Agent机会发现的一种刻画:溯因推理及其扩展

机会发现(Chance Discovery)是近年来提出的一个新的研究课题。文章考察了溯因推理作为主体“机会”规范和机会发现推理机制的优劣，提出了将Lm4c嵌入到溯因推理中。对Chance Discovery从两个角度进行了扩展。并且实现了在相关性解释下的“机会”规范和机会发现推理。     

“小灵通”命运多桀

《小灵通漫游未来》，这部科幻作品可能大家都快忘记了，尤其是现在的人们，已没有什么机会见识和阅读。但从这部科幻作品取名的“手机”却令人难以忘怀——“水灵通”！正是这个“小灵通”，在神州大地的中小城市掀起一波又一波热潮，也经历了风风雨雨，潮起潮落，到现在，“小灵通”还是飘忽不定，如同走钢丝一样，战战兢兢地走在中国电信市场上。     

移动机会网络路由问题研究进展

移动机会网络基于节点接触形成的通信机会逐跳转发数据,是满足物联网透彻感知与泛在互联的一种重要技术手段.机会路由作为实现间歇式连通环境下节点通信的基本方法,具有十分重要的研究意义,引起了研究人员的广泛关注.首先介绍了移动机会网络的概念、体系结构、典型应用以及所面临的一些挑战;然后详细阐述了机会路由算法的评价指标、设计需求与转发机制,并介绍了研究进展;最后,对机会路由未来的研究趋势进行了分析与展望.     

基于身份加密的机会网络安全路由架构

从分析当前机会网络安全路由架构建设的必然性入手,分析了基于身份加密的机会网络安全路由架构的基本概况和特点,具体实施过程,并在文章的最后对该架构的基本内容进行了详细的分析和阐述。     

认知社会物联网中能量感知的编码机会路由协议

社会物联网是一种集合人与物关系的新型物联网形式。针对物联网频谱资源匮乏的问题,提出基于认知无线电技术的社会物联网——认知社会物联网(CR-SIoT)。认知社会物联网中频谱资源的动态性、设备的移动性和社会性及业务流的多样性,给路由机制的设计带来更大的挑战。机会路由充分利用无线信道的广播特性机会地传输数据,进而提高网络性能。因此,提出一种面向多业务的能量感知的编码机会路由。路由度量标准考虑了认知社会物联网中的社会属性及能量问题,提出基于拍卖模型的双层候选节点集选择算法和基于博弈论的信道分配算法。同时,为了加快数据传输进程,在所选候选节点传输数据时,采用网络编码技术进行"批量"传输。通过仿真实验验证了该机会路由的有效性。     

机会网络节点协作缓存策略设计与实现

针对如何有效利用机会网络中节点间的协作关系以及节点有限的缓存资源,避免拥塞和提升数据传输性能的问题,提出一种机会网络协作缓存优化策略——HMP-Cache。该策略根据节点不同运动状态的特点,利用目标地址匹配标准选择协作缓存节点,采用同步Cache数据表达到局部域内缓存信息共享的目的。仿真实验结果表明,该策略能够有效控制数据访问的网络开销,降低网络热点数据访问延迟。     

唉，我没有分身术！

“思科的用户大会有那么多精彩纷 呈的讲座，我每个都想听，可是我又不会分身术，怎么办呢？”“那你只能忍痛割爱了，有所取舍地选听一些讲座了。”“这也正印证了鱼和熊掌不能兼得的理论。”一个偶然的机会，获悉了这样一段对话的内容，不禁好奇地想看一下思科将要在上海举行     

基于机会网络的社会性活动组织研究

具有短距离通信功能的设备(特别是智能手机)的广泛普及为机会网络的应用带来了可能。提出了社会活动组织(SAF,Social Activity Formation)的应用。为实现机会网络下的社会活动组织信息的传播,需要代理用户的支持。现有代理算法中一般假设代理愿意帮助信息发起者进行传播,而没有考虑人的主观因素。从个体意愿度角度出发,认为用户不一定愿意接受代理任务,从而会带来“丢包”问题。鉴于此,提出了基于“社会关系”和“活跃度”的代理选择算法STBS(Social Tie based Broker Selection Algorithm)。采用MIT提供的智能手机数据集RealityMining做了实验,结果表明,STBS具有较好的性能,能较好地提供社会活动组织服务。     

模糊铁合金配料机会约束模型

在铁合金配料问题的大量传统研究工作中,多数研究工作均与确定性系统相关。在不确定系统中考虑一类新的带有可信性约束的模糊铁合金配料机会约束模型。由于提出的模糊铁合金配料问题常常包含带有无限支撑的模糊变量参数,因此它是一个很少被直接求解的无穷维优化问题。为了求解这个模糊优化问题,通过逼近方法将模糊铁合金配料机会约束问题转化为一个有限维优化问题。设计一个含有逼近方法、神经网络和遗传算法的混合智能算法求解提出的带有可信性约束的铁合金配料机会约束问题。给出一个数值例子来表明所设计模型和算法的实用性。     

网上旅游预订市场数据分析

互联网时代．网络给传统旅游业带来了新机会。当“旅游＋互联网”的模式出现，无论是市场机会还是企业的发展机会都会比传统旅游行业要大。[第一段]     

一种基于相关性和STRIPS系统的Chance Discovery模型

机会发现(CD)是近年提出的一个新的研究课题.扩展了CD相关性的概念,使之具有更丰富的内涵和更大的应用范围,并将CD相关性推理嵌入到STRIPS规划系统之中,从而构建一种更接近应用需要的CD过程模型.     

