You are previewing Discoveries and Breakthroughs in Cognitive Informatics and Natural Intelligence.
O'Reilly logo
Discoveries and Breakthroughs in Cognitive Informatics and Natural Intelligence

Book Description

Discoveries and Breakthroughs in Cognitive Informatics and Natural Intelligence, provides emerging research topics in cognitive informatics research with a focus on such topics as reducing cognitive overload, real-time process algebra, and neural networks for iris recognition, emotion recognition in speech, and the classification of musical chords.

Table of Contents

  1. Copyright
  2. Editorial Advisory Board
  3. List of Reviewers
  4. Preface
  5. 1. A Computational Cognitive Model of the Brain
    1. ABSTRACT
    2. INTRODUCTION
    3. RELATED WORK
    4. CONNECTED COMPONENT NETWORK
    5. USING CCN TO MODEL THE BRAIN
      1. Knowledge Representation
      2. Learning of a CCNB
      3. Consciousness and Subconsciousness
      4. Feature Selection and Attention
      5. Similarity and Disambiguation
      6. "Thinking" in a CCNB
      7. Making Inference in a CCNB
    6. EXPERIMENTAL EVIDENCE
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
    10. ENDNOTES
  6. 2. A Cognitive Approach to the Mechanism of Intelligence1
    1. ABSTRACT
    2. INTRODUCTION
    3. A DEFINITION OF INTELLIGENCE AND A MODEL OF HUMAN INTELLIGENCE FORMATION
    4. CORE MECHANISM OF INTELLIGENCE FORMATION: INFORMATION- KNOWLEDGE-INTELLIGENCE TRANSFORMATIONS
      1. The Transformation 1: From Ontological Information to Epistemological Information
      2. The Transformation 2: From Information to Knowledge
      3. Transformation 3: From Knowledge to Intelligence in the Narrow Sense (Intelligent Strategy)
      4. Transformation 4: From Strategy to Action
      5. The Mechanism of Intelligence Formation (A Summary)
    5. A UNIFYING THEORY OF AI
    6. OPEN ISSUES: NEW ROOM FOR DISCOVERIES AND INNOVATIONS
      1. The Mathematical Dimension
      2. The Biological Dimension
      3. Technological Dimension
    7. CONCLUSION
    8. REFERENCES
    9. ENDNOTE
  7. 3. Reducing Cognitive Overload by Meta-Learning Assisted Algorithm Selection
    1. ABSTRACT
    2. META–LEARNING BASIC CONCEPT
    3. EXISTING META–LEARNING METHODS AND ALGORITHM SELECTION SYSTEMS
      1. Data Characterization Methods
      2. Information and Statistical Properties Based Data Characterization
      3. Landmarking
      4. Decision Tree Based Data characterization
      5. Algorithm Selection Methods
      6. Existing Algorithm Selection Systems
    4. A ROUGH SET–ASSISTED META–LEARNING METHOD
      1. Method
      2. The Distance Based Multicriteria Evaluation Measurement
      3. Feature Selection and Rough Set Assisted Reduction
      4. Weight Adjustment by Using Mutual Information
    5. EXPERIMENT
      1. Experimental Descriptions
      2. Experimental Setting
      3. Experimental Procedure
    6. RESULTS AND DISCUSSION
    7. CONCLUSION AND FUTURE WORK
    8. REFERENCES
  8. 4. Analyzing Learning Methods in a Functional Environment
    1. ABSTRACT
    2. ANALYZING LEARNING METHODS IN A FUNCTIONAL ENVIRONMENT
    3. LEARNING THEORIES
    4. THE PROGRAMMING LANGUAGE
      1. Basic Environment
    5. DEFINING COGNITIVE PROCESSES
    6. INTRODUCING OBSERVATIONS IN EDEN
      1. Basic Ideas of Our Implementation
    7. OBSERVING ENTITIES
      1. Behavioral Observations
      2. Constructivism Observations
    8. CONCLUSION AND CURRENT WORK
    9. REFERENCES
    10. ENDNOTES
  9. 5. Humans and Machines: Nature of Learning and Learning of Nature
