检索结果-内蒙古大学图书馆

1999 Congress on Evolutionary Computation, CEC 1999

作者： Pan, Zhengjun Sabisch, Theo Adams, Rod Bolouri, Hamid Science and Technology Research Centre Department of Computer Science University of Hertfordshire Hatfield Herts ALlO 9AB United Kingdom State Key Laboratory of Software Engineering Wuhan University Wuhan Hubei 430072 China

ISBN: (纸本)0780355369

The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. We present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems. © 1999 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Using partial order techniques to improve performance of data flow analysis based verification 99

Using partial order techniques to improve performance of dat...

引用

Proceedings of the 1999 ACM SIGPLAN-SIGSOFT workshop on Program analysis for software tools and engineering

作者： Gleb Naumovich Lori A. Clarke Jamieson M. Cobleigh Laboratory for Advanced Software Engineering Research Computer Science Department University of Massachusetts Amherst Massachusetts

ISBN: (纸本)9781581131376

Partial order optimization techniques for distributed systems improve the performance of finite state verification approaches by avoiding redundant exploration of some portions of the state space. Previously, such techniques have been applied in the context of model checking approaches. In this paper we propose a partial order optimization of the program model used by FLAVERS, a data flow based finite state verification approach for checking user-specified properties of distributed software. We demonstrate experimentally that this optimization often leads to significant reductions in the run time of the analysis algorithm of FLAVERS. On average, for those cases where this optimization could be applied, we observed a speedup of 21%. For one of the cases, the optimization resulted in an analysis speedup of 91%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contextual fuzzy cognitive maps for geographic information systems

Contextual fuzzy cognitive maps for geographic information s...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： R. Satur Zhi-Qiang Liu Computer Vision and Machine Intelligence Laboratory Department of Computer Science and Software Engineering University of Melbourne Parkville VIC Australia

Designing a system that is able to make use of quantitative and qualitative data for real world applications is a challenging problem. Traditional systems produce representational descriptions that are often not very useful to the human expert. To rectify this problem we propose a structure based on contextual fuzzy cognitive maps (CFCMs) for GIS systems. For a given goal, our system structure is hierarchical by context, multi-layered by variations in data over periods of time, and semi-qualitative in that the CFCMs build causal links and relationships between landmarks and concepts.

关键词： Fuzzy cognitive maps Geographic Information Systems Humans Computational Intelligence Society computer vision Machine intelligence computer science software engineering Application software Communication cables

来源：评论

学校读者我要写书评

暂无评论

Fuzzy cognitive map and its causal inferences

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Zhi-Qiang Liu Yuan Miao Department of Computer Science and Software Engineering Computer Vision and Machine Intelligence Laboratory University of Melbourne Parkville VIC Australia

ISBN: (纸本)0780354060

Fuzzy cognitive maps (FCM) is a powerful framework for representing structured human knowledge and causal inference. This paper presents a new and effective approach to analyzing causal inference mechanism of FCM. We focus on binary concept states proposed originally by Kosko (1986). Given initial conditions, FCM is able to reach only certain states in its state space. The problem of finding whether a state is reachable in the FCM is NP hard. In order to effectively carry out the design of fuzzy cognitive maps we propose to divide an FCM into basic FCM modules. This paper also presents a recursive formula for the calculation of FCM inference patterns in terms of key vertices.

关键词： Fuzzy cognitive maps State-space methods Fuzzy systems computer vision Machine intelligence computer science software engineering Humans Inference mechanisms Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

UML-based fusion analysis 99

引用

Proceedings of the 2nd international conference on The unified modeling language: beyond the standard

作者： Shane Sendall Alfred Strohmeier Swiss Federal Institute of Technology Department of Computer Science Software Engineering Laboratory Lausanne-EPFL Switzerland

ISBN: (纸本)9783540667124

In recent times, there has been an increased requirement for software to be distributed. The well-known Fusion development method, however, can only be used to develop sequential reactive systems, and certain restricted kinds of concurrent systems. In contrast, the Unified Modeling Language (UML) provides a rich set of notations that can be used to model systems that are distributed. In addition, UML provides the ability to introduce rigor into diagrams through its constraint language OCL. In this paper, we present a UML-based Fusion analysis phase by way of a simple bank case study, and we discuss some enhancements that were made in addition to a mapping of notations; our proposal is the first step towards providing a Fusion-based analysis phase which supports high-level modeling of distributed systems.

关键词： analysis UML object-oriented software development fusion

来源：评论

学校读者我要写书评

暂无评论

JUSTICE: a judicial search tool using intelligent concept extraction 99

JUSTICE: a judicial search tool using intelligent concept ex...