Chance Discovers研究综述

Chance Discovery是国际上新兴的一个研究领域。本文着重从人工智能的角度,分析Chance Discovery的背景和研究现状,并具体介绍几项主要的研究成果,包括Chance的特性和理论抽象、Chance Discovery的技术手段和Chance Discovery的若干应用。     

Qualitative Chance Discovery - Extracting competitive advantages

There are two directions in data mining research, qualitative analysis and quantitative analysis. Chance Discovery is a useful qualitative analysis method to visualize the data structure and to discover the potential future scenario. But in reality, due to tremendous amount of information, data structure may be too complex for the user to comprehend. In this paper, using Chance Discovery as a basic driving force, we proposed an innovative interactive human-computing process model to extract the data structure of a specific topic that the user is most interested in. Our model combined the strength of both qualitative analysis and quantitative analysis where Grounded theory and text mining technology were applied to sift out meaningful but small data. Experiment results showed that the visualized results generated by our model were more accurate than those obtained by Chance Discovery method. Furthermore, users can evaluate the relevant data structure generated by our model to decide on potential chances.     

Decision process modeling across internet and real world by double helical model of chance discovery

A case is presented for the double helical processing of chance discovery — human and an automated data mining system co-work, each progressing spirally toward the creative reconstruction of ideas. Especially, the discovery of what we call chances, significant novel events, is realized in this process. The example shown here is an application to questionnaire analysis for understanding new behaviors of Internet users. Internet users are born and bred with face-to-face human relations in the real world, but their interactions with WWW are distilling new value-criteria, keeping personal real-world senses of rationality, empathy, ethics, etc. In our method for aiding the discovery based on the double-helix model, the in-depth interaction of the Internet, the fundamental (i.e., common both in the Internet and in the real world) characters and the behaviors of people are discussed with revealing unnoticed value-criteria. Yukio Ohsawa, Ph.D.: BS, U. Tokyo, 1990, MS, 1992, DS, 1995. Research associate Osaka U. (1995). Associate prof. Univ. of Tsukuba (1999-) and also researcher of Japan Science and Technology Corp (2000-). He has been working for the program com. of the Workshop on Multiagent and Cooperative Computation, Annual Conf. Japanese Soc. Artificial Intelligence, International Conf. MultiAgent Systems, Discovery Science, Pacific Asia Knowledge Discovery and Data Mining, International Conference on Web Intelligence, etc. He chaired the First International Workshop of Japanese Soc. on Artificial Intelligence, Chance Discovery International Workshop Series and the Fall Symposium on Chance Discovery from AAAI. Guest editor of Special Issues on Chance Discovery for the Journal of Contingencies and Crisis Management, Journal of Japan Society for Fuzzy Theory and intelligent informatics, regular member of editorial board for Japanese Society of Artificial Intelligence. Currently he is authoring book “Chance Discovery” from Springer Verlag, “Knowledge Managament” from Ohmsha etc. Yumiko Nara, Ph.D.: She graduated from Nara Women’s University in 1987 and obtained her Master and Ph.D. degrees from Nara Women’s University respectively in 1993 and 1996. From 1987 through 1990 she worked for Sumitomo Bank. She is at Osaka Kyoiku University as lecturer (1997–2001) and as associate professor (2002-). She serves as a member of The Japan Sociological Society, The Japan Association for Social and Economic Systems Studies, The Japan Society of Home Economics, and The Japan Risk Management Society. She is an editorial committee member of the journal of Social and Economic Systems Studies (2001-), and a council member of The Japan Risk Management Society (1997-). In 1997, she received research awards from The Japan Society of Home Economics and The Japan Risk Management Society for studies on risk management.     

Chance discoveries for making decisions in complex real world

Chance discovery is to become aware of a chance and to explain its significance, especially if the chance is rare and its significance is unnoticed. This direction matches with various real requirements in human life. This paper presents the significance, viewpoints, theories, methods, and future work of chance discovery. Three keys for the progress are extracted from fundamental discussions on how to realize chance discovery: (1) communication, (2) imagination, and (3) data mining. As an approach to chance discovery, visualized data mining methods are formalized as tools aiding chance discoveries on the basis of these keys. Yukio Ohsawa, Ph.D.: He received Bechelor of Engineering (1990) from Faculty of Engineering, Master of Engineering (1992) and Ph.D. (1995) from Graduate School of Engineering, respectively of The University of Tokyo. In the doctoral course he began artificial intelligence research, especially of abductive inference. He was a research associate (1995–1999) in Osaka University on studies of text mining and related issues, and moved to the current position, associate professor in the University of Tsukuba in 1999. From 2001, he is also a researcher of TRESTO (changed to PRESTO) in Japan Science and Technology Corporation. He received best paper awards in two Annual Conferences of Japasese Society of AI (1994 and 1998), and a Journal Paper Award from JSAI in 1998. His social activities are committees of conferences e.g., International Conference of Multi-Agent Systems (ICMAS) since 1998 and Discovery Science (DS) since 2001, program chair of MultiAgent and Cooporative Computations (MACC, in Japan) in 1999, and committes of meetings including ones on Chance Discovery.     

