Foundations of Intelligent Systems

Name: Foundations of Intelligent Systems | 19th International Symposium, ISMIS 2011, Warsaw, Poland, June 28-30, 2011, Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

19th International Symposium, ISMIS 2011, Warsaw, Poland, June 28-30, 2011, Proceedings

Marzena Kryszkiewics Henryk Rybinski Andrzej Skowron Zbigniew W. Ras(Editor)

Springer (Publisher)

Published on 24. June 2011

XIX, 746 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-21916-0 (ISBN)

€96.29incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Title
Preface
Organization
Table of Contents
Invited Papers
Intelligent Multimedia Solutions Supporting Special Education Needs
Introduction
Multimodal Interfaces
Gesture-Controlled Interactive Whiteboard
Kalman Filtering
Fuzzy Logic Interpreter
Audio Modality: Speech Stretcher
Conclusions
Reference
Relational Mining in Spatial Domains: Accomplishments and Challenges
Introduction
Integration with Spatial Databases
Dealing with Hierarchical Representations of Objects and Relationships
Dealing with Spatial Autocorrelation
Dealing with Unlabeled Data
Dealing with Dynamic Spatial Networks
Conclusions
References
Towards Programming Languages for Machine Learning and Data Mining (Extended Abstract)
Motivation
Machine Learning and Data Mining as Constraint Satisfaction and Optimization Problems
Declarative Programming for Machine Learning and Data Mining
Challenges
Conclusions
References
Rough Sets - in Memoriam Zdzis law Pawlak
The Extraction Method of DNA Microarray Features Based on Modified F Statistics vs. Classifier Based on Rough Mereology
Introduction
DNA Microarrays
Basic Notions of Rough Set Theory and Granular Theory
Granular Classification of Knowledge
Application of Residual Rough Inclusions
Residua of T-Norms, Residual Rough Inclusions
A Voting Scheme for Decision Value Assignment
DNA Microarray Features Extraction Method
Augmented Weighted Voting by Granules of Training Objects
The Results of Experiments with Leave One Out Method for Sample DNA Microarray Data
The Results for Our Gene Extraction Method
Conclusions
References
Attribute Dynamics in Rough Sets
Introduction
Preliminary Notions
Rough Sets Basis
Temporal Dynamics in Information Tables
Theoretical Results
Reducts Update
Rules Update
Experiments
Conclusion
References
A Comparison of Some Rough Set Approaches to Mining Symbolic Data with Missing Attribute Values
Introduction
Rough Set Approaches to Missing Attribute Values
A Probabilistic Option
Experiments
Conclusions
References
Action Reducts
Introduction
Algorithm
Notations
Algorithm Description
Example
Implementation and Experiment
Related Work and Contribution
Summary
References
Incremental Rule Induction Based on Rough Set Theory
Introduction
Rough Sets and Probabilistic Rules
Rough Set Theory
Probabilistic Rules
Problems in Incremental Rule Induction
An Algorithm for Incremental Learning
Algorithm
Example
Experimental Results
Related Work
Conclusions
References
Challenges in Knowledge Discovery and Data Mining - in Memoriam Jan $\.{Z}ytkow
Mining Classification Rules for Detecting Medication Order Changes by Using Characteristic CPOE Subsequences
Introduction
A Method to Obtain Classification Rules with Characteristic Order Subsequences
Processing Order History Data to the Dataset for Rule Mining
Gathering Patient Basic Information
Constructing the Instances of the Dataset for Rule Mining
Extracting Characteristic Order Entry Subsequences by Using Sequential Pattern Mining Approach
A Case Study on an Actual Order Entry Histories
Counts of the Five Kinds of Order Entries and the Medication Order Entry Changes
Extracting Characteristic Order Entry Subsequences by Using Term ExtractionMethod in Natural Language Processing
Obtaining Classification Rules with/without Characteristic Order Entry Subsequences
Conclusion
References
Incorporating Neighborhood Effects in Customer Relationship Management Models
Introduction
Methodology
Data Description
Generalized Linear Autologistic Regression Model
Results
Conclusions
References
