
Artificial Intelligence and Soft Computing
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 140 revised full papers presented were carefully reviewed and selected from 242 submissions. The papers included in the first volume are organized in the following three parts: neural networks and their applications; evolutionary algorithms and their applications; and pattern classification.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents - Part I
- Contents - Part II
- Neural Networks and Their Applications
- Three-Dimensional Model of Signal Processing in the Presynaptic Bouton of the Neuron
- 1 Introduction
- 2 Motivations
- 3 The Model
- 4 Simulations
- 5 Results
- 6 Concluding Remarks
- References
- The Parallel Modification to the Levenberg-Marquardt Algorithm
- 1 Introduction
- 2 The Classic Levenbert-Marquardt Algorithm
- 3 Parallel Modification
- 4 Results
- 4.1 Approximating y = 4x(1 - x) Function
- 4.2 Approximating y = sinx logx Function
- 5 Conclusion
- References
- On the Global Convergence of the Parzen-Based Generalized Regression Neural Networks Applied to Streaming Data
- 1 Introduction
- 2 Algorithm
- 3 Global Convergence of Algorithm (4)
- 4 Experimental Results
- 5 Conclusions
- References
- Modelling Speaker Variability Using Covariance Learning
- 1 Introduction
- 2 Model Formulation
- 3 Model Implementation
- 3.1 PCA Implementation
- 3.2 SOM Implementation
- 4 Covariance Learning
- 5 Results
- 5.1 Overall Average Analysis
- 5.2 Principal Component Visualisation
- 5.3 SOM Covariance Visualisation
- 6 Conclusion
- References
- A Neural Network Model with Bidirectional Whitening
- 1 Introduction
- 2 Multilayer Perceptron and Natural Gradient Descent
- 2.1 Multilayer Perceptron
- 2.2 Natural Gradient Method
- 2.3 Approximation of the Fisher Information Matrix
- 3 Whitened Neural Networks
- 3.1 Natural Gradient Descent by Whitening
- 3.2 Extension of Whitening
- 4 Numerical Experiment
- 5 Discussion
- References
- Block Matching Based Obstacle Avoidance for Unmanned Aerial Vehicle
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Video Camera Calibration
- 2.2 Block Match Algorithm
- 2.3 Semi-Global Block Match (SGBM) Algorithm
- 3 Design of UAV with Obstacle Avoidance System
- 3.1 Hardware
- 3.2 Software
- 4 Experimental Validation of Obstacle Avoidance System
- 4.1 Experimental Setting
- 4.2 Results
- 5 Conclusion
- Acknowledgements
- References
- Prototype-Based Kernels for Extreme Learning Machines and Radial Basis Function Networks
- 1 Introduction
- 2 Prototype-Based Kernels for Extreme Learning Machines
- 3 Comparison of New Algorithm with Others
- 4 Summary
- References
- Supervised Neural Network Learning with an Environment Adapted Supervision Based on Motivation Learning Factors
- 1 Introduction
- 2 Limitations of the Supervised Learning Algorithms
- 3 Environment Based Motivated Learning Factors
- 4 Environment Adapted Supervision of Neural Network
- 5 Experiments Applied to a Robot in a Certain Environment
- 6 Adaptive Knowledge-Based Learning
- 7 Conclusions and Remarks
- References
- Autoassociative Signature Authentication Based on Recurrent Neural Network
- 1 Introduction
- 2 Autoassociative Recurrent Neural Network Authentication (ARNN)
- 2.1 Normalization and Feature Extraction
- 2.2 Reference Modeling
- 3 Experimental Results
- 3.1 Experimental Conditions
- 3.2 Authentication Experiment
- 4 Conclusion
- References
- American Sign Language Fingerspelling Recognition Using Wide Residual Networks
- 1 Introduction
- 2 Related Work
- 3 Problem Description
- 4 Applied Deep Learning Techniques
