Advances in Neural Networks - ISNN 2012

Name: Advances in Neural Networks - ISNN 2012 | 9th International Symposium on Neural Networks, ISNN 2012, Shenyang, China, July 11-14, 2012. Proceedings, Part I
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

9th International Symposium on Neural Networks, ISNN 2012, Shenyang, China, July 11-14, 2012. Proceedings, Part I

Jun Wang Gary G. Yen Marios M. Polycarpou(Editor)

Springer (Publisher)

Published on 23. July 2012

XXVI, 683 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-31346-2 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Title
Preface
Organization
Table of Contents
Mathematical Modeling
Attractor Neural Network Combined with Likelihood Maximization Algorithm for Boolean Factor Analysis
Introduction
Generative Model of Signals Appropriate for BFA
Likelihood Maximization (LM)
Hybrid LANNIA Method
LANNIA Application to the Genome Data Set Analysis
Discussion
References
Pruning Feedforward Neural Network Search Space Using Local Lipschitz Constants
Introduction
An FNN Is Lipschitzian
Estimating the Lipschitz Constant of an FNN
One Hidden Layer with a Single Output
Multiple Output Units and Hidden Layers
Computing Local Lipschitz Constant
Illustrative Example
Conclusions
References
Context FCM-Based Radial Basis Function Neural Networks with the Aid of Fuzzy Clustering
Introduction
Context FCM-Based p-RBF Neural Networks
Architecture of Proposed Context FCM-Based p-RBF Neural Networks
Context Fuzzy C-Means Clustering Algorithm
The Learning Method of WLSE
Experimental Results
Automobile Miles Per Gallon Dataset (MPG)
Boston Housing Dataset
Concluding Remarks
References
Modeling Spectral Data Based on Mutual Information and Kernel Extreme Learning Machines
Introduction
MI and Kernel ELM Based Modeling Approach
Feature Selection Based on Mutual Information
Nonlinear Modeling Based on Kernel ELM
Nonlinear Modeling Based on MI and Kernel ELM
Application Study
Conclusions
References
A Hierarchical Neural Network Architecture for Classification
Introduction
Hierarchical Neural Network for Classification
Simulation Analysis
Data Set Description
Simulation Procedure
Simulation Results and Analysis
Conclusions
References
Discrete-Time ZNN Algorithms for Time-Varying Quadratic Programming Subject to Time-Varying Equality Constraint
Problem Formulation and Continuous-Time ZNN Model
Discrete-Time ZNN Algorithms
Simulative and Numerical Verification
Conclusions
References
Patch Processing for Relational Learning Vector Quantization
Introduction
Prototype Based Classification
Patch Relational Generalized Learning Vector Quantization
Experiments
Conclusions
References
A Neural Network Modelfor Currency Arbitrage Detection
Introduction
The Lotka-Volterra Recurrent Neural Networks
The LV RNN Model for Currency Arbitrage Detection
Simulations
Conclusions
References
A Rank Reduced Matrix Method in Extreme Learning Machine
Introduction
Review of ELM
The Rank Reduced Matrix (MMR) Method in ELM
Performance Evaluation
Conclusions
References
Research of Dynamic Load Identification Based on Extreme Learning Machine
Introduction
Principle of Dynamic Load Identification
Brief introduction of ELM
Load Identification Based on ELM
Data Source
Identification Framework
Numerical Results
Conclusions
References
Fuzzy Relation-Based Polynomial Neural Networks Based on Hybrid Optimization
Introduction
Hybrid Optimization Algorithm
A Design of the HOFRPNN
Fuzzy Rule-Based Model
Experimental Studies
Gas Furnace Process
Automobile Miles Per Gallon (MPG) Data
Conclusions
References
Time-Varying Moore-Penrose Inverse Solving Shows Different Zhang Functions Leading to Different ZNN Models
Introduction
ZFs and ZNN Models
Convergence Characteristics
Computer Simulations
Conclusions
References
A Multi-object Segmentation Algorithm Based on Background Modeling and Region Growing
Introduction
Related Work
Multi-object Segmentation Algorithm
Experimental Results
Conclusion
References
Reflectance Estimation Using Local Regression Methods
Introduction
Regression Methods to Estimate Spectral Reflectance
Global Regression Methods
Local Regression Methods
Experimental Results
Conclusions
References
Applying a Novel Decision Rule to the Semi-supervised Clustering Method Based on One-Class SVM