ETree Miner: A New GUHA Procedure for Building Exploration Trees
Introduction
Induction of Exploration Trees
The Algorithm
Empirical Evaluation
Related Work
Conclusions
References
Mapping Data Mining Algorithms on a GPU Architecture: A Study
Introduction
Motivation
Hardware Configuration
Performance Study
Data Mining on GPUs
Memory Latency Analysis
Communication Patterns
Performance Analysis for Different Number of Threads
Performance Optimization Guidelines
Conclusion and Future Work
References
Applying Domain Knowledge in Association Rules Mining Process - First Experience
Introduction
STULONG Data Set
Data Matrix Entry
Domain Knowledge
Association Rules
Applying LISp-Miner System
Analytical Question and 4ft-Miner
Atomic Consequences of {\em BMI} $ \uparrow \uparrow $ {\em Diast}
Filtering Out Consequences of {\em BMI} $ \uparrow \uparrow $ {\em Diast}
Conclusions and Further Work
References
A Compression-Based Dissimilarity Measure for Multi-task Clustering
Introduction
Related Works
Preliminaries
Compression-Based Multi-task Clustering
Intuition Behind Our Method
CMC Framework with LDCDM Measure
Experimental Results
Results on Language and Heterogeneous Data Sets
Results on Document Data
Conclusions
References
Data Mining in Meningoencephalitis: The Starting Point of Discovery Challenge
Introduction
Database on Meningoencephalitis
Information about Data
Statistical Analysis and Experts' Prejudice
Preliminary Results
Rule Induction Methods
SIBLE:Interactive Evolutionary Computation
GDT-RS
Association Rules Analysis with Discretization
Exception Rule Discovery
Summary
References
Social Networks
Extracting Social Networks Enriched by Using Text
Introduction
Related Work
From Theory to Experiments
Theoretical Framework
Extracting Quotations
System Overview
Results
Conclusion
References
Enhancing Navigation in Virtual Worlds through Social Networks Analysis
Introduction
A SNA Approach for Realism Enhancing in VWs
Evaluation and Preliminary Results
Related Work
Conclusion and Future Work
References
Learning Diffusion Probability Based on Node Attributes in Social Networks
Introduction
Diffusion Model
AsIC Model
Extension of AsIC Model for Using Node Attributes
Learning Problem and Method
Learning Problem
Learning Method
Experimental Evaluation
Dataset
Results
Conclusion
References
Multi-Agent Systems
Analysing the Behaviour of Robot Teams through Relational Sequential Pattern Mining
Introduction
Learning Behavioural Relational Representation
Experimental Evaluation
Related Work and Conclusions
References
Deliberation Dialogues during Multi-agent Planning
Introduction
Speech Acts and Dialogues
Stages of Teamwork
The Logical Language
Kripke Models
Semantics of Speech Acts
A Four-Stage Model of Deliberation
Unveiling the Plan Formation Stage
Conclusions and Future Work
References
DDLD-Based Reasoning for MAS
Introduction
Related Work
Basic Concepts
Distributed Reasoning with Defaults
Transforming Defaults
Reasoning with Default Transformations
DDLD-Based Multi-Agent System
Agent Knowledge
Distributed Reasoning
Conclusion
References
Theoretical Backgrounds of AI
Markov Blanket Approximation Based on Clustering
Introduction
Theoretical Aspects
Proposed Methods
Experiments and Summary
References
Tri-Based Set Operations and Selective Computation of Prime Implicates
Introduction
Preliminaries
Prime Implicates under Truth-Functional Substitution
Tri-Based Operations
The New pi-trie Algorithm
Selective Computation
Experiments with Subset Invariant Properties
Reference
Cholesky Decomposition Rectification for Non-negative Matrix Factorization
Introduction
Cholesky Decomposition Rectification for NMF
Non-negative Matrix Factorization
Clustering with NMF
Representation Learning with NMF
Cholesky Decomposition Rectification
Evaluations
Experimental Settings
Results
Concluding Remarks
References
Machine Learning
A New Method for Adaptive Sequential Sampling for Learning and Parameter Estimation
Introduction
Background
The Proposed Adaptive Sampling Method
Our Sampling Scheme for Controlling Absolute Error
Our Sampling Scheme for Controlling Relative Error
