By Topic

Cognitive Informatics, 2006. ICCI 2006. 5th IEEE International Conference on

Date 17-19 July 2006

Go

Filter Results

Displaying Results 1 - 25 of 59
  • [Front matter]

    Publication Year: 2006 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (1211 KB)  
    Freely Available from IEEE
  • [Frontmatter and table of contents]

    Publication Year: 2006 , Page(s): i - xv
    Save to Project icon | Request Permissions | PDF file iconPDF (1055 KB)  
    Freely Available from IEEE
  • Using Accelerator Feedback to Improve Performance of Integral-Controller Particle Swarm Optimization

    Publication Year: 2006 , Page(s): 665 - 668
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1363 KB) |  | HTML iconHTML  

    Integral-controller particle swarm optimization (ICPSO), influenced by inertia weight w and coefficient phi is a new swarm technology by adding accelerator information. Based on stability analysis, the convergence conditions imply the negative selection principles of inertia weight w, and the relationship between w and phi. To improve the computational efficiency, an adaptive strategy for tuning the parameters of ICPSO is described using a new statistical variable reflecting computational efficiency index-average accelerator information. The optimization computing of some examples is made to show that the ICPSO has better global search capacity and rapid convergence speed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent Robot Motion using Fuzzy logic-Based CTP and Artificial Neural Networks

    Publication Year: 2006 , Page(s): 669 - 674
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2012 KB) |  | HTML iconHTML  

    Human has some perception based behavior seen in his body movements. Movements of hands, legs, head, etc. show the inner emotion of the person in specific situations subconsciously. This paper introduces a Generalized Constraint Language (GCL) for humanoid robots to categorize data needed for trajectory tracking for each joint of the robot which lead to emotion mimicry. An artificial neural network generates velocity and acceleration for each joint of humanoid using GCL values. A concept that plays a key role in emotion mimicry with CTP is GCL View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Mutation Operator Based on the T Probability Distribution in Evolutionary Programming

    Publication Year: 2006 , Page(s): 675 - 679
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1093 KB) |  | HTML iconHTML  

    A new mutation operator based on the T probability distribution is studied. The T probability distribution is stable and can generate an offspring that is farther away from its parent than the commonly employed Gaussian mutation. Moreover, it has a better fine-tuning ability than the Cauchy mutation. In this paper, evolutionary programming (EP) with mutations based on the T probability distribution is studied. The new algorithm is tested on 23 benchmark functions and compared with the conventional EP and the fast EP. The experimental results demonstrate that the performance of the proposed algorithm outperforms the conventional EP and the fast EP View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Communication Adapter Design of Multi-Agent in Webgis

    Publication Year: 2006 , Page(s): 680 - 684
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3006 KB) |  | HTML iconHTML  

    On the characteristics of multi-source, heterogenous structure, mass data of WebGIS as well as the complexity of the system, the paper proposes the design model based on Web and multi-agent. Moreover, through analyzing the characteristics of each agent of the design model, the paper makes a further research on the communication problem of the agents. It also proposes the communication model and gives analysis and design to communication adapter View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Inverse Problem of Support Vector Machines Solved by a New Intelligence Algorithm

    Publication Year: 2006 , Page(s): 685 - 689
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2372 KB) |  | HTML iconHTML  

    An inverse problem of support vector machines (SVMs) was investigated. The inverse problem is how to split a given dataset into two clusters such that the margin between the two clusters attains the maximum. Here the margin is defined according to the separating hyper plane generated by support vectors. It is difficult to give an exact solution to this problem. An immunogenetic particle swarm incorporated intelligence algorithm was proposed to solve this problem. This study on the inverse problem of SVMs is motivated by designing a heuristic algorithm for generating decision trees with high generalization capability. The application in the recognition of the bank risk shows it is effective View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Commitment and Obligation Based on Utility in Agent Organization

    Publication Year: 2006 , Page(s): 690 - 695
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (470 KB) |  | HTML iconHTML  

