Advances in Neural Networks - ISNN 2004 International Symposium on Neural Networks, Dalian, China, August 19-21, 2004, Proceedings, Part I

This book constitutes the proceedings of the International Symposium on Neural N- works (ISNN 2004) held in Dalian, Liaoning, China during August 19–21, 2004. ISNN 2004 received over 800 submissions from authors in ?ve continents (Asia, Europe, North America, South America, and Oceania), and 23 countries and regions (mainland China, Hong Kong, Taiwan, South Korea, Japan, Singapore, India, Iran, Israel, Turkey, H- gary, Poland, Germany, France, Belgium, Spain, UK, USA, Canada, Mexico, Venezuela, Chile, and Australia). Based on reviews, the Program Committee selected 329 hi- quality papers for presentation at ISNN 2004 and publication in the proceedings. The papers are organized into many topical sections under 11 major categories (theore- cal analysis; learning and optimization; support vector machines; blind source sepa- tion, independent component analysis, and principal component analysis; clustering and classi?cation; robotics and control; telecommunications; signal, image and time series processing; detection, diagnostics, and computer security; biomedical applications; and other applications) covering the whole spectrum of the recent neural network research and development. In addition to the numerous contributed papers, ?ve distinguished scholars were invited to give plenary speeches at ISNN 2004. ISNN 2004 was an inaugural event. It brought together a few hundred researchers, educators, scientists, and practitioners to the beautiful coastal city Dalian in northeastern China.

Theoretical Analysis.- Approximation Bounds by Neural Networks in L ? p [-4pt].- Geometric Interpretation of Nonlinear Approximation Capability for Feedforward Neural Networks.- Mutual Information and Topology 1: Asymmetric Neural Network.- Mutual Information and Topology 2: Symmetric Network.- Simplified PCNN and Its Periodic Solutions.- On Robust Periodicity of Delayed Dynamical Systems with Time-Varying Parameters.- Delay-Dependent Criteria for Global Stability of Delayed Neural Network System.- Stability Analysis of Uncertain Neural Networks with Delay.- A New Method for Robust Stability Analysis of a Class of Recurrent Neural Networks with Time Delays.- Criteria for Stability in Neural Network Models with Iterative Maps.- Exponential Stability Analysis for Neural Network with Parameter Fluctuations.- Local Stability and Bifurcation in a Model of Delayed Neural Network.- On the Asymptotic Stability of Non-autonomous Delayed Neural Networks.- Global Exponential Stability of Cohen-Grossberg Neural Networks with Multiple Time-Varying Delays.- Stability of Stochastic Cohen-Grossberg Neural Networks.- A Novel Approach to Exponential Stability Analysis of Cohen-Grossberg Neural Networks.- Analysis for Global Robust Stability of Cohen-Grossberg Neural Networks with Multiple Delays.- On Robust Stability of BAM Neural Networks with Constant Delays.- Absolutely Exponential Stability of BAM Neural Networks with Distributed Delays.- Stability Analysis of Discrete-Time Cellular Neural Networks.- Novel Exponential Stability Criteria for Fuzzy Cellular Neural Networks with Time-Varying Delay.- Stability of Discrete Hopfield Networks with Delay in Serial Mode.- Further Results for an Estimation of Upperbound of Delays for Delayed Neural Networks.- Synchronization in Two Uncoupled Chaotic Neurons.- Robust Synchronization of Coupled Delayed Recurrent Neural Networks.- Learning and Optimization.- Self-Optimizing Neural Networks.- Genetically Optimized Self-Organizing Neural Networks Based on PNs and FPNs.- A New Approach to Self-Organizing Hybrid Fuzzy Polynomial Neural Networks: Synthesis of Computational Intelligence Technologies.- On Soft Learning Vector Quantization Based on Reformulation.- A New Approach to Self-Organizing Polynomial Neural Networks by Means of Genetic Algorithms.- Fuzzy-Kernel Learning Vector Quantization.- Genetic Generation of High-Degree-of-Freedom Feed-Forward Neural Networks.- Self-Organizing Feature Map Based Data Mining.- Diffusion and Growing Self-Organizing Map: A Nitric Oxide Based Neural Model.- A New Adaptive Self-Organizing Map.- Evolving Flexible Neural Networks Using Ant Programming and PSO Algorithm.- Surrogating Neurons in an Associative Chaotic Neural Network.- Ensembles of RBFs Trained by Gradient Descent.- Gradient Descent Training of Radial Basis Functions.- Recent Developments on Convergence of Online Gradient Methods for Neural Network Training.- A Regularized Line Search Tunneling for Efficient Neural Network Learning.- Transductive Learning Machine Based on the Affinity-Rule for Semi-supervised Problems and Its Algorithm.- A Learning Algorithm with Gaussian Regularizer for Kernel Neuron.