    1. ABSTRACT
    2. INTRODUCTION
    3. HUMAN LEARNING
      1. Nature of Learning
        1. Preliminary Considerations: Different Objects of Human Learning, One Fundamental Base
        2. A Little Allegory of the Scientific Models of Human Learning
      2. Conclusion
      3. Learning of Nature
        1. A Little Allegory of the Scientific Understanding of Scientific Processes
        2. Conclusion 1: Nature of Learning and Learning of Nature
        3. Conclusion 2: Implications for Learning of Nature in the Classroom
    4. HUMAN AND MACHINE ASSOCIATED LEARNING OF NATURE
      1. A Little Allegory of Learning from Each other
        1. Passive Learning
        2. Active Learning
        3. Social Learning
      2. Implementation of the Last Variation
      3. Learning Impact of the Game
      4. Extensions on Machine Learning
      5. Conclusion
    5. GENERAL CONCLUSION
      1. What Can We Expect, or Not, From Machine Assisted Human Learning?
      2. What Do We Expect from Machine Assisted Human Learning?
    6. REFERENCES
    7. ENDNOTES
  10. 6. On Cognitive Properties of Human Factors and Error Models in Engineering and Socialization
    1. ABSTRACT
    2. INTRODUCTION
    3. COGNITIVE FOUNDATIONS OF HUMAN TRAITS
      1. Axiomatic Human Traits
      2. Basic Personality Traits in Engineering
    4. THE HIERARCHICAL MODEL OF BASIC HUMAN NEEDS
    5. CHARACTERISTICS OF HUMAN FACTORS
      1. Properties of Human Factors in Engineering
      2. Properties of Human Factors in Socialization
      3. Social Environments for software Engineering
    6. THE FORMAL MODEL OF HUMAN ERRORS
      1. Taxonomy of Human Errors
      2. The Behavioral Model of Human Errors
      3. The Random Feature of Human Errors
      4. The Theoretical Foundation of Quality Assurance in Creative Work
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  11. 7. User-Centered Interactive Data Mining
    1. ABSTRACT
    2. INTRODUCTION
    3. A FRAMEWORK OF INTERACTIVE DATA MINING
      1. Modelling User Preference
      2. A User-Centered Three-Layered Framework
    4. MULTIPLE VIEWS IN THE PHILOSOPHY LAYER
      1. Languages for Rule Description
      2. Measures of Rules
        1. Objective Measures
        2. Subjective Measures
      3. Interpretations of Rules
    5. MULTIPLE STRATEGIES IN THE TECHNIQUE LAYER
      1. Retaining Strategies
      2. Compromising Strategies
    6. MULTIPLE EXPLANATIONS IN THE APPLICATION LAYER
    7. CONCLUSION
    8. REFERENCES
  12. 8. On Concept Algebra: A Denotational Mathematical Structure for Knowledge and Software Modeling
    1. ABSTRACT
    2. INTRODUCTION
    3. THE MATHEMATICAL MODEL OF ABSTRACT CONCEPTS
    4. RELATIONAL OPERATIONS OF CONCEPTS
    5. COMPOSITIONAL OPERATIONS OF CONCEPTS
    6. CONCEPT ALGEBRA FOR KNOWLEDGE MANIPULATION
      1. The Mathematical Model of Knowledge
      2. The Hierarchical Model of Concept Networks
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  13. 9. On System Algebra: A Denotational Mathematical Structure for Abstract System Modeling
    1. ABSTRACT
    2. INTRODUCTION
    3. THE ABSTRACT SYSTEM THEORY
      1. The Mathematical Model of Closed Systems
      2. The Mathematical Model of Open Systems
    4. PROPERTIES OF ABSTRACT SYSTEMS
      1. Taxonomy of Systems
      2. Magnitude of Systems
    5. RELATIONAL OPERATIONS ON SYSTEMS
      1. Algebraic Relations of Closed Systems
      2. Algebraic Relations of Open Systems
      3. Relations Between Open and Closed Systems
    6. COMPOSITIONAL OPERATIONS ON SYSTEMS