    It is important to design an agent with logical and decisive rationality in agent organization. Study about organization focuses on the definition of agent organization model and the analysis of organization formation and evolution, an attractive and challenging issue is how to combine logical and decisive rationality into a uniform framework. This paper aims at arguing the combination with logic and decision in agent organization. To pursue this aim, we extend the notions of commitment and obligation with utility in agent organization and utility reflects agent decision. In order to systematize the notions, formal tools are introduced to describe them as well as the semantics of utility for commitment and obligation are defined. We specify the properties and consequences of the extension for agent organization View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matrix Computation For Concept Lattices

    Publication Year: 2006 , Page(s): 696 - 700
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (353 KB) |  | HTML iconHTML  

    Rough set theory and formal concept analysis (FCA) can be viewed as two different approaches of data analysis on data description and summarization. They focus on different characteristics of data in a context: the indiscernibility relation and the binary relation. The indiscernibility of objects with respect to a set of properties is an important notion in rough set theory. In general, this relation is an equivalence relation. A matrix can be seen as an internal representation of equivalence relations. The binary relation in FCA can establish contact with matrix through rough set theory. Representing knowledge in a form of matrix has many advantages. For examples, to represent knowledge in a form of a discernibility matrix enable simple computation of the core, reducts, etc. In this paper, this approach is first applied to FCA. Concept lattices are expressed in terms of matrices that can be computed intuitively and efficiently View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extension Rule in First Order Logic

    Publication Year: 2006 , Page(s): 701 - 706
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1471 KB) |  | HTML iconHTML  

    The extension rule (ER) is a new method for theorem proving, which is potentially a complementary method to resolution-based methods. But the first-order ER method is incomplete. We improve the first-order ER approach by (a) revise the definition of the potential blockage, give a complete first-order ER algorithm, (b) increasing the case M-satisfiability by giving a bound M, so as to make the ER method more useful for theorem proving and logic programming, and (c) accelerating it through invoking the more efficient proposition ER method. We also prove the soundness and completeness of the improved first-order ER algorithm and report some preliminary computational results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convergence Analysis of Mind Evolutionary Algorithm Based on Functional Analysis

    Publication Year: 2006 , Page(s): 707 - 710
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (693 KB) |  | HTML iconHTML  

    As one of new type evolutionary computing methods, mind evolutionary algorithm processes evolutionary operations by using 'similartax' and 'dissimilation' operator. This paper studies the variance of population during the evolution from the view of the functional analysis. Interval sheath theorem is used to prove the global convergence of the algorithm. The conclusion is validated again by the numerical experiment results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Approach to Self-Adaptive Active Control Mechanism to Support E-Government Based On Multi-Agent System

    Publication Year: 2006 , Page(s): 711 - 715
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2894 KB) |  | HTML iconHTML  

    In the distributed CSCW system, a cooperative workflow will always be interacted with many kinds of services during their interactive process, which make the application have much high demand for the quality of active control mechanism to support e-government platform. On the basis of discussing multi-agent system (MAS) interactive architecture under distributed network environment, it takes emphasis research on the active control strategy to support e-government platform. Then, a multi-agent supported self-adaptive structure of e-government is proposed to deal with multi-domain distributed applications in this paper. Furthermore, both the self-adaptive interactive control mechanism and communication protocol are implemented under network environment. Finally, it realizes the dynamic model of active control mechanism and carries out the self-adaptive environment, so it make the control structure be self-adaptive to the application of e-government platform effectively and satisfactorily View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Activation Function of Wavelet Chaotic Neural Networks

    Publication Year: 2006 , Page(s): 716 - 721
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2828 KB) |  | HTML iconHTML  

    In this paper, we studied the activation function of chaotic neural network, at first we review Chen's chaotic neural network and then propose a novel chaotic neural network model whose activation function is compose of sigmoid and wavelet function. Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chen's and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rough Set Theory-based Multi-class Decision Attribute Reduction Algorithm and Its Application

    Publication Year: 2006 , Page(s): 722 - 725
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (339 KB) |  | HTML iconHTML  