- An Effective Learning Algorithm of Synergetic Neural Network.- Sparse Bayesian Learning Based on an Efficient Subset Selection.- A Novel Fuzzy Neural Network with Fast Training and Accurate Generalization.- Tuning Neuro-Fuzzy Function Approximator by Tabu Search.- Finite Convergence of MRI Neural Network for Linearly Separable Training Patterns.- A Rapid Two-Step Learning Algorithm for Spline Activation Function Neural Networks with the Application on Biped Gait Recognition.- An Online Feature Learning Algorithm Using HCI-Based Reinforcement Learning.- Optimizing the Weights of Neural Networks Based on Antibody Clonal Simulated Annealing Algorithm.- Backpropagation Analysis of the Limited Precision on High-Order Function Neural Networks.- LMS Adaptive Notch Filter Design Based on Immune Algorithm.- Training Radial Basis Function Networks with Particle Swarms.- Optimizing Weights by Genetic Algorithm for Neural Network Ensemble.- Survival Density Particle Swarm Optimization for Neural Network Training.- Modified Error Function with Added Terms for the Backpropagation Algorithm.- Robust Constrained-LMS Algorithm.- A Novel Three-Phase Algorithm for RBF Neural Network Center Selection.- Editing Training Data for kNN Classifiers with Neural Network Ensemble.- Learning Long-Term Dependencies in Segmented Memory Recurrent Neural Networks.- An Optimal Neural-Network Model for Learning Posterior Probability Functions from Observations.- The Layered Feed-Forward Neural Networks and Its Rule Extraction.- Analysing Contributions of Components and Factors to Pork Odour Using Structural Learning with Forgetting Method.- On Multivariate Calibration Problems.- Control of Associative Chaotic Neural Networks Using a Reinforcement Learning.- A Method to Improve the Transiently Chaotic Neural Network.- A New Neural Network for Nonlinear Constrained Optimization Problems.- Delay PCNN and Its Application for Optimization.- A New Parallel Improvement Algorithm for Maximum Cut Problem.- A New Neural Network Algorithm for Clique Vertex-Partition Problem.- An Algorithm Based on Hopfield Network Learning for Minimum Vertex Cover Problem.- A Subgraph Isomorphism Algorithm Based on Hopfield Neural Network.- A Positively Self-Feedbacked Hopfield Neural Network for N-Queens Problem.- NN-Based GA for Engineering Optimization.- Applying GENET to the JSSCSOP.- Support Vector Machines.- Improvements to Bennett’s Nearest Point Algorithm for Support Vector Machines.- Distance-Based Selection of Potential Support Vectors by Kernel Matrix.- A Learning Method for Robust Support Vector Machines.- A Cascade Method for Reducing Training Time and the Number of Support Vectors.- Minimal Enclosing Sphere Estimation and Its Application to SVMs Model Selection.- Constructing Support Vector Classifiers with Unlabeled Data.- Nested Buffer SMO Algorithm for Training Support Vector Classifiers.- Support Vector Classifier with a Fuzzy-Value Class Label.- RBF Kernel Based Support Vector Machine with Universal Approximation and Its Application.- A Practical Parameters Selection Method for SVM.- Ho–Kashyap with Early Stopping Versus Soft Margin SVM for Linear Classifiers –An Application.- Radar HRR Profiles Recognition Based on SVM with Power-Transformed-Correlation Kernel.- Hydrocarbon Reservoir Prediction Using Support Vector Machines.- Toxic Vapor Classification and Concentration Estimation for Space Shuttle and International Space Station.- Optimal Watermark Detection Based on Support Vector Machines.- Online LS-SVM Learning for Classification Problems Based on Incremental Chunk.- A Novel Approach to Clustering Analysis Based on Support Vector Machine.- Application of Support Vector Machine in Queuing System.- Modelling of Chaotic Systems with Novel Weighted Recurrent Least Squares Support Vector Machines.- Nonlinear System Identification Based on an Improved Support Vector Regression Estimator.- Anomaly Detection Using Support Vector Machines.- Power Plant Boiler Air Preheater Hot Spots Detection System Based on Least Square Support Vector Machines.- Support Vector Machine Multiuser Detector for TD-SCDMA Communication System in Multipath Channels.- Eyes Location by Hierarchical SVM Classifiers.- Classification of Stellar Spectral Data Using SVM.- Iris Recognition Using Support Vector Machines.- Heuristic Genetic Algorithm-Based Support Vector Classifier for Recognition of Remote Sensing Images.- Landmine Feature Extraction and Classification of GPR Data Based on SVM Method.- Occupant Classification for Smart Airbag Using Stereovision and Support Vector Machines.- Support Vector Machine Committee for Classification.- Automatic Modulation Classification by Support Vector Machines.- Blind Source Separation, Independent Component Analysis and Principal Component Analysis.- Blind Sourc