Introduction
The CCOSVM Clustering Algorithm
The Proposed Method CCOSVM_NDR
Experimental Results
Conclusions
References
State Estimation of Markovian Jump Neural Networks with Mixed Time Delays
Introduction
Problem Formulation
Main Result
Conclusion
References
Lattice Boltzmann Model for Nonlinear Heat Equations
Introduction
Lattice Boltzmann Model
Equilibrium Distribution Functions and Their Higher-Order Moments
Recovery of the Macroscopic Equations
Numberical Simulation Results
Conclusion
References
A Modified One-Layer Spiking Neural Network Involves Derivative of the State Function at Firing Time
Introduction
The Modified One-Layer Spiking Neural Network
Error-Backpropagation Training Algorithm
Numerical Simulation
Conclusion
References
Modeling and Monitoring of Multimodes Process
Introduction
Modeling of Multimode Processes
Introduction of LLE
Modeling of the Multimodes Process
Monitoring of Multimode Processes
Illustration Example
Conclusion
References
Data-Based Modeling and Monitoring for Multimode Processes Using Local Tangent Space Alignment
Introduction
The Main Steps of LTSA Algorithm
Monitoring of Multimode Processes
Illustration Example
Conclusion
References
Modeling Rate-Dependent and Thermal-Drift Hysteresis through Preisach Model and Neural Network Optimization Approach
Introduction
Experimental Setup and Simulation Model
Introduction to Preisach Hysteresis Model
Off-Line Pre-identification of the Density Plane for Preisach Model
On-Line Realtime Neurodynamic Optimization
Numerical Simulation Tests and Discussions
Conclusion
References
Neurodynamics
The Neuron's Modeling Methods Based on Neurodynamics
Introduction
The Neuron's Dynamic Description
The Neuron's Modeling Methods and Procedures Based on Neurodynamics
Decision of the Involved Current Kinds of the Studied Neuron and Their Corresponding Dynamic General Equations
The Parameter Values' Decision of the Currents' Dynamic General Equations
The Neuron Model's Building, Testing and Revising
Conclusion
References
Stability Analysis of Multiple Equilibria for Recurrent Neural Networks
Introduction
Paper Preparation
Main Result
Illustrative Example
Conclusion
References
Addressing the Local Minima Problem by Output Monitoring and Modification Algorithms
Introduction
Gradient Descent Algorithms
Output Monitoring and Modification Methodology
An Extreme Error
Output Monitoring and Modification (OMM)
OMM with Reiteration (OMM-R)
Numerical Results
Application of OMM to Different Learning Algorithms
OMM with Reiteration (OMM-R)
Conclusions
References
Stability Analysis and Hopf-Type Bifurcation of a Fractional Order Hindmarsh-Rose Neuronal Model
Introduction
Preliminaries
Stability Theorems
Model Descriptions
Main Results
Local Stability
Hopf Bifurcation
Oscillation Region
Numerical Simulations
Concluding Remarks
References
Study on Decision Algorithm of Neurons' Synchronization Based on Neurodynamics
Introduction
The Neuron's Synchronization and Its Classfication
The Neuron's Dynamic Phase Function and Synchronization Decision Algorithm
Synchronization of Two Uncoupled HR Neurons
Conclusion
References
The SMC Approach to Global Synchronization of the Cellular Neural Networks with Multi-delays and Distributed Delays
Introduction
Model Description and Preliminaries
SMC Design
Conclusions
References
A Novel Feature Sparsification Method for Kernel-Based Approximate Policy Iteration
Introduction
Approximate Linear Dependence (ALD) Analysis in KLSPI
ALD Based on Relative Approximation Error for KLSPI
The Origin of the Basic Ideas
ALD Based on Relative Approximation Error in KLSPI
Experiments and Evaluations
Conclusion
References
Quasi-synchronization of Different Fractional-Order Chaotic Systems with External Perturbations and Its Application
Introduction
Preliminaries
Main Results
Numerical Simulations
References
Synchronization of Complex Interconnected Neural Networks with Adaptive Coupling
Introduction
Problem Description and Preliminaries
Main Results
Conclusions
References
Quasi-synchronization of Delayed Coupled Networks with Non-identical Discontinuous Nodes
Introduction
Model Formulation and Preliminaries
Uniform Boundedness of Complex Networks
Quasi-synchronization of Coupled Networks
