自重构机器人的自组织变形

本文深入研究了自重构机器人实现自组织变形的基本方法．首先根据自重构机器人 系统结构的基本特征提出一种描述模型，可以对各类模块化自重构机器人的拓扑结构进行统 一描述．然后提出一种建立在全离散的局部智能基础上的自重构机器人的自组织变形策略， 通过建立适当的模块运动规则和规则进化使机器人由局部自主运动产生全局系统自组织的结 果．     

Exploring college English language learners’ self and social regulation of learning during wiki-supported collaborative reading activities

Students’ regulation has been conceptualized as an important impetus for effective and efficient collaborative learning. However, little empirical evidence has been reported about language learners’ regulatory behaviors in computer-supported collaborative learning (CSCL). The purpose of this study is to investigate the occurrence of self and social aspects of regulation during wiki-supported collaborative reading activities in the context of learning English as a foreign language (EFL). Sixty Chinese college students organized in twelve groups participated in this study over a sixteen-week semester. Using an integrated method of content analysis and sequential analysis, students’ chat logs were coded and analyzed to explore the characteristics of students’ self and social regulatory behaviors in terms of regulation type, regulation process, and regulation focus. Results indicate that all groups demonstrated active social regulation in the collaborative activities. Compared with low-performing groups, high-performing groups displayed distinctively different patterns of regulatory behaviors in “social regulation,” “evaluating,” “content monitoring,” and “social emotional regulation.” Moreover, the analysis further reveals a more continuous and smooth regulation in the high-performing groups, while low-performing groups tended to be lost in a single repeated regulatory behavior pattern such as “self-regulation” or “organizing”. This study not only fills a gap in the current collaborative English learning literature, but also contributes to our knowledge of social regulation in CSCL. Pedagogical implications and future research are also addressed.     

Building Minority Language Corpora by Learning to Generate Web Search Queries

The Web is a source of valuable information, but the process of collecting, organizing, and effectively utilizing the resources it contains is difficult. We describe CorpusBuilder, an approach for automatically generating Web search queries for collecting documents matching a minority concept. The concept used for this paper is that of text documents belonging to a minority natural language on the Web. Individual documents are automatically labeled as relevant or nonrelevant using a language filter, and the feedback is used to learn what query lengths and inclusion/exclusion term-selection methods are helpful for finding previously unseen documents in the target language. Our system learns to select good query terms using a variety of term scoring methods. Using odds ratio scores calculated over the documents acquired was one of the most consistently accurate query-generation methods. To reduce the number of estimated parameters, we parameterize the query length using a Gamma distribution and present empirical results with learning methods that vary the time horizon used when learning from the results of past queries. We find that our system performs well whether we initialize it with a whole document or with a handful of words elicited from a user. Experiments applying the same approach to multiple languages are also presented showing that our approach generalizes well across several languages regardless of the initial conditions.     

基于自我意识的Agent通信语言研究

Agent间的通信目的是不断完善其自我意识,Agent间的通信内容是Agent对其自我意识的解释,Agent间的通信过程是Agent在其自我意识上的推理。在研究经典Agent通信语言的基础上,结合知识类别、自我意识、语气等相关研究成果,以能描述语义的互表性、模糊性、动态性和自我意识性的动态本体描述语言作为通信内容的表示工具,设计了一个基于自我意识的Agent通信语言,给出了该语言的消息结构和语用词,并通过实例来解释Agent间的通信过程是Agent在其自我意识上的推理。     

Formatted syntaxes and modula-2

The formatted syntax notation has been developed for the specification of formatted programming languages. This paper describes how a formatted syntax may be constructed for the purpose of prettyprinting an existing free-format language. Those aspects of the system of particular relevance to free-format languages are emphasized and their use explained. Also, a number of deficiencies in the defining metasyntax and formatting symbol repertoire are discussed. Practical enhancements and further areas of research are suggested. The programming language Modula-2 is used for illustration, and a formatted syntax for it is given.     