Conclusions and Future Work
References
An Evolutionary Algorithm for Global Induction of Regression Trees with Multivariate Linear Models
Introduction
Global Versus Local Induction
Related Work
An Evolutionary Induction of Model Trees
Representation
Initialization
Genetic Operators
Selection and Termination Condition
Fitness Function
Experimental Validation
Synthetical Datasets
Real-Life Datasets
Conclusion
References
Optimizing Probabilistic Models for Relational Sequence Learning
Introduction
Lynx: A Relational Pattern-Based Classifier
Feature Construction via Pattern Mining
Pattern-Based Classification
Feature Selection with Stochastic Local Search
Experiments
Conclusions
References
Learning with Semantic Kernels for Clausal Knowledge Bases
Statistical Learning for Complex Representations
Learning Relational Classifiers through Kernel Methods
Clausal Knowledge Bases
Learning Linear Classifiers
Kernels for Structured Representations
Semantic Kernels for Clausal Spaces
Kernel Definition
Discussion
Extensions
Classification and Query Answering
Experiments
Setup
Outcomes
Concluding Remarks and Outlook
References
Topic Graph Based Non-negative Matrix Factorization for Transfer Learning
Introduction
Topic Graph based NMF for Transfer Learning
Non-negative Matrix Factorization
Topic Graph
Overview
Topic Graph based NMF for Transfer Learning
The Algorithm
Regularization via Pairwise Relation in the Target Domain
Evaluations
Experimental Settings
Evaluation on Real-World Datasets
Discussions
Concluding Remarks
References
Compression and Learning in Linear Regression
Introduction
Minimum Description Length.
Regularized Linear Regression vs. Compressive Linear Regression
Methods
Coding of Integers
Coding of Rationals within a Real Line Interval
Spherical Coding of a Signed Integer Sequence
MDL for Linear Regression
Results
Conclusion
References
Data Mining
The Impact of Triangular Inequality Violations on Medoid-Based Clustering
Introduction
Dissimilarity Spaces and Metricity
Rectifiers
Impact of TI Violations on Clustering
A Quality Measure for Clusterings
Experimental Results
Conclusions and Future Work
References
Batch Weighted Ensemble for Mining Data Streams with Concept Drift
Introduction
Related Works
Batch Weighted Ensemble Framework
Experiments
Discussion of Results and Final Remarks
References
A Generic Approach for Modeling and Mining n-ary Patterns
Introduction
Definitions and First Examples
Local Patterns
N-ary Patterns
Motivating Example
Related Work
Modeling and Mining n-ary Queries Using CP
Examples of n-ary Queries
Soving n-ary Queries Using CP
Experiments
Conclusion and Future Works
References
Neighborhood Based Clustering Method for Arbitrary Shaped Clusters
Introduction
Proposed Clustering Method
Performance Evaluations
Synthetic Datasets
RealWorld Datasets
Conclusions
References
FAST Sequence Mining Based on Sparse Id-Lists
Introduction
Problem Definition
Algorithm
Data Structure: Sparse Id-List
Support Counting for Item and Itemset Based on Sparse Id-List
Support Counting for Sequence Based on Sparse Id-List
Experiments
Performance Comparison
Memory Usage
Conclusions
References
From Connected Frequent Graphs to Unconnected Frequent Graphs
Introduction
Basic Notions
From Connected to Unconnected
Filtering Based on Connected Frequent Graphs Lattice
The UFC Algorithm
Reuse of UGM Optimizations
Experiments
Conclusions
References
Distributed Classification for Pocket Data Mining
Introduction
Related Work
PDM: The Pocket Data Mining Architecture
Implementation and Evaluation
Experimental Setup
Distributed Hoeffding Trees
Distributed Naive Bayes
Conclusions
References
K-Means Based Approaches to Clustering Nodes in Annotated Graphs
Introduction
Clustering
Related Work
Background Definitions
K-Means with the Hybrid Similarity Measure
K-medoids
K-means-NAM: K-means with Neighbor Annotation Means
K-means-NAMA: K-means-NAM Efficiently Approximated
Experimental Results
Experimental Setup
K-means-NAM vs K-means-NAMA
Quality Improvement due to the Hybrid Similarity Measures
Conclusion
References
