统与设计的实现系统的结合进行了探讨,提出了数值编译器与反编译器、图形／编码转换器等将神经网络引入设计系统来的工具和方法。     

库存智能管理系统的研究与设计

以商业企业库存管理为背景,研究了库存智能管理系统的基本结构,提出了数据库管理系统,模型库管理系统及知识库系统的设计方案。     

Structural Synthesis of Modular Weakly Connected Neural Networks. II. Nuclear Neural Networks

The simplest modular neural network is investigated, in which each module is a single-layer perceptron (a neural kernel). Numerical indices of quality by the criteria of operating speed and plasticity are proposed to characterize structural properties of nuclear neural networks. Based on the indices introduced, optimum procedures of structural synthesis are constructed.     

AutoTutor: Incorporating Back-Channel Feedback and Other Human-Like Conversational Behaviors into an Intelligent Tutoring System

This paper describes our recent attempts to incorporate human-like conversational behaviors into the dialog moves delivered by an animated pedagogical agent that simulates human tutors. We first present a brief overview of the modules comprising AutoTutor, an intelligent tutoring system. The second section describes a set of conversational behaviors that are being incorporated into AutoTutor. The behaviors of interest involve variations in intonation, head movements, arm and hand movements, facial expressions, eye blinking, gaze direction, and back-channel feedback. The final section presents a recent empirical study concerned with back-channel feedback events during human-to-human tutoring sessions. The back-channel feedback events emitted by tutors are mostly positive (63%), mostly verbal (77%), and immediately follow speech-act boundaries or noun-phrase boundaries (83%). Tutors also deliver back-channelevents at a very high rate when students are emitting dialog, about 13 events per minute. Conversely, 88% of students' back-channel feedback events are head nods, and they occur at unbounded locations (63%).     

Designing Agent-Based Electronic Employment Markets

Two modes of matching people with jobs prevail at present: 1) hierarchical planning and 2) distributed markets. Each has strengths and limitations, but few systems have been designed to take advantage of strengths corresponding to both. With evolving information technology, however, the job-matching process could be accomplished far more equitably and efficiently using web-based markets within the firm, and intelligent agents offer excellent potential to help both potential employees and employers find one another in a distributed, electronic marketplace. But realizing this potential goes well beyond simply changing the rules of internal job matching or making agent technology available to job searchers. Rather, the corresponding markets and technologies must be designed, together, to mutually accomplish the desired results (e.g., efficient and effective matching) and conform to necessary properties (e.g., market clearing). Through the research described in this paper, we draw from Game Theory results to assess the feasibility of using two-sided matching algorithms to address this market-design problem. We also draw from current agent research to address the information technology dimension of the problem by implementing a proof-of-concept multi-agent system to enact, automate and support the corresponding market solution. This paper integrates the key economic and technological elements required to design robust electronic employment markets. And the corresponding research provides new knowledge and insight into co-development of the requisite economic markets and agent technologies.