一种基于多目标的自组织神经网络学习方法

自组织神经网络又称为无教师指导学习网络，可以自动地从环境中学习、获取知识、从而具有较强的自适应能力。目前，自组织神经网络在图象理解、模式识别、智能机器人控制等领域得到越来广泛的应用。但是，由于目前大部分组织神经网络都采用单准则无教师指导学习方法，从而导致了神经网络学习效率低等问题，这在一程度上影响了自组织神经网络更加广泛的有效应用。为此，本文提出了一种基于模糊熵准则和误差平方和准则的多目标（准则）自组织神经网络学习算法，该算法可以克服单准则无教师指导学习方法所存在的局限性，实验结果表明：该算法是有效的，并且较其它自组织神经网络学习方法，无论在学习效率上，还是在网络优化上，都具有很大的优越性。     

轨迹分布模式学习的层次自组织神经网络方法

提出一个层次自组织神经网络模型，并将其应用于基于事件识别的轨迹分布模式学习中。该文利用神经元的侧向连接将神经元连成若干条线，每条线对应一个“内部网”。对应于层次神经网络模型，建立了两个领域，即神经元领域和“内部网”领域，两个领域内的神经元都要不同程度地改变权值，从而完成运动轨迹分布模式的学习。还给出了利用轨迹分布模式检测出局部可能的异常现象、检测整个运动轨迹所表示的事件是否为异常事件和目标行为预测的方法。实验进一步说明了该方法的可行性和有效性。     

位移不变的视觉模式在线学习和识别

提出了一种二维模式识别的神经网络模型ART-Cognizer,该模型采用新认知机的 结构和自适应共振网络的自顶向下的注意和匹配机制,因此对模式在视野中的缩放和平移有 容忍能力,并对自组织学习过程有自稳定能力,它可以在线学习新的模式而不损伤其原有记 忆.     

自组织前向神经网络与非线性动态系统模化

将自组织学习过程引入到前向网络的训练中,提出了一种新的三层前向神经网络的训练方法,训练过程首先利用自组织分族算法确定隐含层结点的数目以及权值,然后通过求解线性最小二乘问题估计输出层权值,自组织过程产生的激活权值对输入数据具有一种特征变换的功能,利用该方法训练的网络可以称之为自组织前向网络（ＳＯＦＮ）。文中通过实际非线性动态系统建模的例子,说明了ＳＯＦＮ网络具有良好性能。     

A contribution to the organization of an expert system for process control of FMC

The distributed processes control model was investigated. A discussion of the automated acquisition of knowledge for process control is presented. The logical solution concept and basic details for implementing an interpreter are described. How it functions was considered, as well as the language for the control of expressions in base rules. A set of rules from the rule base are presented to show a simplified method of organizing a knowledge base by Petri net models of robots and machines.     

Self-creating and organizing neural networks

We have developed a self-creating and organizing unsupervised learning algorithm for artificial neural networks. In this study, we introduce SCONN and SCONN2 as two versions of self-creating and organizing neural network (SCONN) algorithms. SCONN creates an adaptive uniform vector quantizer (VQ), whereas SCONN2 creates an adaptive nonuniform VQ by neural-like architecture. SCONN's begin with only one output node, which has a sufficiently wide activation level, and the activation level decrease depending upon the time or the activation history. SCONN's decide automatically whether to adapt the weights of existing nodes or to create a new "son node." They are compared with two famous algorithms-the Kohonen's self organizing feature map (SOFM) (1988) as a neural VQ and the Linde-Buzo-Gray (LBG) algorithm (1980) as a traditional VQ. The results show that SCONN's have significant benefits over other algorithms.     

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self‐organizing map

Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self‐organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley & Sons, Inc.     