      1. System Inheritance
      2. System Tailoring
      3. System Extension
      4. System Substitution
      5. System Composition
      6. System Difference
      7. System Decomposition
      8. System Aggregation
      9. System Specification
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  14. 10. RTPA: A Denotational Mathematics for Manipulating Intelligent and Computational Behaviors
    1. ABSTRACT
    2. INTRODUCTION
    3. THE TYPE SYSTEM OF RTPA
      1. The Type System for Data Objects Modeling in RTPA
      2. Advanced Types of RTPA
      3. Formal Type Rules of RTPA
    4. METAPROCESSES OF RTPA
    5. ALGEBRAIC PROCESS OPERATIONS IN RTPA
    6. MANIPULATION OF COMPUTATIONAL BEHAVIORS BY RTPA
      1. The Universal Mathematical Model of Programs Based on RTPA
      2. ADT Modeling and Specification in RTPA
        1. Architectural Modeling in RTPA
        2. Static Behavior Modeling in RTPA
        3. Dynamic Behavior Modeling in RTPA
    7. MANIPULATION OF INTELLIGENT BEHAVIORS BY RTPA
      1. The Cognitive Process of Memorization
      2. Formal Description of the Memorization Process in RTPA
    8. CONCLUSION
    9. ACKNOWLEDGMENT
    10. REFERENCES
  15. 11. A Denotational Semantics of Real-Time Process Algebra (RTPA)
    1. ABSTRACT
    2. INTRODUCTION
    3. THE ACTIVITY DURATION CALCULUS
      1. Variables and Values
      2. Environments
      3. Durations
      4. Temporal Ordered Duration Sequences
      5. Sequence Operations
    4. THE ABSTRACT SYNTAX OF RTPA
      1. Variables of RTPA
      2. Expressions of RTPA
      3. Processes of RTPA
    5. THE SEMANTIC DOMAINS OF RTPA
      1. Variables and Values in RTPA
        1. Process Executions in RTPA
    6. THE DENOTATIONAL SEMANTIC FUNCTIONS OF RTPA META PROCESSES
    7. THE DENOTATIONAL SEMANTIC FUNCTIONS OF RTPA PROCESS RELATIONS
    8. CONCLUSION
    9. ACKNOWLEDGMENT
    10. REFERENCES
  16. 12. An Operational Semantics of Real-Time Process Algebra (RTPA)
    1. ABSTRACT
    2. INTRODUCTION
    3. THE ABSTRACT SYNTAX OF RTPA
      1. The Meta Processes of Software Behaviors in RTPA
      2. Process Operations of RTPA
      3. The Type System of RTPA
    4. THE REDUCTION MACHINE OF RTPA
    5. OPERATIONAL SEMANTICS OF RTPA META-PROCESSES
    6. OPERATIONAL SEMANTICS OF PROCESS RELATIONS
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  17. 13. Formal Modeling and Specification of Design Patterns Using RTPA
    1. ABSTRACT
    2. INTRODUCTION
    3. APPROACHES TO SOFTWARE PATTERN DESCRIPTION
      1. The Layout Object Model
      2. The Constraint Diagrams
      3. LePUS: Language for Patterns Uniform Specification
      4. Other Approaches
    4. THE RTPA METHODOLOGY FOR PATTERN MODELING AND SPECIFICATION
      1. The Generic Model of Classes in RTPA
      2. The Generic Model of Patterns in RTPA
    5. CASE STUDIES ON FORMAL SPECIFICATIONS OF PATTERNS IN RTPA
      1. Formal Specification of the State Pattern
      2. Formal Specification of the Strategy Pattern
      3. Formal Specification of the MasterSlave Pattern
    6. CONCLUSION
    7. ACKNOWLEDGMENT
    8. REFERENCES
  18. 14. Deductive Semantics of RTPA
    1. ABSTRACT
    2. INTRODUCTION
    3. THE THEORY OF DEDUCTIVE SEMANTICS
      1. The Semantic Environment and Semantic Function
      2. Deductive Semantics of Programs at Different Levels of Compositions
      3. Properties of Software Semantics
    4. DEDUCTIVE SEMANTICS OF RTPA METAPROCESSES
      1. The Assignment Process
      2. THE EVALUATION PROCESS