Pairwise Constraint Propagation for Graph-Based Semi-supervised Clustering
Introduction
Semi-Supervised Clustering
Preliminaries
Problem Setting
Pairwise Constraint Propagation over Graph
Graph-Based Semi-supervised Clustering
Weight Modification via Cannot-Links
Regularization via Cannot-Links
Evaluations
Experimental Settings
Evaluation of Regularization Based on Cannot-Links
Evaluation on Real World Datasets
Concluding Remarks
References
Mining in Databases and Warehouses
Space-Time Roll-up and Drill-down into Geo-Trend Stream Cubes
Introduction
Basic Concepts and Problem Definition
Geo-Trend Stream Cube
A Case Study
Conclusions
References
Data Access Paths in Processing of Sets of Frequent Itemset Queries
Introduction
Multiple-Query Optimization for Frequent Itemset Queries
Basic Definitions and Problem Statement
Apriori
Review of Existing Methods
Sequential Execution
Common Counting
Common Candidate Tree
Mine Merge
Data Access Paths in Frequent Itemset Query Set Processing
Data Structures and Access Paths
Implementation of Compared Methods
Theoretical Cost Analysis
Experimental Results
Conclusion
References
Injecting Domain Knowledge into RDBMS - Compression of Alphanumeric Data Attributes
Introduction
Starting Point
Challenges
Ideas
Implementation
Experiments
Conclusions
References
Text Mining
Extracting Conceptual Feature Structures from Text
Introduction
The Approach
Generative Ontologies and Conceptual Feature Structures
Ontology-Based Concept Extraction
Phase 1: Annotation
Phase 2: Generation
A Unified Lexical Resource
VerbNet
NOMLEX and NOMLEX-Plus
Unifying Lexical Resources
Applying the Unified Ressource
Conclusions and Future Work
References
Semantically-Guided Clustering of Text Documents via Frequent Subgraphs Discovery
Introduction
Background
System Overview
Candidate Subgraph Pruning Using Gaussian Minimum Support
Semantically-Guided Candidate Subgraph Generation
Clustering and Evaluation
Experimental Results and Conclusions
Performance and Accuracy Analysis of the Subgraph Discovery Process
Conclusions
References
A Taxonomic Generalization Technique for Natural Language Processing
Introduction
Background
Taxonomic Generalization and Coverage
Evaluation
Conclusions
References
Fr-ONT: An Algorithm for Frequent Concept Mining with Formal Ontologies
Introduction
Preliminaries
Representation and Inference
Refinement Operators for DL
The Task of Frequent Concept Mining
An Algorithm for Frequent Concept Mining
Canonical Form for EL++ Concepts
Refinement Operator
Searching Pattern Space
Implementation
Conclusions and Future Work
References
Evaluation of Feature Combination Approaches for Text Categorisation
Introduction
Related Work
Feature Selection Methods
Combination of Feature Selection Methods
Compatibility between Methods
Fitness of Individual Methods
Correlations of Individual Methods
Actual Combination Techniques
Experiments
Individual Pair-Wise Correlations
Conclusions and Future Work
References
Towards Automatic Acquisition of a Fully Sense Tagged Corpus for Persian
Introduction
Related Work
Creating the Sense Tagged Corpus
Evaluation
Conclusions and Future Work
References
Theoretical Issues and Applications of Intelligent Web
Extracting Product Descriptions from Polish E-Commerce Websites Using Classification and Clustering
Introduction
Related Work
Algorithm
Experimental Results
Final Notes
References
Cut-Free ExpTime Tableaux for Checking Satisfiability of a Knowledge Base in the Description Logic $ALCI$
Introduction
Notation and Semantics of ALCI
A Tableau Calculus for ALCI
Conclusions
References
SWRL Rules Plan Encoding with OWL-S Composite Services
Introduction
Background
Encoding the SWRL Plan with OWL-S Constructs
The Procedure to Build the OWL-S Constructs Tree
Example
Related Work
Conclusions and Future Work
References
Detecting Web Crawlers from Web Server Access Logs with Data Mining Classifiers
Introduction
Related Work
Dataset Preparation
Session Identification
Features
Dataset Labelling
Experimental Design
Web Server Access Logs
Classification Algorithms
Performance Metrics
Classification Results
