By Topic

Cognitive Informatics, 6th IEEE International Conference on

Date 6-8 Aug. 2007

Filter Results

Displaying Results 1 - 25 of 80
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (642 KB)  
    Freely Available from IEEE
  • [Breaker page]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (361 KB)  
    Freely Available from IEEE
  • [Breaker page]

    Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (105 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): iii - vii
    Save to Project icon | Request Permissions | PDF file iconPDF (452 KB)  
    Freely Available from IEEE
  • Preface

    Page(s): viii
    Save to Project icon | Request Permissions | PDF file iconPDF (195 KB)  
    Freely Available from IEEE
  • Contributor listings

    Page(s): ix
    Save to Project icon | Request Permissions | PDF file iconPDF (76 KB)  
    Freely Available from IEEE
  • [Society related material]

    Page(s): x
    Save to Project icon | Request Permissions | PDF file iconPDF (368 KB)  
    Freely Available from IEEE
  • Language Understanding and Unified Cognitive Science

    Page(s): 1
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (86 KB) |  | HTML iconHTML  

    Summary form only given. Artificial intelligence applications, particularly those involving natural language understanding, are actually less ambitious than they, were decades ago. Statistical and machine learning techniques have had great success on tasks that can be treated without understanding, but there are many important areas that require semantic systems. The key to building more powerful AI applications is to model the world knowledge and the linguistic and other basic abilities that people bring to bear. We now know that these abilities can not be fully expressed in abstract formalisms, but require models that map onto human biology and behavior. Cognitive science is the field that is best placed to unite the theory and applications of intelligence. However, as with other fields, there is a tendency to specialize in a narrow sub-domain. This talk will make the case that a unified cognitive science is now possible, based on rapid advances in all the relevant disciplines, including computational modeling, and that there are already applications of this more cognitive approach to AI. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive Informatics Foundations of Nature and Machine Intelligence

    Page(s): 3 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4267 KB) |  | HTML iconHTML  

    Intelligence is a driving force or an ability to acquire and use knowledge and skills, or to inference in problem solving. This keynote lecture describes the taxonomy and nature of intelligence. It analyzes roles of information in the evolution of human intelligence, and the needs for logical abstraction in modeling the brain and natural intelligence. A formal model of intelligence is developed known as the generic intelligence mode (GIM), which provides a foundation to explain the mechanisms of advanced natural intelligence such as thinking, learning, and inferences. A measurement framework of intelligent capability of humans and systems is presented in the forms of intelligent quotient, intelligent equivalence, and intelligent metrics. On the basis of GIM model and theories, the compatibility of nature and machine intelligence is revealed, which forms a theoretical foundation for rigorous study in machine intelligence, AI, and intelligent systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Challenges in the Design of Adaptive, Intelligent and Cognitive Systems

    Page(s): 13 - 25
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6151 KB) |  | HTML iconHTML  

    Numerous attempts are being made to develop machines that could act not only autonomously, but also in an increasingly intelligent and cognitive manner. Such cognitive machines ought to be aware of their environments which include not only other machines, but also human beings. Such machines ought to understand the meaning of information in more human-like ways by grounding knowledge in the physical world and in the machines' own goals. The motivation for developing such machines range from self-evidenced practical reasons such as the expense of computer maintenance, to wearable computing in health care, and gaining a better understanding of the cognitive capabilities of the human brain. To achieve such an ambitious goal requires solutions to many problems, ranging from human perception, attention, concept creation, cognition, consciousness, executive processes guided by emotions and value, and symbiotic conversational human-machine interactions. This paper discusses some of the challenges emerging from this new design paradigm, including systemic problems, design issues, teaching the subjects to undergraduate students in electrical and computer engineering programs, research related to design. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formal Descriptions of a Set of Meta Cognitive Processes of the Brain

    Page(s): 26 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1820 KB) |  | HTML iconHTML  

    A set of fundamental cognitive processes of the brain is formally described in this paper. The cognitive processes defined at the meta cognitive level of the layered reference mode of the brain (LRMB) encompass those of object identification, concept establishment, categorization, comparison, qualification, quantification, selection, and search. Real-time process algebra (RTPA) is adopted as the denotational mathematical means for rigorous modeling and describing the meta cognitive processes. The mathematical model of each meta process is created and modeled in RTPA. All cognitive models and processes are explained on the basis of the object- attribute-relation (OAR) model for internal information and knowledge representation and manipulation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Approach to Representation Changes While Executing Problem Solver Intelligent Systems

    Page(s): 35 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2054 KB) |  | HTML iconHTML  

    The choice of an appropriate representation is generally assumed to play a decisive part in problem solving, both in human and computer performance. Some AI problem solvers have so far succeeded in performing automatic representation change, but none of them is actually able to do so once the resolution process is started. This inability proves to be a drawback so as to achieving a suitable representation is concerned. Also it should be observed that in human problem solving representation changes can actually occur in every stage of the resolution process. Taking all this into account, in the present paper we deal with a technique for changing representation while problem solving by making use of specific procedures which assign and modify a certain relevance value to every attribute involved in the problem representation, on behalf of their respective importance so as to actually solve the problem. This technique allows adapting representation to the peculiarities of each problem while the actual problem solving process takes place. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formal Linguistics and the Deductive Grammar