      3. The Addressing Process
      4. The Memory Allocation Process
      5. The Memory Release Process
      6. The Read Process
      7. The Write Process
      8. The Input Process
      9. The Output Process
      10. The Timing Process
      11. The Duration Process
      12. The Increase Process
      13. The Decrease Process
      14. The Exception Detection Process
      15. The Skip Process
      16. The Stop Process
    5. DEDUCTIVE SEMANTICS OF RTPA PROCESS RELATIONS
      1. The Sequential Process Relation
      2. The Jump Process Relation
      3. The Branch Process Relation
      4. The Switch Process Relation
      5. The While-Loop Process Relation
      6. The Repeat-Loop process Relation
      7. The For-Loop Process Relation
      8. The Function Call Process Relation
      9. The Recursive Process Relation
      10. The Parallel Process Relation
      11. The Concurrent Process Relation
      12. The Interleave Process Relation
      13. The Pipeline Process Relation
      14. The Interrupt Process Relation
    6. DEDUCTIVE SEMANTICS OF SYSTEM-LEVEL PROCESSES OF RTPA
      1. The System Process
      2. The Time-Driven Dispatching Process Relation
      3. The Event-Driven Dispatching Process Relation
      4. The Interrupt-Driven Dispatching Process Relation
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  19. 15. On the Big-R Notation for Describing Iterative and Recursive Behaviors
    1. ABSTRACT
    2. INTRODUCTION
    3. THE BIG-R NOTATION
      1. The Basic Control Structures of Computing
      2. The Big-R Notation for Denoting Iterations and Recursions
    4. MODELING ITERATIONS USING THE BIG-R NOTATION
      1. Existing Semantic Models of Iterations
      2. A Unified Mathematical Model of Iterations
    5. MODELING RECURSIONS USING THE BIG-R NOTATION
      1. Properties of Recursions
      2. The Mathematical Model of Recursions
    6. COMPARATIVE ANALYSIS OF ITERATIONS AND RECURSIONS
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  20. 16. Formal RTPA Models for a Set of Meta — Cognitive Processes of the Brain
    1. ABSTRACT
    2. INTRODUCTION
    3. THE COGNITIVE PROCESS OF OBJECT IDENTIFICATION
    4. THE COGNITIVE PROCESS OF CONCEPT ESTABLISHMENT
    5. THE COGNITIVE PROCESS OF SEARCH
    6. THE COGNITIVE PROCESS OF CATEGORIZATION
    7. THE COGNITIVE PROCESS OF COMPARISON
    8. THE COGNITIVE PROCESS OF QUALIFICATION
    9. THE COGNITIVE PROCESS OF QUANTIFICATION
    10. THE COGNITIVE PROCESS OF SELECTION
    11. CONCLUSION
    12. ACKNOWLEDGMENT
    13. REFERENCES
  21. 17. Unifying Rough Set Analysis and Formal Concept Analysis Based on a Logic Approach to Granular Computing
    1. ABSTRACT
    2. INTRODUCTION
    3. OVERVIEW OF GRANULAR COMPUTING
      1. Granular Structures
      2. The Triarchic Model of Granular Computing
    4. THE LOGIC LANGUAGE L
      1. Syntax and Semantics
      2. Differences between L and Other Decision Logic Languages
        1. Two Sub-Languages of L
        2. Interpretation of Granules
        3. Interpretation of Granular Structures
        4. Interpretation of Rules
    5. THE LANGUAGE L IN ROUGH SET ANALYSIS
      1. Information Tables
        1. Granules in Rough Set Analysis
        2. Interpretation of Low and High Order Rules
        3. Granular Structures in Rough Set Analysis
    6. THE LANGUAGE L IN FORMAL CONCEPT ANALYSIS
        1. Formal Contexts
        2. Granules in Formal Concept Analysis
        3. Granular Structures in Formal Concept Analysis
        4. Implications and Dependencies in Formal Concept Analysis