Numerical Examples
Conclusions
References
Hybrid Synchronization of Two Delayed Systems with Uncertain Parameters
Introduction
Problem Description
Control Law Design
The Hybrid Synchronization of Chen and Lü Systems
Conclusion
References
Adaptive Projective Synchronization and Function Projective Synchronization of Chaotic Neural Networks with Delayed and Non-delayed Coupling
Introduction
Neural Networks Model and Preliminaries
Adaptive Projective Synchronization and Function Projective Synchronization Analysis
Adaptive Projective Synchronization Analysis
Function Projective Synchronization Analysis
Conclusions
References
Global Asymptotic Synchronization of CoupledInter connected Recurrent Neural Networks via Pinning Control
Introduction
Problem Formulation
Main Results
Conclusions
References
Mean Square Stability of Stochastic Impulsive Genetic Regulatory Networks with Mixed Time-Delays
Introduction
Model Description and Preliminaries
Main Results
An Example
References
Mesh Exponential Stability of Look-Ahead Vehicle Following System with Time Delays
Introduction
Preliminaries
Main Results
Conclusions
References
Global Dissipativity of Neural Networks with Time-Varying Delay and Leakage Delay
Introduction
Problem Formulation and Preliminaries
Main Result
Conclusions
References
Novel Results on Mesh Stability for a Class of Vehicle Following System with Time Delays
Introduction
Preliminaries
Main Results
Example
Conclusions
References
Robust Stability Analysis of Fuzzy Cohen-Grossberg Neural Networks with Mixed Time-Varying Delay
Introduction
Model Description and Preliminaries
Main Result
An Illustrative Example
Conclusion
References
Adaptive Stochastic Robust Convergence of Neutral-Type Neural Networks with Markovian Jump Parameters
Problem Description and Preliminaries
Main Result
Conclusion
References
A New Global Asymptotic Stability of Cellular Neural Network with Time-Varying Discrete and Distributed Delays
Introduction
Problem Statement
Main Result
Conclusion
References
Cognitive Neuroscience
Localizing Sources of Brain Activity Relevant to Motor Imagery Brain-Computer Interface Performance, Using Individual Head Geometry
Introduction
Methods
Experimental Protocol
Relevant Source Localization
Results
Independent Components the Most Relevant for BCI Control
Source Localization
Discussion
References
Clustering Social Networks Using Interaction Semantics and Sentics
Introduction
Related Work
Our Approach
Adding Semantics to Social Interaction
Creating the Socio-interaction Matrix
Reducing the Dimensionality of the Socio-interaction Matrix
Conclusions and Future Work
References
Ontology-Based Semantic Affective Tagging
Introduction
The Semantic Web and the Linked Data Initiative
Semantic Tagging
Semlib Project
Human Emotion Ontology
Enriching Wordnet Tags with Affective Information
Extracting Affect from Other Knowledge Bases
Conclusions
References
Dominance Detection in a Reverberated Acoustic Scenario
Introduction
Speech Enhancement Front-End
Dominance Detector
Speech Feature Extraction
Most and Least Dominant Person Estimation Based on LSTM
Experiments
Corpus Description
Acoustic Scenario
Dominance Detector Training and Evaluation Procedure
Results
Conclusion
References
Analysis of Attention Deficit Hyperactivity Disorder and Control Participants in EEG Using ICA and PCA
Introduction
Methods
Independent Component Analysis
Principal Component Analysis
Results
Experimental Setup and CPT Task
Artifacts Removal by ICA Method
EEG Channel Selection
Discussion
References
A Systematic Independent Component Analysis Approach to Extract Mismatch Negativity
Introduction
Method
Data Description
General ICA Approach to Extract Brain Signals
Systematic ICA Approach to Extract MMN
Data Processing and Analysis
Results
Conclusion
References
A Study of Sickness Induced by Perceptual Conflict in the Elderly within a 3D Virtual Store and Avoidance
Introduction
General Introduction
Sickness in VEs
Objectives
Experiment I: Effects of Exposure Situations on Sickness
Participants, Apparatus and the Virtual Store
Hypotheses
Questionnaires
Experimental Design and Procedures
Experimental Design and Procedures
A Fuzzy Warning System for Combating Sickness
System Development
Second Experiment and Result