- 5 Solution Description
- 6 Experiments
- 7 Conclusions and Future Work
- References
- Neural Networks Saturation Reduction
- 1 Introduction
- 2 Neural Network Saturation
- 2.1 Neuron Saturation Detection
- 2.2 Changing Working Space
- 3 Saturation Reduction - Example
- 4 Experimental Results
- 5 Conclusions
- References
- Learning and Convergence of the Normalized Radial Basis Functions Networks
- 1 Introduction
- 2 Nonlinear Function Learning
- 3 Recursive Classification Rules
- 4 Consistency and Rates of Convergence
- 4.1 Convergence Results
- 4.2 Outlines of Proofs
- 5 Conclusions
- References
- Porous Silica-Based Optoelectronic Elements as Interconnection Weights in Molecular Neural Networks
- 1 Introduction
- 2 Experimental Part
- 3 Conclusion
- References
- Data Dependent Adaptive Prediction and Classification of Video Sequences
- 1 Introduction
- 2 Description of the APCN Architecture
- 3 Algorithm
- 3.1 Data-Dependent Pooling
- 3.2 Cost Function
- 4 Simulation Setup and Results
- 4.1 Synthetic Data Set Generation
- 4.2 Prediction Using Data Dependent Pooling
- 4.3 Adaptability of the Network
- 5 Conclusion
- References
- Multi-step Time Series Forecasting of Electric Load Using Machine Learning Models
- 1 Introduction
- 2 Time Series Forecasting Strategies
- 2.1 Single-Step Forecasting
- 2.2 Multi-step Forecasting
- 3 ARIMA Based Time Series Forecasting
- 4 LSTM Based Time Series Forecasting
- 5 Experiments and Results
- 5.1 Dataset
- 5.2 ARIMA Model Formulation
- 5.3 LSTM Model Formulation
- 5.4 Forecast Performance of the Models
- 5.5 Discussion
- 6 Conclusions
- References
- Deep Q-Network Using Reward Distribution
- 1 Introduction
- 2 Deep Q-Network
- 2.1 Structure
- 2.2 Learning
- 3 Deep Q-Network Using Reward Distribution
- 4 Computer Experiment Results
- 4.1 Experimental Conditions
- 4.2 Score Transition
- 4.3 Transition of Acquired Negative Reward
- 5 Conclusion
- References
- Motivated Reinforcement Learning Using Self-Developed Knowledge in Autonomous Cognitive Agent
- 1 Introduction
- 2 Robot's Reinforcement Learning Using Motivation
- 2.1 Interaction with the Surroundings
- 2.2 External Rewards and Reinforcement Learning
- 2.3 Internal Rewards and Motivation Factors
- 2.4 Motivation to Achieve the Goal
- 2.5 Deep Q-Learning
- 2.6 Motivation to Explore and Curiosity
- 2.7 Experience Replay
- 2.8 Final Algorithm Controlling the Robot's Movements
- 3 Simulation and Experimental Results
- 3.1 Virtual Environment
- 3.2 Robot Rating
- 3.3 Learning Rate
- 3.4 Neural Network Structure
- 3.5 Motivation to Explore
- 4 Conclusions and Final Remarks
- References
- Company Bankruptcy Prediction with Neural Networks
- 1 Introduction
- 2 Methodology of the Research
- 3 Experimental Results
- 4 Conclusion
- References
- Soft Patterns Reduction for RBF Network Performance Improvement
- 1 Introduction
- 2 Concept of Soft Patterns Reduction
- 2.1 Error Correction Algorithm
- 3 Experimantal Results
- 3.1 Peaks Function
- 3.2 Schwefel Function
- 3.3 Shaffer Function
- 4 Conclusions
- References
- An Embedded Classifier for Mobile Robot Localization Using Support Vector Machines and Gray-Level Co-occurrence Matrix
- 1 Introduction
- 2 Related Works
- Mobile Robots Localization and Navigation.
- Embedded SVM Classifiers.
- Embedded GLCM Feature Extractor.
- 3 Proposed Approach
- 3.1 Data Base
- 3.2 Feature Extractor and the Pattern Recognition
- 3.3 Feature Selection and Reduction
- Feature Selection Based on Correlation (CFS).
- Study on Features Complexity.
- 3.4 Selecting the Input Image Size
- 3.5 Memory Consumption
- Analytical Study.