    Page(s): 43 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3142 KB) |  | HTML iconHTML  

    This paper presents a comparative study on fundamental theories of natural and artificial languages by contrasting their morphologies, syntaxes, semantics, and grammars. Formal syntaxes and semantics of natural languages are analyzed. The abstract syntaxes of English and their formal manipulations are described. A universal language processing model and the deductive grammar of English are developed toward the formalization of the universal grammar proposed in linguistics. Comparative analyses of natural and programming languages, as well as the linguistic perception on software engineering, are discussed. A wide range of applications of the deductive grammar of English have been explored in language acquisition, comprehension, generation, and processing in intelligent systems and cognitive informatics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a Spatial Representation for the Meta Cognitive Process Layer of Cognitive Informatics

    Page(s): 52 - 61
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2973 KB) |  | HTML iconHTML  

    This paper reviews related work in cognitive psychology, philosophy, and a bunch of independent research work in spatial knowledge representation, sets some criteria for potential spatial representations for cognitive informatics(CI), i.e. an expected theory of spatial knowledge for the meta representation layer of cognitive informatics shall take region as primitive, and be able to develop other spatial concepts. The paper critically points out the limitations of one dominant theory in spatial cognition, the RCC theory. It then introduces internal relations among different kinds of spatial knowledge, outlines a basic connection calculus for extended objects, and shows how notions of orientation relations, distance relations are developed in this calculus. The paper briefly presents how the notion of point can be further developed. By showing this we argue that this calculus meets the criteria for being a potential spatial representation for meta cognitive process layer of CI. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Visual Implications of Inspection Time

    Page(s): 62 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4809 KB) |  | HTML iconHTML  

    The quest to define human intelligence has led researchers down a large range of paths. One such path has been to search for a single psychometric measure that can be used to account for a large portion of the variance in human mental ability. Inspection time (IT) has emerged at the forefront of these efforts and is often referred to as the amount of time required to make a single observation of sensory input. IT can be shown to account for approximately 20% of the variance in human mental ability. In this study, we attempt to gain an insight into the nature of IT as a psychometric measure by contrasting individuals that are adept at performing the IT task (those with low ITs) with individuals that are not (those with high ITs) using oculomotor and task-performance measures recorded during two visual tasks. These tasks were designed to test participants' visual-attentional control and visual working memory under varying degrees of difficulty. The data show that a sensory-level theory of IT is incapable of accounting for the results found during the visual tasks, which leads us to introduce a novel theory of IT that places IT as a measure of information propagation. A discussion is presented on the implications and need for future validation of the theory. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Decomposition and Reconstruction using Two-Dimensional Complex-Valued Gabor Wavelets

    Page(s): 72 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2409 KB) |  | HTML iconHTML  

    This paper presents a scheme for image decomposition and reconstruction, using complex Gabor wavelets. Gabor functions have been used extensively in areas related to the human visual system due to their localization in space and bandlimited properties. However, since the standard two-sided Gabor functions are not orthogonal and lead to nearly singular Gabor matrices, they have been used in the decomposition and feature extraction of images rather than in image reconstruction. In an attempt to reduce the singularity of the Gabor matrix and produce reliable image reconstruction, in this paper, we show that a single-sided Gabor function can accomplish both, with the reconstruction residual error being very small (PSNR of at least 300 dB). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive Informatics in Automatic Pattern Understanding

    Page(s): 79 - 84
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2996 KB) |  | HTML iconHTML  

    In the paper a new way of pattern interpretation directed for automatic semantic categorization and image content understanding will be described. Such an understanding will be based on the linguistic theories of pattern classification and is aimed at facilitation of merit content analysis of for some classes of medical and economical patterns. The approach presented in this paper will show the great possibilities of automatic diseases interpretation in some analysed structures, and supporting information management using the grammar approach. The interpretation will be based on cognitive resonance processes, which imitate the psychological processes of understanding the registered patterns as they take place in the brain of a human being. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Cognitive Data Visualization Method Based on Hyper Surface

    Page(s): 85 - 91
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2815 KB) |  | HTML iconHTML  

    The understanding of data is highly relevant to how one senses and perceives them. The existing approaches for classification have been developed mainly based on exploring the intrinsic structure of dataset itself less or no emphasis paid on simulating human visual cognition. A new hyper surface classification method (HSC) has been studied since 2002. HSC is a universal classification method, in which a model of hyper surface is obtained by adoptively dividing the sample space and then the hyper surface is directly used to classify large database based on Jordan curve theorem in topology. In this paper we point out that HSC is a cognitive data visualization method. Simulation results show the effectiveness of the proposed method on large test data with complex distribution and high density. In particular, we show that HSC can very often bring a significant reduction of computation effort without loss of prediction capability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Simple High Accuracy Approach for Face Recognition