Conclusion
References
A Co-adaptive Training Paradigm for Motor Imagery Based Brain-Computer Interface
Introduction
Experimental Setup
Subjects
The EEG Signal Recording and Preprocessing
Neurofeedback Training Paradigm
Classification Model Trained Framework
Feature Selection Based Model Training Strategy
Non-feature Selection Based Model Training Strategy
Results
Comparison of Training Performance
Off-Line Analysis for Model Training
Discussion and Conclusion
References
Learning Algorithms
Overcoming the Local-Minimum Problem in Training Multilayer Perceptrons with the NRAE Training Method
Introduction
Evaluating NRAE and Its Derivatives
Numerical Experiments
Function Approximation
Discussion
Conclusion
References
Magnified Gradient Function to Improve First-Order Gradient-Based Learning Algorithms
Introduction
Magnified Gradient Function (MGF)
Application of MGF in Fast Learning Algorithms
MGF Applied in Quickprop
MGF Applied in Rprop and iRprop
Simulation Results
Conclusions
References
Sensitivity Analysis with Cross-Validation for Feature Selection and Manifold Learning
Introduction
Cross-Validation
Comparison of Multiple Algorithms
Contribution of Work
Dimension Reduction and Variable Selection Analysis
Locality Preserving Projections Implementation
Least Angle Regression
Data Construction and Measurement Protocols
Face Aging Databases
Data Constructions and Experiment Setups
Performance Measure
How to Use Cross Validation on Subspace Learning or Feature Selection
How to Compare Two Learning Algorithms Statistically?
A Toy Simulation Example with 10-Fold Cross-Validation
Repeated Cross-Validation
Conclusion
References
Selective Ensemble of Support Vector Data Descriptions for Novelty Detection
Introduction
SVDD
Selective Ensemble of SVDDs
Negative Correlation Learning
NCL Based on Correntropy
Experimental Results
Synthetic Data Sets
Benchmark Data Sets
Conclusions
References
Tutorial and Selected Approaches on Parameter Learning in Bayesian Network with Incomplete Data
Introduction
Bayesian Network
Inferring Unobserved Variables
Parameters Learning
Conditional Probability Tables
Learning Parameter with Complete Data
Statistical Approach
Bayesian Approach
Learning Parameter with Incomplete Data
EM Algorithm
Robust Bayesian Estimator (RBE) Algorithm
Gibbs Algorithm
Some Approaches Dealing with Data Missing in Parameter Learning
Conclusion
References
Selective Ensemble Modeling Parameters of Mill Load Based on Shell Vibration Signal
Introduction
Selective Ensemble Modeling Parameters of Mill Load
Strategy of Soft Sensor
Data Preprocessing Module
Sub-model Module
Selective Ensemble Module
Application Study
Conclusions
References
Selective Weight Update Rule for Hybrid Neural Network
Introduction
Incremental Learning and Pattern Recognition by CNN
Incremental Learning
Pattern Recognition by CNN
Capability of Function Approximation by Sub-Networks
VSF-NETWORK
Learning Procedure
Selecting Weights for Update
Experiments and Discussion
Task for Experiment
Experiment 1
Experiment 2
Conclusion
References
Applying Ensemble Learning Techniques to ANFIS for Air Pollution Index Prediction in Macau
Introduction
Paper Organization
Methodology Review
Adaptive Neuro-fuzzy Inference System (ANFIS)
Ensemble learning
Performance Index
Input Selection
Results and Discussion
Conclusion
References
A PSO-SVM Based Model for Alpha Particle Activity Prediction Inside Decommissioned Channels
Introduction
The Hybrid PSO-SVM Model
Particle Swarm Optimization Algorithm
The SVM Parameter Optimization Process on PSO
Computational Results and Analysis
Conclusion
References
Training Pool Selection for Semi-supervised Learning
Introduction
Semi-supervised Learning
Problem Statement
Selection Strategies
Training Data Selection
Number of Unlabeled Set
Capacity of Training Pool
Experimental Analysis
UCI Dataset
Configurations
Result
Conclusions and Future Work
References
A Rapid Sparsification Method for Kernel Machines in Approximate Policy Iteration
Introduction
Markov Decision Processes and LSPI
Markov Decision Processes
The LSPI Algorithm
Sparsification of Kernel Machines for API Algorithms
Sequential Sparsification of Kernel Machines for LSPI
Rapid Sparsification of Kernel Machines for LSPI
Experimental Results
