The Sixth International Symposium on Neural Networks (ISNN 2009)

ISBN-13: 9783642012150 / Angielski / Miękka / 2009 / 936 str.

Hongwei Wang; Yi Shen; Tingwen Huang

Opis

This volume of Advances in Soft Computing and Lecture Notes in Computer th Science vols. 5551, 5552 and 5553, constitute the Proceedings of the 6 Inter- tional Symposium of Neural Networks (ISNN 2009) held in Wuhan, China during May 26 29, 2009. ISNN is a prestigious annual symposium on neural networks with past events held in Dalian (2004), Chongqing (2005), Chengdu (2006), N- jing (2007) and Beijing (2008). Over the past few years, ISNN has matured into a well-established series of international conference on neural networks and their applications to other fields. Following this tradition, ISNN 2009 provided an a- demic forum for the participants to disseminate their new research findings and discuss emerging areas of research. Also, it created a stimulating environment for the participants to interact and exchange information on future research challenges and opportunities of neural networks and their applications. ISNN 2009 received 1,235 submissions from about 2,459 authors in 29 co- tries and regions (Australia, Brazil, Canada, China, Democratic People's Republic of Korea, Finland, Germany, Hong Kong, Hungary, India, Islamic Republic of Iran, Japan, Jordan, Macao, Malaysia, Mexico, Norway, Qatar, Republic of Korea, Singapore, Spain, Taiwan, Thailand, Tunisia, United Kingdom, United States, Venezuela, Vietnam, and Yemen) across six continents (Asia, Europe, North America, South America, Africa, and Oceania). Based on rigorous reviews by the Program Committee members and reviewers, 95 high-quality papers were selected to be published in this volume."