    Rough set theory is an effective tool in dealing with vague and uncertainty information, attribute reduction is one of its important concept. Many attribute reduction algorithms have been proposed, but they are more suitable for two classes problem. For multi-class decision attributes problem, a new attribute reduction algorithm based on discernibility matrix is proposed in the paper, it makes great use of the advantage of decision attribute's class information. In addition, we may draw an important conclusion that attribute reduction connects with class information in multi-class decision system, that is to say there will be deferent reduction results between deferent classes. The proposed algorithm can effectively reduce the computational complexity and increase reduction efficiency. Finally it is applied to diesel engine fault diagnosis, diagnosis result shows its feasibility and validity View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Improved Ant Colony Algorithm Based on Immunity System Genetic Algorithm and Application

    Publication Year: 2006 , Page(s): 726 - 731
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2144 KB) |  | HTML iconHTML  

    In this paper, aims at the weakness of ant colony algorithm that leads to converge rashly to the non-overall superior solution and its calculating time is long, when deals with resolving large optimization problem, a improved ant colony algorithm is presented. The algorithm combines the overall hunting ability with expansibility of the genetic algorithm and the character of immunity system in guiding partial hunting for particular problem. It is applied to the process of searching for the optimization in TSP, compares with the result of GA and ACA, the result of the new algorithm closes to superior solution much more, the validity of the algorithm is verified View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decomposition and Hierarchical Process for Fuzzy Cognitive Maps of Complex Systems

    Publication Year: 2006 , Page(s): 732 - 737
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5393 KB) |  | HTML iconHTML  

    In order to reduce the scale and complexity, the decomposition methods of fuzzy cognitive maps for knowledge representation and reasoning are presented. Partition the vertices of original cognitive map into some groups, and then construct quotient cognitive map based on these groups. Thus, the analysis of the original FCM can be reduced to that of quotient FCM, which provides global information of original FCM, and some sub FCMs which keep an original topological structure and inference and provide local information of original FCM. It extremely reduces the original size and complexity, meanwhile, it is possible to study system at different slices and enhance the enrichment and flexibility of research between concepts. Some knowledge representations and reasoning of complex system use the method of hierarchical for fuzzy cognitive maps. Therefore, it highlights the hierarchical causal relationship and inclusion relationship between concepts, and embodies the space causal relation between concepts View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimal Cognitive Model for Deliberate Agents

    Publication Year: 2006 , Page(s): 738 - 742
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5424 KB) |  | HTML iconHTML  

    In this paper we present a minimal cognitive model for deliberate agents, which includes problem formation, validity analysis, utility analysis, and belief changes. Through the model we emphasize that cognition may be a complex and recursive process that is relevant not only an agent's expertise but also domain problem-solving. Some methods for implementation of the model are discussed or described, and discriminating criterions are also presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on Communication Mechanism among Cooperating Multi-Intrusion Detection Agents

    Publication Year: 2006 , Page(s): 743 - 748
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5197 KB) |  | HTML iconHTML  

    In this paper, a communication mechanism of cooperation multi-IDAs (intrusion detection agent) is showed to solve disadvantage of IDS (intrusion detection system) with controlling center. After communication mechanism is given among cooperation multi-IDAs, a strategy of loading balance is described. Experiments showed that multi-IDAs can accomplish intrusion detection tasks. After the usage scope of IDS is given and the works next to do are presented, the validity of communication mechanism is confirmed by experiments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal Rough Neural Network

    Publication Year: 2006 , Page(s): 749 - 753
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (427 KB) |  | HTML iconHTML  

    This paper describes a new temporal rough neural network which consists of a combination of rough set and temporal concept. Temporal factors are combined with the input of neural network. That is to say, input of neural network is function of time, so conventional neurons are reconstructed temporal neurons. Neurons of temporal rough neural network is temporal rough neurons, they use pairs of upper and lower bounds as values for input and output and as variability for time. In some practical situations, it is preferable to develop prediction models that use ranges as values for input and/or output variables and as variability for time. A need to provide tolerance these ranges is an example of such a situation. Inability to record precise values of the variables is another situation where ranges of values must be used. In the example used in this study, a number of input values are associated with a single value of the output variable and with time. Hence, it seems appropriate to represent the input values as ranges. Temporal rough neural network can depict these situations and provide a better solution View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolved Patterns of Connectivity in Associative Memory Models

    Publication Year: 2006 , Page(s): 754 - 759
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5515 KB) |  | HTML iconHTML  