Experiment 1 Results
Experiment 2 Results
Conclusion and Final Remarks
References
To Diversify or Not to Diversify Entity Summaries on RDF Knowledge Graphs?
Introduction
Problem Formulation and Baseline Algorithm (PRECIS)
Diversified Entity Summarisation on RDF-Graphs (DIVERSUM)
Evaluation Experiment
Results and Discussion
Conclusions and Further Work
References
Improving the Accuracy of Similarity Measures by Using Link Information
Introduction
Problem Setting
Annotated Graphs
Semantic and Observed Similarity
Similarity Approximations
Similarity Measures
Content-Based, Contextual, and Combined similarity
Intuitive Motivation for Hybrid Similarity
Analysis of Hybrid Similarity
Experiments with Synthetic Data
The Synthetic Data Set
Clustering Methods
Results
Results on Real Data
Related Work
Conclusion
References
Application of Intelligent Systems in Sound Processing
Repetition and Rhythmicity Based Assessment Model for Chat Conversations
Introduction
Functions of Repetition
Extracted Information
Validation
Verification of the Model
Conclusion and Further Work
References
Emotion Based Music Visualization System
Introduction
Previous Work
System Construction
Method of Creating Spatial Figures
Figure Parameters
Unchanging Figure Parameters
Figure Parameters Modified According to the Detected Emotion
Tester Questionnaires
The Experiment Results
Clustering and Searching for User Profiles
Group Characteristics
Profile-Dependent Visualization
Conclusion
References
Notes on Automatic Music Conversions
Introduction
Syntactical Structuring
Printed Music Notation
Braille Music
Semantics
Semantics of Printed Music Notation
Semantics of Braille Music
Conversions
Conclusions
References
All That Jazz in the Random Forest
Introduction
FeatureVector
Audio Data
Random Forests
Methodology of RF Training in the Experiments
Experiments and Results
Summary and Conclusions
References
Intelligent Applications in Biology and Medicine
Selection of the Optimal Microelectrode during DBS Surgery in Parkinson's Patients
Initial Signal Analysis
Removal of Low Frequency Components
Spike Shape Retention
Spike Detection
Derivative Approach
Amplitude Approach
Comparison of Approaches
Spike Clustering
Clustering Using PCA over Spike Amplitude
Clustering Using PCA over Wavelet Decomposition
Clustering Summary
Power Spectrum Analysis
Creating the Temporary Signal
Extracting the Power Spectrum
Power Analysis
Usefulness of Cumulative Power
Conclusions and Acknowledgement
References
Biometric System for Person Recognition Using Gait
Introduction
The Biometric System Using Human Gait
Ground Reaction Force and Center of Pressure
Feature Extraction
Applying of the Neural Networks
Results
Experimental Population
Recognition Accuracy
Conclusions
References
minedICE: A Knowledge Discovery Platform for Neurophysiological Artificial Intelligence
Introduction
minedICE Architecture
Experiments
Conclusion and Future Work
References
Fuzzy Sets Theory and Applications
On Different Types of Fuzzy Skylines
Introduction
Reminder about Skyline Queries
Different Types of Fuzzy Skylines
Refining the Skyline
Making the Skyline More Flexible
Simplifying the Skyline
Dealing with Uncertain Data
Dealing with Incomplete Contextual Preferences
Conclusion
References
On Database Queries Involving Inferred Fuzzy Predicates
Introduction
Reminder about Fuzzy Sets and Fuzzy Queries
Basic Notions about Fuzzy Sets
About SQLf
Inferred Fuzzy Predicates: A First Approach
Presentation of the Approach by Koyuncu
Critical Discussion
A Fuzzy-Reasoning-Based Approach
Reminder about Fuzzy Control
Computation of the Final Degree
Implementation Aspects
Conclusion
References
PMAFC: A New Probabilistic Memetic Algorithm Based Fuzzy Clustering
Introduction
A Novel Probabilistic Memetic Algorithm Based Fuzzy Clustering
Representation of String And Population Initialization
Computation of Objective Function
Recombination
Opposite Based Local Search
Other Processes
Selection
Termination Criterion
Experimental Results
Synthetic Data Sets
Real Life Data Sets
Input Parameters And Performance Metric