- 4 Classifier Evaluation on an Embedded Platform
- 5 Conclusions
- References
- A New Method for Learning RBF Networks by Utilizing Singular Regions
- 1 Introduction
- 2 Background
- 2.1 RBF Networks
- 2.2 Existing Methods for Learning RBF Networks
- 2.3 Singular Regions of RBF Networks
- 3 SSF for RBF Networks
- 3.1 General Flow of RBF-SSF
- 3.2 Techniques for Making SSF Faster
- 4 Experiments
- 4.1 Experiments Using Engine Behavior Dataset
- 4.2 Experiment Using Building Energy Dataset
- 4.3 Experiment Using Parkinsons Telemonitoring Dataset
- 4.4 Findings Obtained from Experiments
- 5 Conclusion
- References
- Cyclic Reservoir Computing with FPGA Devices for Efficient Channel Equalization
- 1 Introduction
- 2 Methodology
- 2.1 FPGA Implementation of Cyclic Reservoir Systems
- 2.2 Nonlinear Channel Equalization
- 3 Results
- 4 Conclusions
- References
- Discrete Cosine Transform Spectral Pooling Layers for Convolutional Neural Networks
- 1 Introduction
- 2 Spectral Representation
- 2.1 Spectral Convolution
- 2.2 Spectral Pooling
- 3 Discrete Cosine Transform Spectral Pooling
- 4 Experiment Results
- 5 Final Remarks
- References
- Extreme Value Model for Volatility Measure in Machine Learning Ensemble
- Abstract
- 1 Introduction
- 2 Prediction Results Improvement
- 3 Volatility as Destructive Components Indicator
- 4 Practical Experiment
- 5 Conclusions
- References
- Deep Networks with RBF Layers to Prevent Adversarial Examples
- 1 Introduction
- 2 Adversarial Examples and Related Work
- 3 Deep Networks with RBF Layers
- 4 Experimental Results
- 5 Conclusion
- References
- Application of Reinforcement Learning to Stacked Autoencoder Deep Network Architecture Optimization
- 1 Introduction
- 2 Stacked Autoencoder Deep Network
- 3 Reinforcement Learning
- 3.1 Introduction
- 3.2 Q(0)-learning
- 4 Proposed Approach
- 5 Empirical Results and Discussion
- 6 Conclusions
- References
- Evolutionary Algorithms and Their Applications
- An Optimization Algorithm Based on Multi-Dynamic Schema of Chromosomes
- 1 Introduction
- 2 Methodology
- 2.1 Dissimilarity Operator
- 2.2 Similarity Operator
- 2.3 Dynamic Schema Operator
- 2.4 Dynamic Dissimilarity Operator
- 3 The MDSDSC Algorithm
- 4 Experimental Results
- 5 Conclusion
- References
- Eight Bio-inspired Algorithms Evaluated for Solving Optimization Problems
- 1 Introduction
- 2 Bio-inspired Algorithms
- 3 Automatic Parameter Tuning
- 4 Optimization Problems
- 5 Performance Analysis
- 6 Statistical Analysis
- 7 Convergence Analysis
- 8 Conclusion
- References
- Robotic Flow Shop Scheduling with Parallel Machines and No-Wait Constraints in an Aluminium Anodising Plant with the CMAES Algorithm
- 1 Introduction
- 2 Robotic Flow Shop Problems
- 3 CMAES for Robotic Flow Shop Scheduling
- 3.1 Background on CMAES
- 3.2 The CMAES-Based Robotic Flow Shop Scheduling Algorithm
- 4 Empirical Evaluation
- 5 Using the CMAES Algorithm for Business Decisions
- 6 Conclusion
- References
- Migration Model of Adaptive Differential Evolution Applied to Real-World Problems
- 1 Introduction
- 2 Adaptive Variants of Differential Evolution
- 3 Migration Model of DE
- 4 Experimental Settings
- 5 Results and Discussion
- 6 Conclusion
- References
- Comparative Analysis Between Particle Swarm Optimization Algorithms Applied to Price-Based Demand Response