应用自组织神经网络客观评定织物折皱等级

本文采用Kohonen自组织神经网络客观评定织物折皱等级，首先介绍自组织神经网络的基本算法，再结合自组织神经网络结构实现神经元的竞争和训练，并将结果输出到相应的分类模式中，以此确定试样的折皱等级，最后采用26种真实织物验证该方法的可行性。     

基于支持向量机的非线性系统故障诊断

提出了联想度的概念,并由此设计出一种自组织模糊CMAC（SOFCMAC）及其学习算法,证明了SOFCMAC能以任意精度对非线性特性一致逼近。该网络具有学习速度快,逼近精度高等特点,用该SOFCMAC作为非线性系统观测器而生成残差,通过支持向量诊断器得到故障检测与诊断结果。对某型歼击机的结构故障进行诊断,仿真结果表明了该方法的有效性。     

一种基于理性原则的多机器人协调控制

自组织多机器人系统具有一定的柔性,且鲁棒性强,但系统建模复杂,优化协调控制 困难.以多机器人系统的自组织自约束决策模型为基础,提出了一种多机器人系统的理性协 调控制方法,并分析了这种方法与最优控制方法的关系.     

Language learning with interactive virtual agent scenarios and speech recognition: Lessons learned

The SPELL (Spoken Electronic Language Learning) system is a self‐access computer‐assisted language learning (CALL) package that integrates speaker‐independent continuous speech recognition technology with virtual worlds and embodied virtual agents to create an environment in which learners can converse in the target language within meaningful contextualized scenarios. In this paper we provide an overview of the functionality, architecture, and implementation of the SPELL system. We also describe four phases of usability evaluation conducted with the system and summarize the main results of these user assessments. Finally, we discuss the most significant lessons learned in the development and evaluation of the system. The paper focuses on the technological aspects of the system and its evaluation for usability and robustness, rather than its pedagogical methodology. Copyright © 2008 John Wiley & Sons, Ltd.     

产品的造型语言及其符号分析

造型因素作为传达各种信息的符号,构成了现代设计中的产品语言。本文从产品的造型语言角度对其符号进行分析,包括造型语言的符号构成,符号传达及其符号应用等内容。把握好造型语言的运用和符号的表现能实现产品与生活、产品与人做更加贴近、更富感情的对话。     

Tarskian Set Constraints

We investigate set constraints over set expressions with Tarskian functional and relational operations. Unlike the Herbrand constructor symbols used in recent set constraint formalisms, the meaning of a Tarskian function symbol is interpreted in an arbitrary first order structure. We show that satisfiability of Tarskian set constraints is decidable in nondeterministic doubly exponential time. We also give complexity results and open problems for various extensions and restrictions of the language.     

How organizing visions influence the adoption and use of reverse auctions

This research investigates strategic and tactical approaches to reverse auction use, and how they are influenced by organizing visions. Organizing visions are real and perceived forces that influence the adoption of information technology. We use an extensive literature review and a case study of a reverse auction provider, that has managed thousands of auctions for organizations, to investigate how organizing visions impact on decision making in relation to reverse auction adoption and use. The findings from the study show that e-auctions are used to reduce procurement costs and improve efficiency and are more likely to be used for commodity purchases. The narrower tactical role for e-auctions that is now evident in some organizations is shaped by the fear and disdain surrounding past use and in particular the perception of the damage to supplier relationships that their widespread adoption in procurement could create. The reverse auction vendor legitimates tactical adoption through the type of service provided. The paper makes an original contribution to theory in extending the concept of organizing visions. It concludes that although an organizing vision is often viewed as a force for adopting technology it can also be a limiting force that inhibits organizations from obtaining significant benefits from technological opportunities.     

主题地图在关系数据库中的应用研究

作为ISO确立的新标准,主题地图用来描述知识结构及其内在关联。它提供了语义级的数据导航和组织方式,是一个表达和交换结构化信息的元数据模型。文中在介绍了主题地图的相关概念后,设计了一种基于主题地图、扩展关系数据库的方法,并利用主题地图的描述语言XTM导出数据库,为多个关系数据库之间的数据交换提供了新的理念。