Results
Test for Statistical Significance
Conclusion
References
Intelligent Systems, Tools and Applications
An Approach to Intelligent Interactive Social Network Geo-Mapping
Introduction and Related Work
Object Evaluation
General Object Significance
Personal Object Significance
Collaborative Object Significance
Content Visualization
Real-time Visualization of Social Network Dynamics
Evaluation
Conclusion
References
Semantics of Calendar Adverbials for Information Retrieval
Introduction
State of the Art
From Calendar Expressions to Calendar Intervals
Functional Representation
Referential Representation
Toward a Heuristic to Calculate Calendar Expressions Relevance
Experimentation
Conclusion
References
Concentric Time: Enabling Context + Focus Visual Analysis of Architectural Changes
Introduction
Research Background
The Concentric Time Visualisation: Principles, Implementation
Evaluation, Limitations, Perspectives
Conclusion
References
Analysis of Synergetic Aerodynamic Process by Means of Locally Asymptotic Estimation Derived from Telemetry Data
Introduction
The Algorithm for Derivation of Locally Asymptotic Estimation of Topological Instability at Changing Dimensionality
The Scheme of Numerical Simulations of Aerodynamic Measurement for Onboard Equipment
Numerical Simulations with Telemetry Data
Conclusions
References
Landmark Detection for Autonomous Spacecraft Landing on Mars
Introduction
Absolute Position Estimation Algorithm
Landmarks Extraction
Homogeneity Analysis
Algorithm Evaluation
Simulated Landing Scenario
Analysis on Mars Images
Conclusions
References
Precise and Computationally Efficient Nonlinear Predictive Control Based on Neural Wiener Models
Introduction
Model Predictive Control Algorithms
Neural Wiener Models
MPC-NPLPT Algorithm with Neural Wiener Models
Quadratic Programming MPC-NPLPT Optimisation Problem
Implementation Details
Simulation Results
Conclusions
References
Adaptive Immunization in Dynamic Networks
Introduction
Problem Statements
An Adaptive AOC-Based Immunization Strategy
Experiments
The Structures of Experimental Email Networks
The Static Email Networks
The Dynamic Email Networks
Conclusion
References
A Memetic Algorithm for a Tour Planning in the Selective Travelling Salesman Problem on a Road Network
Introduction
Problem Definition
The MA
Experimental Results
Conclusions
References
Application of DRSA-ANN Classifier in Computational Stylistics
Introduction
Computational Stylistics
Classification with ANN
Analysis of Characteristic Features Based on Relative Reducts
Experiments Performed
Conclusions
References
Investigating the Effectiveness of Thesaurus Generated Using Tolerance Rough Set Model
Introduction
Basic Notions on Tolerance Rough Set Model (TRSM)
Data of the Study
Methodology
Extraction Phase
Rough Set Phase
Evaluation Phase
Analysis
ALL vs. RS
WL vs. RS
Tolerance Value
ICL list vs. Lexicon
Conclusion
References
Contest on Music Information Retrieval
Report of the ISMIS 2011 Contest: Music Information Retrieval
Introduction
Task 1: Music Genres Recognition
Database and Parametrization Methods
Database Verification
Task 2: Music Instruments Recognition
Data
Solutions and Evaluation
References
High-Performance Music Information Retrieval System for Song Genre Classification
Introduction
Dataset Properties
Method Overview
Error Correcting Output Coding (ECOC)
Music Genre Classification System
Iterative Semi-supervised Learning
Multi-resolution Clustering
Iterative Relabelling Scheme
Experimental Results
Conclusions
References
Multi-label Learning Approaches for Music Instrument Recognition
Introduction
The Data
The Training Sets
The Test Set
Features
Investigation of Multi-label Learning Methods
The Solution that Ranked First
Engineering the Input
Base Classifier
Informed Ranking
Engineering the Output
The Solution that Ranked Second
Engineering the Input
Learning
Engineering the Output
Conclusions
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Foundations of Intelligent Systems

Description

More details

Other editions

Additional editions

Content

System requirements