- 1 Introduction
- 2 Demand Response and Load Scheduling
- 3 Autonomous and Distributed Modelling
- 4 Particle Swarm Optimization
- 4.1 Classical and Linear Decreasing Weight PSO
- 4.2 Proposed PSO Based on Stochastic Population Mechanism
- 5 Results and Discussions
- References
- Visualizing the Optimization Process for Multi-objective Optimization Problems
- 1 Introduction
- 2 Background
- 2.1 Visualization Techniques
- 2.2 Low-dimensionality Visualization Techniques
- 3 Proposed Approach
- 3.1 Scatterplot
- 3.2 Animation
- 3.3 Visualizing the State of the Algorithm
- 4 Experimental Setup and Results
- 4.1 Experiment I
- 4.2 Experiment II
- 5 Conclusion
- References
- Comparison of Constraint Handling Approaches in Multi-objective Optimization
- 1 Introduction
- 2 Background
- 3 Experimental Setup
- 3.1 Algorithms
- 3.2 Performance Measures
- 3.3 Implementation
- 3.4 Procedure
- 4 Results
- 4.1 GD
- 4.2 IGD
- 4.3 HV
- 4.4 Spread
- 5 Conclusion
- References
- Genetic Programming for the Classification of Levels of Mammographic Density
- 1 Introduction
- 2 Previous Work
- 3 Methodology
- 3.1 Thresholding
- 3.2 Feature Extractions
- 3.3 Genetic Programming
- 4 Experimental Results
- 5 Conclusions
- References
- Feature Selection Using Differential Evolution for Unsupervised Image Clustering
- 1 Introduction
- 2 Theoretical Aspects
- 2.1 Feature Selection
- 2.2 Differential Evolution
- 2.3 Unsupervised Cluster Evaluation Metrics
- 3 Method
- 3.1 Overview
- 3.2 Preprocessing
- 3.3 Feature Extraction and Selection Setup
- 3.4 Clustering and Evaluation
- 4 Experimental Results and Analysis
- 4.1 Dataset Description
- 4.2 Evaluation Measures
- 4.3 Cluster Analysis
- 5 Conclusion
- References
- A Study on Solving Single Stage Batch Process Scheduling Problems with an Evolutionary Algorithm Featuring Bacterial Mutations
- 1 Introduction and Literature Review
- 2 Problem Definition
- 3 The Proposed Approach
- 3.1 Representation of Schedules and the Mutation
- 3.2 Fitness Function
- 3.3 Fine Tuning
- 4 Computational Results
- 5 Concluding Remarks
- References
- -1Observation of Unbounded Novelty in Evolutionary Algorithms is Unknowable
- 1 Artificial Life and Endless Novelty
- 1.1 Identifying Unlimited Novelty
- 2 Prefix Free Complexity and Algorithmic Information
- 2.1 Defining the Set Generating Program
- 2.2 Kolmogorov Complexity is not Computable
- 2.3 Chaitin's Incompleteness Theorem
- 3 Limits on Identifying Novelty
- 3.1 Definitions of Novelty
- 3.2 Commonalities of Novelty
- 3.3 Necessary Condition for Novelty
- 3.4 Unbounded Novelty Detection is Nonalgorithmic
- 4 Conclusion
- References
- Multi-swarm Optimization Algorithm Based on Firefly and Particle Swarm Optimization Techniques
- 1 Introduction
- 2 Particle Swarm Optimization
- 3 Firefly Algorithm
- 3.1 A Canonical Version of Firefly Algorithm
- 3.2 Firefly Particle Swarm Optimization
- 3.3 Proposed Hybrid Algorithm
- 4 Experimental Setup
- 5 Results
- 6 Conclusion
- References
- New Running Technique for the Bison Algorithm
- 1 Introduction
- 2 Bison Algorithm
- 2.1 Bison Algorithm Definition
- Swarming Behavior.
- Running Behavior.
- Proposition of the New Running Behavior.
- Bison Algorithm with the New Running Behavior.
- Parameters and Out of Bounds Behavior.