Conclusions and Future Work
References
Computational Properties of Cyclic and Almost-Cyclic Learning with Momentum for Feedforward Neural Networks
Introduction
Cyclic and Almost-Cyclic Learning with Momentum
Cyclic Learning with Momentum of FNN (CMFNN)
Almost-Cyclic Learning with Momentum of FNN (ACMFNN)
Main Results
Simulations
Example 1: Benchmark Classification Problems
Example 2: Regression Problems
Conclusion
References
A Hybrid Evolving and Gradient Strategy for Approximating Policy Evaluation on Online Critic-Actor Learning
Introduction
An Online Actor-Critic Design
Integration of DE-BP Algorithm into ADP Design
Case Study with Cart Polebenchmark
Conclusions
References
Preventing Error Propagation in Semi-supervised Learning
Introduction
Background: Particle Competition Technique (PCM)
Detection and Prevention of Error Propagation via Competitive Learning
Detecting Incorrectly Labeled Vertices
Preventing the Label Propagation from Incorrectly Labeled Vertices
The New Competitive Learning System
Computer Simulations
Setting Up the Proposed Algorithm and Environment
Simulations on Real-World Data Sets
Final Remarks
References
An Incremental Approach to Support Vector Machine Learning
Introduction
SVM Basics
Method
Experiments
Data Set
Implementation
Complexity Analysis
Conclusion
References
Multi-phase Fast Learning Algorithms for Solving the Local Minimum Problem in Feed-Forward Neural Networks
Introduction
Fast Learning Algorithms
Quickprop
RPROP
MGFPROP
Local Minimum Solver (LMS)
Numerical Results
Conclusions
References
Skull-Closed Autonomous Development: Object-Wise Incremental Learning
Introduction
Skull-Closed Developmental WWN-6
Network Structure
Concepts and Algorithms
Experiments and Results
Conclusion
References
Optimization
MaxMin-SOMO: An SOM Optimization Algorithm for Simultaneously Finding Maximum and Minimum of a Function
Introduction
Original SOM-Based Optimization (SOMO) Algorithm
MaxMin-SOMO Algorithm
Simulation Results
Objective Functions
Parameters of Simulation
Simulations of MaxMin-SOMO Algorithm for One Minimum and One Maximum
References
Hybrid Algorithm Based on Particle Swarm Optimization and Artificial Fish Swarm Algorithm
Introduction
The Basic Theory of the Algorithm
Particle Swarm Optimization Algorithm
Artificial Fish Swarm Algorithm
The Hybrid Algorithm Based on PSO and AFSA
Algorithm Steps
Simulation Experience
Conclusion
References
The High Degree Seeking Algorithms with k Steps for Complex Networks
Introduction
Scale-Free Network Model
Classic Search Algorithms
A High Degree Seeking Algorithm with K Steps
Simulation
Conclusions
References
Improved PSO Algorithm with Harmony Search for Complicated Function Optimization Problems
Introduction
Method
Basic PSO Algorithm
Harmony Search Algorithm
IHPSO Algorithm
Experiments
Benchmark Functions
Parameter Settings
Experimental Results and Discussion
Conclusion
References
An Improved Chaotic Ant Colony Algorithm
Introduction
Mathematics Model of ACO
The Improved Chaotic Ant Swarm Algorithm
Overview of Chaotic Ant Swarm
Strategy of Return-Trip Optimization
Elitist Strategy
Simulation Experiments
Conclusion
References
A Game Based Approach for Sharing the Data Center Network
Introduction
Network Virtualization in VDC
Virtual Bandwidth Sharing Algorithm
Basic Model
Distributed Implementation
Performance Evaluation
Conclusion
References
Optimal Task and Energy Scheduling in Dynamic Residential Scenarios
Introduction
The Proposed Algorithm: Analytical Issues
The Proposed Algorithm: Operational Issues
The Static Case Study
The Dynamic Case Study
Computer Simulations
Conclusions
References
Biogeography Based Optimization for Multi-Knapsack Problems
Introduction
Biogeograpy Based Optimization Algorithm
Principle of BBOA
Procedure of MKPBBOA
Experiment Results
Multi-Knapsack Problem
Results and Discussion
Conclusions
References
MRKDSBC: A Distributed Background Modeling Algorithm Based on MapReduce
Introduction
Related Works
KDSBC Algorithm
Algorithm Based on MapReduce
The Proof
Experiment
Conclusion and Future Work
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Advances in Neural Networks - ISNN 2012

Description

More details

Other editions

Additional editions

Content

System requirements