Spis treści

Session 1: Theoretical Analysis.- The Initial Alignment of SINS Based on Neural Network.- Analysis on Basic Conceptions and Principles of Human Cognition.- Global Exponential Stability for Discrete-Time BAM Neural Network with Variable Delay.- The Study of Project Cost Estimation Based on Cost-Significant Theory and Neural Network Theory.- Global Exponential Stability of High-Order Hopfield Neural Networks with Time Delays.- Improved Particle Swarm Optimization for RCP Scheduling Problem.- Exponential Stability of Reaction-Diffusion Cohen-Grossberg Neural Networks with S-Type Distributed Delays.- Global Exponential Robust Stability of Static Reaction-Diffusion Neural Networks with S-Type Distributed Delays.- A LEC-and-AHP Based Hazard Assessment Method in Hydroelectric Project Construction.- A Stochastic Lotka-Volterra Model with Variable Delay.- Extreme Reformulated Radial Basis Function Neural Networks.- Research of Nonlinear Combination Forecasting Model for Insulators ESDD Based on Wavelet Neural Network.- Parameter Tuning of MLP Neural Network Using Genetic Algorithms.- Intelligent Grid of Computations.- Method of Solving Matrix Equation and Its Applications in Economic Management.- Efficient Feature Selection Algorithm Based on Difference and Similitude Matrix.- Exponential Stability of Neural Networks with Time-Varying Delays and Impulses.- Session 2: Machine Learning.- Adaptive Higher Order Neural Networks for Effective Data Mining.- Exploring Cost-Sensitive Learning in Domain Based Protein-Protein Interaction Prediction.- An Efficient and Fast Algorithm for Estimating the Frequencies of 2-D Superimposed Exponential Signals in Presence of Multiplicative and Additive Noise.- An Improved Greedy Based Global Optimized Placement Algorithm.- An Alternative Fast Learning Algorithm of Neural Network.- Computer Aided Diagnosis of Alzheimer’s Disease Using Principal Component Analysis and Bayesian Classifiers.- Margin-Based Transfer Learning.- Session 3: Support Vector Machines and Kernel Methods.- Nonlinear Dead Zone System Identification Based on Support Vector Machine.- A SVM Model Selection Method Based on Hybrid Genetic Algorithm and Empirical Error Minimization Criterion.- An SVM-Based Mandarin Pronunciation Quality Assessment System.- An Quality Prediction Method of Injection Molding Batch Processes Based on Sub-Stage LS-SVM.- Soft Sensing for Propylene Purity Using Partial Least Squares and Support Vector Machine.- Application of Support Vector Machines Method in Credit Scoring.- Session 4: Pattern Recognition.- Improving Short Text Clustering Performance with Keyword Expansion.- Nonnative Speech Recognition Based on Bilingual Model Modification at State Level.- Edge Detection Based on a PCNN-Anisotropic Diffusion Synergetic Approach.- Automatic Face Recognition Systems Design and Realization.- Multi-view Face Detection Using Six Segmented Rectangular Features.- Level Detection of Raisins Based on Image Analysis and Neural Network.- English Letters Recognition Based on Bayesian Regularization Neural Network.- Iris Disease Classifying Using Neuro-Fuzzy Medical Diagnosis Machine.- An Approach to Dynamic Gesture Recognition for Real-Time Interaction.- Dynamic Multiple Pronunciation Incorporation in a Refined Search Space for Reading Miscue Detection.- Depicting Diversity in Rules Extracted from Ensembles.- A New Statistical Model for Radar HRRP Target Recognition.- Independent Component Analysis of SPECT Images to Assist the Alzheimer’s Disease Diagnosis.- The Multi-Class Imbalance Problem: Cost Functions with Modular and Non-Modular Neural Networks.- Geometry Algebra Neuron Based on Biomimetic Pattern Recognition.- A Novel Matrix-Pattern-Oriented Ho-Kashyap Classifier with Locally Spatial Smoothness.- An Integration Model Based on Non-classical Receptive Fields.- Classification of Imagery Movement Tasks for Brain-Computer Interfaces Using Regression Tree.- MIDBSCAN: An Efficient Density-Based Clustering Algorithm.- Detection and Following of a Face in Movement Using a Neural Network.- Session 5: Intelligent Modelling and Control.- Nonparametric Inter-Quartile Range for Error Evaluation and Correction of Demand Forecasting Model under Short Product Lifecycle.- Simulated Annealing and Crowd Dynamics Approaches for Intelligent Control.- Accomplishing Station Keeping Mode for Attitude Orbit Control Subsystem Designed for T-SAT.- Nonlinear System Identification Based on Recurrent Wavelet Neural Network.- Approximation to Nonlinear Discrete-Time Systems by Recurrent Neural Networks.- Model-Free Control of Nonlinear Noise Processes Based on C-FLAN.- An Empirical Study of the Artificial Neural Network for Currency Exchange Rate Time Series Prediction.- Grey Prediction with Markov-Chain for Crude Oil Production and Consumption in China.- Fabric Weave Identification Based on Cellular Neural Network.- Cutting Force Prediction of High-Speed Milling Hardened Steel Based on BP Neural Networks.- BP Neural Networks Based Soft Measurement of Rheological Properties of CWS.- A Parameters Self-adjusting ANN-PI Controller Based on Homotopy BP Algorithm.- Session 6: Optimization and Genetic Algorithms.- Study on Optimization of the Laser Texturing Surface Morphology Parameters Based on ANN.- A Combined Newton Method for Second-Order Cone Programming.- MES Scheduling Optimization and Simulation Based on CAPP/PPC Integration.- An Improved Diversity Guided Particle Swarm Optimization.- Research on Intelligent Diagnosis of Mechanical Fault Based on Ant Colony Algorithm.- A New Supermemory Gradient Method without Line Search for Unconstrained Optimization.- A Neural Network Approach for Solving Linear Bilevel Programming Problem.- Fuzzy Solution for Multiple Targets Optimization Based on Fuzzy Max-Min Neural Network.- Fixed-Structure Mixed Sensitivity/Model Reference Control Using Evolutionary Algorithms.- Session 7: Telecommunication and Transportation Systems.- ANN-Based Multi-scales Prediction of Self-similar Network Traffic.- Application of DM and Combined Grey Neural Network in E-Commerce Data Transmission.- Application of Prediction Model in Monitoring LAN Data Flow Based on Grey BP Neural Network.- Monitoring ARP Attack Using Responding Time and State ARP Cache.- A Study of Multi-agent Based Metropolitan Demand Responsive Transport Systems.- Sesson 8: Applications.- The Diagnosis Research of Electric Submersible Pump Based on Neural Network.- The Application of BP Feedforward Neural Networks to the Irradiation Effects of High Power Microwave.- A Novel Model for Customer Retention.- Neural Network Ensemble Approach in Analog Circuit Fault Diagnosis.- Research on Case Retrieval of Case-Based Reasoning of Motorcycle Intelligent Design.- Improving Voice Search Using Forward-Backward LVCSR System Combination.- Agent Oriented Programming for Setting Up the Platform for Processing EEG / ECG / EMG Waveforms.- A Forecasting Model of City Freight Volume Based on BPNN.- The Estimations of Mechanical Property of Rolled Steel Bar by Using Quantum Neural Network.- Diagnosis of Epilepsy Disorders Using Artificial Neural Networks.- Neural Forecasting Network for the Market of Pleione Formosana Hayata Orchid.- Harmonic Current Detection Based on Neural Network Adaptive Noise Cancellation Technology.- Study on Dynamic Relation between Share Price Index and Housing Price: Co-integration Analysis and Application in Share Price Index Prediction.- Application of RBF and Elman Neural Networks on Condition Prediction in CBM.- Judging the States of Blast Furnace by ART2 Neural Network.- Research on Dynamic Response of Riverbed Deformation Based on Theory of BP Neural Network.- Adaboosting Neural Networks for Credit Scoring.- An Enterprise Evaluation of Reverse Supply Chain Based on Ant Colony BP Neural Network.- Ultrasonic Crack Size Estimation Based on Wavelet Neural Networks.

Blurb

This volume of Advances in Soft Computing and Lecture Notes in Computer Science vols. 5551, 5552 and 5553, constitute the Proceedings of the 6^th International Symposium of Neural Networks (ISNN 2009) held in Wuhan, China during May 26 - 29, 2009. ISNN is a prestigious annual symposium on neural networks with past events held in Dalian (2004), Chongqing (2005), Chengdu (2006), Nanjing (2007) and Beijing (2008). Over the past few years, ISNN has matured into a well-established series of international conference on neural networks and their applications to other fields. Following this tradition, ISNN 2009 provided an academic forum for the participants to disseminate their new research findings and discuss emerging areas of research. Also, it created a stimulating environment for the participants to interact and exchange information on future research challenges and opportunities of neural networks and their applications.