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
  22. 18. On Foundations and Applications of the Paradigm of Granular Rough Computing
    1. ABSTRACT
    2. NOTIONS CENTRAL TO GRANULATION OF KNOWLEDGE
      1. Rough Set Analysis of Knowledge
      2. Mereology
      3. Rough Mereology and Rough Inclusions
      4. Rough Inclusions in Information Systems
      5. The Rough Inclusion from the Hamming Metric
      6. Rough Inclusions from T-Norms
    3. GRANULATION OF KNOWLEDGE
      1. Granules from Rough Inclusions
      2. Granular RM-Logics
      3. Rough Inclusions on Sets
      4. Networks of Granular Agents
      5. A Granular Approach to Data Classification
    4. SUMMARY AND CONCLUSION
    5. ACKNOWLEDGMENT
    6. REFERENCES
  23. 19. Robust Independent Component Analysis for Cognitive Informatics
    1. ABSTRACT
    2. INTRODUCTION
    3. INDEPENDENT COMPONENT ANALYSIS
      1. FastICA
      2. Extended Infomax
    4. JADE
      1. Radical
      2. Beta-Divergence
      3. Whitening
    5. MEASURES OF OUTLIER ROBUSTNESS
      1. Amari Separation Performance Index
      2. Optimum Rotation-Angle Error
      3. Contrast Function Difference
    6. DESIGN OF EXPERIMENTS
      1. Contrast Function Setup
      2. Parameters Used in Software
      3. Reporting of Results
    7. RESULTS AND DISCUSSION
      1. Amari Separation Performance
      2. Optimum Angle of Rotation Error
      3. Contrast Function Difference
      4. Other Considerations
    8. CONCLUSION
    9. ACKNOWLEDGMENT
    10. REFERENCES
  24. 20. A Relative Fractal Dimension Spectrum for a Perceptual Complexity Measure
    1. ABSTRACT
    2. INTRODUCTION
    3. BACKGROUND ON FRACTAL MEASURES
      1. Single Fractal Dimension Measures
      2. Multifractal Dimension Measures
      3. Rényi Fractal Dimension Spectrum
    4. MEASURING CLOSENESS OF PROBABILITY MODELS
    5. RELATIVE MULTIFRACTAL DIMENSION MEASURES
      1. Derivation
      2. Image Quality Metric, IQM
    6. COMPUTATIONAL CONSIDERATIONS
      1. Choice of Probabilities
      2. Avoidance of Zero Probabilities
      3. Sufficiency of the Number of Data Points
      4. Robust slope Estimation
    7. EXPERIMENTAL RESULTS
    8. CONCLUSION
    9. ACKNOWLEDGMENT
    10. REFERENCES
  25. 21. 3D Object Classification Based on Volumetric Parts
    1. ABSTRACT
    2. PROBLEM DESCRIPTION
      1. Volumetric Representation: Superquadric-Based Geon (SBG)
        1. RBC Theory and Geons
        2. Superquadric Models
        3. Superquadric-Based Geons
      2. SBG Extraction
        1. 3D Models
    3. FEATURES, CONSTRAINTS, AND TREE SEARCH
      1. Features and Corresponding Constraints
        1. Unary Features and Constraints
        2. Binary Features and Constraints
      2. Constrained Tree Search
    4. SIMILARITY MEASURE COMPUTATION
      1. Part Similarity Measure – Psim(ml, i, dji)
      2. Whole and Partial similarity Measure – Msimlw and Msimlp
      3. Focus Similarity Measure – FOsim
      4. Classification
    5. EXPERIMENTAL RESULTS AND EVALUATION
      1. Whole Match
      2. Whole Match and Partial Match
        1. Focus Match on Key Parts
    6. CONCLUSION AND FURTHER DIRECTIONS
    7. ACKNOWLEDGMENT
    8. REFERENCES
  26. 22. Modeling Underwater Structures
    1. ABSTRACT
    2. INTRODUCTION
    3. AQUA AND THE AQUASENSOR
    4. OBTAINING LOCAL SURFACE MODELS
    5. VISUAL EGOMOTION ESTIMATION
    6. IMU INTEGRATION
    7. SEGMENTING LOCAL MODELS
    8. 3-D LAZY SNAPPING
    9. EXAMPLE SEGMENTATION
      1. Discussion and Future Work
    10. ACKNOWLEDGMENT