    Page(s): 92 - 98
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1707 KB) |  | HTML iconHTML  

    The theory that electoral college is more stable than direct popular vote is applied in face recognition. By simply adopting most traditional PCA approach, the experiments in this paper show a remarkably higher recognition rate than any known algorithm is reached with electoral college strategy on known FERET datasets. It indicates that a significant breakthrough can be expected by embedding electoral college with more effective face recognition algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Real-Time Color-Independent Method for Multiple Faces Tracking

    Page(s): 99 - 105
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2233 KB) |  | HTML iconHTML  

    In this paper, we describe a real-time gradient-based multiple faces tracking (GMFT) algorithm in complex background. In GMFT method first faces are detected by combination of morphological facial feature extraction and gradient-based edge detection methods. After a face is reliably detected, it is tracked over time with a novel real-time algorithm. The algorithm has been implemented and tested under a wide range of real-world conditions. The resulting system runs in real-time on a standard PC, being robust to face scale variations, rotations in depth, and fast changes in subject/camera position. It has consistently provided performance which satisfies the following requirements: 1) able to automatically determine the initial position and size of face(s) and track it/them in complex background; 2) insensitive to face orientation and scale changes; 3) insensitive to pose, lighting, and expression variations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Software Systems as Complex Networks

    Page(s): 106 - 115
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3282 KB) |  | HTML iconHTML  

    As software systems become larger and more complex, in order to understand, manage and evolve these systems, we need better ways of characterizing and controlling their macroscopic properties. We suggest complex network theory may be useful for these purposes. In recent years, researchers have shown that many complex systems from different disciplines can be investigated as complex networks and most of them comply with a scale-free network model. We explore the view that a software system can be studied as a network with a number of components (classes) connected by dependency (integration) relationships; we call this network the component dependency network (CDN). The CDNs of several Java libraries and applications have been examined and all of them exhibit some scale-free characteristics. This result has some practical value including that it allows us to identify important components (classes) and thereby assists software maintenance and reengineering. We have built a tool to study software systems as complex networks. In the paper we also suggest ways of controlling and changing how systems evolve in order to improve their understandability and maintainability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On Experiments for Measuring Cognitive Weights for Software Control Structures

    Page(s): 116 - 119
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (634 KB) |  | HTML iconHTML  

    Shao and Wang have proposed a cognitive complexity measure as a metric that can be used for estimating the comprehension effort for understanding software written in imperative programming languages. The key idea of their approach is to assign a cognitive weight to basic software control structures. The more difficult a control structure is to understand, the greater is its cognitive weight. In this paper, we discuss the experiments that have been used for calibrating the cognitive weights and show how they can be improved. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive Program Complexity Measure

    Page(s): 120 - 125
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1707 KB) |  | HTML iconHTML  

    In cognitive informatics, the functional complexity of software depends on three factors: internal architecture, input, and output. In the earlier proposed metrics based on cognitive informatics, these above factors are not fully considered. This paper proposes an improved cognitive complexity measure. Accordingly, new formula is developed to calculate the cognitive complexity. An attempt has also been made to evaluate and validate the proposed measure through Weyuker's properties and a practical framework. It has been found that seven of nine Weyuker's properties have been satisfied by the proposed cognitive complexity measure. It also satisfies most of the parameters required by the practical framework, hence establishes as a well-structured one. Finally, a comparative study with similar measures has been made to prove its robustness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Methodology from Software Engineering Inspection which Supports Replicable Mental Models Research

    Page(s): 126 - 133
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1301 KB) |  | HTML iconHTML  

    A modified inspection-style approach is used in two studies, the second a replication variant of the first, to determine the mental models of subjects with regard to their beliefs about methodological constraints in tools. In addition to determining the degree of variability of perception and the reasons for the variability, three belief biases were discovered. The inspection-style approach supports replication work and we recommend this approach to laboratory work for mental model research. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Object Oriented Complexity Metric Based on Cognitive Weights

    Page(s): 134 - 139
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1188 KB) |  | HTML iconHTML  

    Complexity in general is defined as "the degree to which a system or component has a design or implementation that is difficult to understand and verify ". Complexity metrics are used to predict critical information about reliability and maintainability of software systems. Object oriented software development requires a different approach to software metrics. In this paper, an attempt has been made to propose a metric for an object oriented code, which calculates the complexity of a class at method level. The proposed measure considers the internal architecture of the class, subclass, and member functions, while other proposed metrics for object oriented programming do not. An attempt has also been made to evaluate and validate the proposed measure in terms of Weyuker's properties and against the principles of measurement theory. It has been found that seven of nine Weyuker's properties have been satisfied by the proposed measure. It also satisfies most of the parameters required by the measurement theory perspective, hence establishes as a well-structured one. View full abstract»

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