PAI: Automatic indexing for extracting asserted keywords from a document

This paper proposes an automatic indexing method named PAI (Priming Activation Indexing) that extracts keywords expressing the author’s main point from a document based on the priming effect. The basic idea is that since the author writes a document emphasizing his/her main point, impressive terms born in the mind of the reader could represent the asserted keywords. Our approach employs a spreading activation model without using corpus, thesaurus, syntactic analysis, dependency relations between terms or any other knowledge except for stop-word list. Experimental evaluations are reported by applying PAI to journal/conference papers. Naohiro Matsumura: He received his B.S. and M.S. in Engineering Science from Osaka University in 1998 and 2000. Currently, he is a Ph.D. candidate in Engineering at the University of Tokyo and a research staff of PRESTO of Japan Science and Technology Corporation (2000–). His research interests include chance discovery, computer-mediated communication, and user-oriented data mining/text mining. Yukio Ohsawa, Ph.D.: BS, U. Tokyo, 1990, MS, 1992, DS, 1995. Research associate Osaka U. (1995). Associate prof. Univ. of Tsukuba (1999–) and also researcher of Japan Science and Technology Corp (2000–). He has been working for the program com. of the Workshop on Multiagent and Cooperative Computation, Annual Conf. Japanese Soc. Artificial Intelligence, International Conf. MultiAgent Systems, Discovery Science, Pacific Asia Knowledge Discovery and Data Mining, International Conference on Web Intelligence, etc. He chaired the First International Workshop of Japanese Soc. on Artificial Intelligence, Chance Discovery International Workshop Series and the Fall Symposium on Chance Discovery from AAAI. Guest editor of Special Issues on Chance Discovery for the Journal of Contingencies and Crisis Management, Journal of Japan Society for Fuzzy Theory and intelligent informatics, regular member of editorial board for Japanese Society of Artificial Intelligence. Currently he is authoring book “Chance Discovery” from Springer Verlag, “Knowledge Managament” from Ohmsha etc. Mitsuru Ishizuka, Ph.D.: He is a professor at the Dept. of Infomation and Communication Eng., School of Information Science and Thechnology, the Univ. of Tokyo. Prior to this position, he worked at NTT Yokosuka Lab. and the Institute of Industrial Science, the Univ. of Tokyo. He earned his B.S., M.S. and Ph.D. in electronic engineering from the Univ. of Tokyo. His research interests include artificial intelligence, WWW intelligence, and multimodal lifelike agents. He is a member of IEEE, AAAI, IEICE Japan, IPS Japan, and Japanese Society for AI.     

Metacognitive and computational aspects of chance discovery

Chance discovery is concerned with events or situations that affect human decision making; such events or situations are viewed as opportunities or risks. Perspectives are mental representations that describe partial knowledge of a task domain (cognitive perspective) as well as knowledge about other participants (social perspectives). Based on verbal protocols and a computational model of these protocols, it is argued that perspective taking is a suitable strategy to achieve chance discovery. Therefore the cognitive mechanisms underlying this strategy have been investigated and the results implicate metacognition as necessary requirement to achieve chance discovery. Ruediger Oehlmann, Ph.D.: He is a senior lecturer in the Cognitive Science Laboratory, School of Computing and Information Systems, Kingston University, London. He received his degrees in Mathematics, Computer Science and Psychology. His doctoral thesis describes a model of discovery learning, which he has extensively tested using psychological experiments as well as computer programs. His current research interests include perspective taking, creativity, chance discovery and collaborative work in design domains. He is a member of the British Computer Society and the Cognitive Science Society.     

机会发现在多智能体系统中的形式化描述方法

针对多智能体系统(MAS)中执行决策的非确定性问题,研究结合时态/模态逻辑及机会发现理论,引入基于Kripke结构的复合逻辑 ,用于Agent的知识系统(全局知识、局部知识)及机会发现的形式化描述,为实现动态并发环境中MAS的系统协作行为建模及自动决策推理提供依据。给出 的结构及语义,证明了 的可判定性,且计算可在多项式级时间复杂度内实现。     

一种基于元数据的分布式数据源定位算法

随着Internet和数字图书馆这两种基础信息资源的大量涌现,用户在检索信息之前,如何选择合适的目标站点来提交查询,从而降低查询代价、提高查询效率,已经成为一个重要任务。这个问题更加一般的说法是“数据源定位”或“数据库发现”。元数据是关于数据的数据,数字图书馆中,每个数据文档由其元数据描述,元数据是数字图书馆管理、检索数据以及在各个层面上实现互操作的重要手段。文章提出了一种基于元数据的数据源发现算法,并在召回率、检索精度等方面对这种算法作了评价。