- 3 Experiments and Results
- 4 Discussion
- 5 Conclusion
- References
- Evolutionary Design and Training of Artificial Neural Networks
- 1 Introduction
- 2 Used Methods and Algorithms
- 2.1 Self-Organizing Migrating Algorithm
- 2.2 Evolution Strategies
- 3 Experiment Design
- 3.1 Synthesis Using Analytic Programming
- 3.2 Synthesis by Means of Evolutionary Algorithm
- 3.3 Synthesis Using Network Growth Model
- 4 Simulations and Results
- 4.1 Algorithm Settings
- 4.2 Results
- 4.3 Sample Output
- 5 Conclusion
- References
- Obtaining Pareto Front in Instance Selection with Ensembles and Populations
- 1 Introduction
- 2 Bagging Ensembles of DROP5 Instance Selection Algorithms
- 3 NSGA-II Based Evolutionary Instance Selection
- 4 Experiments and Results
- 5 Conclusions
- References
- Negative Space-Based Population Initialization Algorithm (NSPIA)
- 1 Introduction
- 2 Description of Proposed Initialization Algorithm
- 3 Simulation Results
- 4 Conclusions
- References
- Deriving Functions for Pareto Optimal Fronts Using Genetic Programming
- 1 Introduction
- 2 Background
- 2.1 Approaches
- 2.2 Genome Representation
- 3 Algorithm
- 3.1 Initialization
- 3.2 One Iteration
- 3.3 Selection Operator
- 3.4 Crossover
- 3.5 Mutation
- 3.6 Stopping Conditions
- 3.7 Clean Up
- 3.8 New Individuals
- 3.9 Fitness Calculation
- 4 Summation Operator
- 4.1 Start and End Value
- 4.2 Counter Variable
- 4.3 Value Calculation
- 5 Results
- 6 Conclusion and Future Work
- References
- Identifying an Emotional State from Body Movements Using Genetic-Based Algorithms
- Abstract
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Feature Extraction
- 3.2 Machine Learning Classification Methods
- 3.3 Genetic Algorithm
- 4 Experimental Results
- 4.1 Database Description
- 4.2 Classifiers Parameter Tuning
- 4.3 Classification Results
- 5 Conclusions and Future Work
- Acknowledgements
- References
- Particle Swarm Optimization with Single Particle Repulsivity for Multi-modal Optimization
- 1 Introduction
- 2 Particle Swarm Optimization Algorithm
- 3 Proposed Modification
- 4 Experiment
- 5 Results
- 5.1 Convergence in Higher Dimensions
- 6 Results Discussion
- 7 Conclusion
- References
- Hybrid Evolutionary System to Solve Optimization Problems
- 1 Introduction
- 2 The Proposed Hybrid Evolutionary System
- 3 Problem Formulation
- 4 Computational Experiment
- 5 Final Remarks
- References
- Horizontal Gene Transfer as a Method of Increasing Variability in Genetic Algorithms
- 1 Introduction
- 2 Proposed Modification
- 3 Test Problems
- 3.1 The Ackley Function
- 3.2 The Rosenbrock Function
- 3.3 The Schwefel Function
- 4 Numerical Results
- 5 Summary
- References
- Evolutionary Induction of Classification Trees on Spark
- 1 Introduction
- 1.1 Spark
- 1.2 Related Works
- 2 Global Decision Tree Induction Framework
- 3 Spark-Accelerated Evolutionary Induction
- 4 Experimental Validation
- 5 Conclusion
- References
- How Unconventional Chaotic Pseudo-Random Generators Influence Population Diversity in Differential Evolution
- 1 Introduction
- 2 Motivation and Related Research
- 3 Chaotic Systems for CPRNGs
- 4 The Concept of ChaosDE with Discrete Chaotic System as Driving CPRNG
- 5 Differential Evolution
- 5.1 The jDE Algorithm
- 6 Experiment Design
- 7 Results
- 8 Conclusions
- References
- An Adaptive Individual Inertia Weight Based on Best, Worst and Individual Particle Performances for the PSO Algorithm
- 1 Introduction
- 2 Inertia Weight Mechanisms