引用

Proceedings of the 7th international conference on Artificial intelligence and law

作者： James Osborn Leon Sterling Intelligent Agent Laboratory Department of Computer Science and Software Engineering University of Melbourne Parkville Victoria 3052 Australia

ISBN: (纸本)9781581131659

A legal knowledge based system called JUSTICE is presented which provides conceptual information retrieval for legal cases. JUSTICE can identify heterogeneous representations of concepts across all major Australian jurisdictions. The knowledge representation scheme used for legal and common sense concepts is inspired by human processes for the identification of concepts and the expected order and location of concepts. These are supported by flexible search functions and various string utilities. JUSTICE is a client-based legal software agent which works with both plaintext and HTML representations of legal cases over file systems, and the World Wide Web. In creating JUSTICE an ontology for legal cases was developed, and is implicit within JUSTICE. Further, the identification of concepts within data is shown to be a process enabling conceptual information retrieval and search, conceptualised summarisation, automated statistical analysis, and the conversion of informal documents into formalised semi-structured representations. JUSTICE was tested on the precision, recall and usefulness of its concept identifications; achieving good results. The results show the promise of the approach and establish JUSTICE as an intelligent legal research aid offering improved multifaceted access to the concepts within legal cases.

关键词： intelligent law information systems intelligent research aid legal ontology conceptual information retrieval legal WWW agent legal knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Classification tree models of software quality over multiple releases

Classification tree models of software quality over multiple...

引用

International Symposium on software Reliability engineering (ISSRE)

作者： T.M. Khoshgoftaar E.B. Allen W.D. Jones J.I. Hudepohl Department of Computer Science and Engineering Empirical Software Engineering Laboratory Florida Atlantic University Boca Raton FL USA Business Unit of Nortel Networks EMERALD Research Triangle Park NC USA Florida Atlantic University Boca Raton FL USA

software quality models are tools for focusing software enhancement efforts. Such efforts are essential for mission-critical embedded software, such as telecommunications systems, because customer-discovered faults have very serious consequences and are very expensive to repair. We present an empirical study that evaluated software quality models over several releases to address the question, "How long will a model yield useful predictions?" We also introduce the Classification And Regression Trees (CART) algorithm to software reliability engineering practitioners. We present our method for exploiting CART features to achieve a preferred balance between the two types of misclassification rates. This is desirable because misclassifications of fault-prone modules often have much more severe consequences than misclassifications of those that are not fault-prone. We developed two classification-tree models based on four consecutive releases of a very large legacy telecommunications system. Forty-two software product, process, and execution metrics were candidate predictors. The first software quality model used measurements of the first release as the training data set and measurements of the subsequent three releases as evaluation data sets. The second model used measurements of the second release as the training data set and measurements of the subsequent two releases as evaluation data sets. Both models had accuracy that would be useful to developers.

关键词： Classification tree analysis software quality Predictive models software measurement Training data software tools Mission critical systems Embedded software Regression tree analysis software algorithms

来源：评论

学校读者我要写书评

暂无评论

Using AulaNet for Web-based course development

Using AulaNet for Web-based course development

引用

String Processing and Information Retrieval Symposium (SPIRE)

作者： R. Choren C. Laufer M. Blois V. Torres F. Ferraz G. Robichez L. Daflon C.J.M.P. de Lucena H. Fuks Computer Science Department Software Engineering Laboratory Catholic University of Rio de Janeiro Rio de Janeiro Brazil

A variety of technologies are being used to replace or supplement the face-to-face learning process, including the World Wide Web. We present AulaNet, an environment for creating, updating and attending Web-based courses. We illustrate some dynamics of three experiments of course development and delivery with AulaNet, pointing out their features. We discuss how easy and how difficult it is to orchestrate technology for educational purposes.

关键词： Educational technology Internet computer science software engineering Navigation Laboratories Videoconference Streaming media Explosions Education

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Algorithm to Solve the Task Partition Problem in MDOCEM

引用

Wuhan University Journal of Natural sciences 1999年第2期4卷 27-30页

作者： He Yan-xiang Chen Xin-mong Donald H. Cooley Zhang Jian-ping College of Computer Science and Technology Wuhan University Wuhan China State Key Laboratory of Software Engineering Wuhan University Wuhan China Department of Computer Science Utah State University Logan USA

This paper examines task partition problem in a Multiagent based Distributed Open Computing Environment Model(MDOCEM). We first present a formal method to describe the task partition problem, then give a heuristic al... 详细信息

关键词： distributed open computing environment task partition planning management operation set

来源：评论

学校读者我要写书评

暂无评论

Formal verification of RACE protocol using SSM

Formal verification of RACE protocol using SSM

引用

IEEE Region 10 International Conference TENCON

作者： Hahnseng Kim Jin-Young Choi Ando Ki Woo-Jong Han Department of Computer Science & Engineering Korea University Seoul South Korea Computer System Dept ETRI-CSTL(Computer and Software Technology Laboratory) Taejon South Korea

Cache coherence protocols are important for operating a shared-memory multiprocessor system with efficiency and correctness. Cache coherence protocols have become increasingly complex because physical memory is logically distributed, so that it is difficult for programmers to understand the view of logical shared-memory systems. Since random testing and simulations are not enough to validate the correctness of these protocols, it is necessary to develop efficient and reliable verification methods. Through the use of the Symbolic State Model (SSM) of Fong Pong (1995), we verified a directory-based protocol called the RACE (Remote-Access Cache coherence Enforcement) protocol. The protocol is verified for any system size, without state-space explosion.

关键词： Formal verification Access protocols State-space methods Explosions Electronic mail Multiprocessing systems Testing Error correction Network interfaces computer science

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：