    This paper investigates possible connection strategies in sparsely connected associative memory models. This is interesting because real neural networks must have both efficient performance and minimal wiring length. We show, by using a genetic algorithm to evolve networks, that connection strategies, like those with exponentially reducing numbers of connections from near to far units, work efficiently and have low wiring costs. This implies, when modelling brain-like abilities in artificial neural networks, that it is possible to get good performance even with minimal numbers of long range connections View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Introduction to the World of Quantum Computers

    Publication Year: 2006 , Page(s): 760 - 764
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4614 KB) |  | HTML iconHTML  

    The world is changing very fast, and so are the ways of communication and computation. This article is about a new communication and information technology based on the principles of the quantum physics. At first we discuss about some fundamental paradigms of Quantum Computers World, and then introducing the basis of quantum computation: "QBit". After that we explain some magic properties of this atomic QBit including quantum measurement, superposition, entanglement, etc. Then we introduce quantum gates the basic modules of the next generation computers, their relation with the ordinary logical gates and the properties of some of the most useful quantum gates. And finally, we have a brief talk on some magic algorithm and the relation between these new born creatures and other fields of computers world, based on the quantum theories and manipulated by the quantum circuits View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Programming Task Demands

    Publication Year: 2006 , Page(s): 765 - 770
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6218 KB) |  | HTML iconHTML  

    Not all programming tasks are the same. Agile software development emphasizes people over process and working software over documents. This changes not only what we have learnt from years of experience in software development but also how we should see the relationships between software teams and programming tasks, as process management and control documents to support programming tasks have been much de-emphasized. Thus, we make an initial exploration of programming task demands. This provides a theoretical framework to better understand experienced-based agile practices and for managing programming tasks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Construction Approach of Regular Expressions from Finite Automata Including Multi-Node Loops

    Publication Year: 2006 , Page(s): 771 - 776
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5393 KB) |  | HTML iconHTML  

    The automaton theory has been widely applied in many areas of science, such as system simulations, neural networks, etc. It is also a basic theory of compiling routine for discriminating words of a programming language. This paper analyses the equivalence theorem between finite automata and regular expressions, points out the problem existing in the construction rules from finite automata to regular expressions, and proposes further a construction approach from finite automata including multi-node loops to regular expressions. The usage of this theorem and the construction process of regular expressions are expatriated, and the principle of choosing loops and their simplification from finite automata to regular expressions are discussed in detail View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Iterative FIR Filter for Image and Video Restoration

    Publication Year: 2006 , Page(s): 777 - 782
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4285 KB) |  | HTML iconHTML  

    Image and video filtering is a key image-processing task in computer vision especially in noisy environment. In most of the cases the noise source is unknown and hence possess a major difficulty in the filtering operation. In this paper we present an error-correction based learning approach for iterative filtering. A new FIR filter is designed in which the filter coefficients are updated based on Widrow-Hoff rule. Unlike the standard filter the proposed filter has the ability to remove noise without the a priori knowledge of the noise. Experimental result shows that the proposed filter efficiently removes the noise and preserves the edges in the image. We demonstrate the capability of the proposed algorithm by testing it on standard images infected by Gaussian noise and on a real time video containing inherent noise. Experimental result shows that the proposed filter is better than some of the existing standard filters View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quantum Algorithms and Hard Problems

    Publication Year: 2006 , Page(s): 783 - 787
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2252 KB) |  | HTML iconHTML  

    Any computation is necessarily a physical process. The current drive towards increasing speed and miniaturization of computers lead modern technology towards the subatomic domain - quantum computing, where strange quantum behavior takes over from familiar classical notions. The quantum computers have the ability to solve problems with varied computational complexities and more importantly hard problems. A problem is said to be hard, if the best possible algorithm requires exponential resources. This exponential quantum parallelism is the basis for the quantum speedup of many algorithms, and has made the construction of fast algorithms for quantum computers possible. Various proposals exist for modeling and devising procedures on computational problems related to factoring, searching, quantum counting, generalization of quantum algorithms etc. (Shor, 1994). In this paper, we have discussed the importance of algorithms such as order-finding, factoring and quantum searching which require exorbitant resources for their solution which otherwise is impossible on a classical computer View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.