- 3 Proposed Adaptive Inertia Weight Mechanism
- 4 Experimental Setup
- 5 Experimental Results and Discussions
- 6 Conclusions
- References
- A Mathematical Model and a Firefly Algorithm for an Extended Flexible Job Shop Problem with Availability Constraints
- 1 Introduction
- 2 MILP Model
- 3 Firefly Algorithm
- 3.1 Variations of Light Intensity and Attractiveness
- 3.2 Firefly Representation for the FJSP
- 3.3 Discrete Firefly Algorithm for the FJSP
- 3.4 Distance
- 3.5 Attraction and Movement
- 4 Numerical Results
- 4.1 Fattahi Instances
- 4.2 FJSP-FCR Instances
- 4.3 Brandimarte Instances
- 4.4 Kacem Instances
- 5 Conclusion
- References
- On the Prolonged Exploration of Distance Based Parameter Adaptation in SHADE
- 1 Introduction
- 2 From DE to Db_SHADE
- 2.1 SHADE
- 2.2 Db_SHADE
- 3 Experimental Settings
- 3.1 SHADE and Db_SHADE Settings
- 3.2 Cluster Analysis
- 4 Results and Discussion
- 5 Conclusion
- References
- Investigating the Impact of Road Roughness on Routing Performance: An Evolutionary Algorithm Approach
- 1 Introduction
- 2 Literature Review
- 2.1 Vehicle Routing
- 2.2 Vehicle Operating Costs
- 2.3 Solution Strategies
- 3 Selected Algorithms
- 3.1 Greedy Heuristic
- 3.2 Simulated Annealing
- 3.3 CMA-ES
- 4 Algorithm Evaluation
- 5 Conclusion
- References
- Pattern Classification
- Integration Base Classifiers in Geometry Space by Harmonic Mean
- 1 Introduction
- 2 Basic Concept
- 3 Proposed Method
- 4 Experimental Studies
- 5 Conclusion
- References
- Similarity of Mobile Users Based on Sparse Location History
- Abstract
- 1 Introduction
- 2 Sparse Location Histograms
- 2.1 Locations, Distance and Places
- 2.2 Histogram Matching
- 3 Experiments
- 3.1 Data Extraction
- 3.2 Test Setup and Results
- 4 Conclusion
- References
- Medoid-Shift for Noise Removal to Improve Clustering
- Abstract
- 1 Introduction
- 2 Existing Work and Their Limitations
- 3 Medoid-Shift Noise Removal
- 3.1 Method Description
- 3.2 Mean or Median?
- 4 Experiments
- 4.1 Datasets
- 4.2 Noise Models
- 4.3 Results
- 5 Conclusions
- References
- Application of the Bag-of-Words Algorithm in Classification the Quality of Sales Leads
- Abstract
- 1 Introduction
- 2 Bag-of-Words Algorithm
- 3 Description of the Presented Method
- 4 Experimental Research
- 5 Conclusions
- References
- Probabilistic Feature Selection in Machine Learning
- 1 Introduction
- 2 Methodology
- 2.1 Architecture
- 2.2 Proposed Mathematical Foundation
- 2.3 Algorithm
- 3 Validation
- 4 Discussion
- References
- Boost Multi-class sLDA Model for Text Classification
- 1 Introduction
- 2 Dimensionality Reduction for Text Classification
- 3 Multi-class sLDA Model
- 3.1 Multi-class sLDA Computation
- 3.2 Approximate Inference
- 3.3 Estimation
- 3.4 Prediction
- 4 Boost Multi-class sLDA
- 4.1 Ensemble
- 4.2 AdaBoost for Multi-class sLDA
- 4.3 Changes to Estimation of Parameters
- 5 Empirical Study
- 5.1 Multi-class sLDA for Various Number of Topics
- 5.2 Boost Multi-class sLDA for Varying Number of Topics
- 5.3 Boost Multi-class sLDA for Best Number of Topics
- 6 Summary
- References
- Multi-level Aggregation in Face Recognition
- 1 Introduction
- 2 Description of LBP Algorithm and Possible Stages of Data Aggregation
- 2.1 Aggregation of Face Features and Color Channels
- 3 Experimental Studies
- 3.1 Modification of LBP Algorithm Based on Aggregation of Data Describing Variations
- 3.2 Aggregation of Different Parts of the Face and Different Channels
- 4 Conclusions and Future Studies
- References