    11. REFERENCES
  27. 23. A Novel Plausible Model for Visual Perception
    1. ABSTRACT
    2. INTRODUCTION
    3. RELATED WORK
      1. Bayesian Network
      2. The Weakness of Bayesian Network
    4. CELLULAR BAYESIAN NETWORKS (CBNS)
      1. Motivation
      2. Model Description
      3. Learning a CBNs
      4. Inference on a CBNs
      5. Model Visual Perception with CBNs
    5. SIMULATION
      1. Dataset
      2. Contrast Detector
      3. Constructing CBNS
      4. Performance Evaluation
    6. DISCUSSION
    7. CONCLUSION
    8. ACKNOWLEDGMENT
    9. REFERENCES
    10. ENDNOTES
  28. 24. An Efficient and Automatic Iris Recognition System Using ICM Neural Network
    1. ABSTRACT
    2. INTRODUCTION
    3. IRIS IMAGE PREPROCESSING
      1. Pupil Location
      2. Iris Outer Boundary Location
      3. Normalization
      4. Iris Enhancement
    4. IRIS FEATURE EXTRACTION USING ICM NEURAL NETWORK AND IRIS MATCHING
      1. Intersecting Cortical Model (ICM) Neural Network
      2. Feature Extraction and Matching
    5. EXPERIMENTAL RESULTS AND DISCUSSION
      1. Experimental Results
      2. Discussion
    6. CONCLUSION
    7. ACKNOWLEDGMENT
    8. REFERENCE
  29. 25. Neural Networks for Language Independent Emotion Recognition in Speech
    1. ABSTRACT
    2. INTRODUCTION
      1. General Background
      2. Previous Work
    3. EMOTIONAL SPEECH ACQUISITION
    4. OVERVIEW OF THE RECOGNITION SYSTEM
      1. Pre-Processing
      2. Spectral Analysis and Feature Extraction
    5. FEATURE SELECTION
      1. Sequential Forward Selection Method
      2. General Regression Neural Network
      3. Consistency Based Feature Selection
    6. RECOGNIZING EMOTIONS
      1. Neural Network Based Classification
      2. K-Nearest Neighbors Classifier
    7. RECOGNITION RESULTS
    8. DISCUSSION
    9. CONCLUSION
    10. ACKNOWLEDGMENT
    11. REFERENCES
  30. 26. An Analysis of Internal Representations for Two Artificial Neural Networks that Classify Musical Chords
    1. INTRODUCTION
    2. RELATED WORK
    3. CHORD CLASSIFICATION BY NEURAL NETWORKS
    4. STUDY 1: CHORDS DEFINED WITH PITCH CLASS REPRESENTATION METHOD
      1. Training Set
      2. Network Architecture
      3. Network Training
    5. RESULTS
      1. Interpretation of Weights from Input Units
      2. Using Hidden Unit Responses To Classify Chords
    6. STUDY 2: CHORD CLASSIFICATION USING LOCAL REPRESENTATION
    7. METHOD
      1. Training Set
      2. Network Architecture
      3. Network Training
    8. RESULTS
      1. Interpretation of Weights from Input Unit
      2. Using Hidden Unit Responses to Classify Chords
    9. DISCUSSION
    10. ACKNOWLEDGMENT
    11. REFERENCES
  31. 27. Foundation and Classification of Nonconventional Neural Units and Paradigm of Nonsynaptic Neural Interaction
    1. ABSTRACT
    2. INTRODUCTION
    3. CLASSIFICATION OF NONCONVENTIONAL NEURAL UNITS
      1. Classification of Neural Units by Nonlinear Aggregating Function
      2. Classification of Neural Units by Neural Dynamics
      3. Classification of Neural Units by Implementation of Time Delays
    4. SYNAPTIC AND NONSYNAPTIC NATURE OF NONLINEAR NEURAL AGGREGATION FUNCTION
    5. SUMMARY
    6. ACKNOWLEDGMENT
    7. REFERENCES
  32. 28. Scaling Behavior of Maximal Repeat Distributions in Genomic Sequences: A Randomize Test Follow Up Study
    1. ABSTRACT
    2. INTRODUCTION
    3. METHOD
    4. RESULTS
    5. SUMMARY AND DISCUSSION
    6. ACKNOWLEDGMENT
    7. REFERENCES
  33. Compilation of References
  34. About the Contributors