- Direct Incorporation of L1-Regularization into Generalized Matrix Learning Vector Quantization
- 1 Introduction
- 2 Related Work
- 3 Method
- 4 Results
- 4.1 Artificial Data
- 4.2 Audio Emotion Recognition
- 5 Conclusion
- References
- Classifiers for Matrix Normal Images: Derivation and Testing
- 1 Introduction
- 2 Problem Statement
- 3 Performance Evaluation by Monte Carlo Experiments
- 4 Testing MCL on Images of Flames of a Gas Burner
- 5 Recommendations and Conclusions
- References
- Random Projection for k-means Clustering
- Abstract
- 1 Introduction
- 2 Projection-Based Initialization
- 2.1 One-Dimensional Projections
- 2.2 Random Projection in Higher Dimensions
- 2.3 Random Projection
- 2.4 Furthest Point Projection
- 2.5 Repeated K-means
- 3 Experiments
- 4 Conclusions
- References
- Modified Relational Mountain Clustering Method
- Abstract
- 1 Introduction
- 2 Mountain Clustering Methods
- 2.1 Mountain Method
- 2.2 Modified Mountain Clustering Algorithm
- 3 Modified Relational Mountain Clustering Method
- 3.1 Relational Mountain Clustering Method
- 3.2 The Proposed Modified Relational Mountain Clustering Method
- 4 Numerical Examples and Comparisons
- 5 Conclusions
- References
- Relative Stability of Random Projection-Based Image Classification
- 1 Introduction
- 2 Random Projections
- 3 An Image and Its Classification
- 3.1 Data Used for Experiments
- 3.2 Stability of the Classifier with Respect to RP
- 4 Random Projections of the Whole Image Treated as a Vector
- 5 Projections of Images Partitioned into Blocks
- 5.1 Block-Based PCA
- 6 Conclusions
- References
- Cost Reduction in Mutation Testing with Bytecode-Level Mutants Classification
- 1 Introduction
- 2 Classification of Mutants
- 2.1 Mutants Generation
- 2.2 Classification Process
- 3 Experimental Results
- 4 Conclusions
- References
- Probabilistic Learning Vector Quantization with Cross-Entropy for Probabilistic Class Assignments in Classification Learning
- 1 Introduction
- 2 Cross-Entropy in Learning in LVQ
- 2.1 Standard Soft Learning Vector Quantization (SLVQ)
- 2.2 Cross-Entropy as an Information Theoretic Objective for the Probabilistic LVQ
- 3 Experiments
- 4 Conclusions
- References
- Multi-class and Cluster Evaluation Measures Based on Rényi and Tsallis Entropies and Mutual Information
- 1 Introduction
- 2 Information Theoretic Cluster/Classification Evaluation Based on Shannon Entropy
- 2.1 General Description of the Evaluation Approach
- 2.2 Numerical Realization
- 3 Information Theoretic Cluster/Classification Evaluation Based on Rényi Entropy
- 4 Information Theoretic Cluster/Classification Evaluation Based on Tsallis Entropy
- 5 Numerical Experiments
- 5.1 Artificial Illustrative Example
- 5.2 Real World Example
- 6 Conclusion
- References
- Verification of Results in the Acquiring Knowledge Process Based on IBL Methodology
- 1 Introduction
- 2 Methods Used to Acquire Knowledge
- 3 Stages of Acquiring Knowledge from an Expert
- 4 Dermatological Asymmetry Measures (DAS) and Dermatological Asymmetry Measure of Shape (DASMShape)
- 5 Research and Discussion of the Results
- 6 Conclusions
- References
- A Fuzzy Measure for Recognition of Handwritten Letter Strokes
- 1 Introduction
- 2 Defining the Problem
- 3 Polynomial Representation of the Stroke
- 3.1 Methods of Comparison
- 3.2 Window Normalization
- 3.3 Component Functions
- 4 Tests
- 4.1 Quality Measure
- 4.2 Results
- 5 Conclusions
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.