This book includes the proceedings of the International Conference on Artificial Neural Networks (ICANN 2006) held on September 10-14, 2006 in Athens, Greece, with tutorials being presented on September 10, the main conference taking place during September 11-13 and accompanying workshops on perception, cognition and interaction held on September 14, 2006. The ICANN conference is organized annually by the European Neural Network Society in cooperation with the International Neural Network Society, the Japanese Neural Network Society and the IEEE Computational Intelligence Society. It is the premier European event covering all topics concerned with neural networks and related areas. The ICANN series of conferences was initiated in 1991 and soon became the major European gathering for experts in these fields. In 2006 the ICANN Conference was organized by the Intelligent Systems Laboratory and the Image, Video and Multimedia Systems Laboratory of the National Technical University of Athens in Athens, Greece. From 475 papers submitted to the conference, the International Program Committee selected, following a thorough peer-review process, 208 papers for publication and presentation to 21 regular and 10 special sessions. The quality of the papers received was in general very high; as a consequence, it was not possible to accept and include in the conference program many papers of good quality.
Proceedings of the 16th International Conference on Artificial Neural Networks, ICANN 2006, in two volumes
Presents 208 revised full papers
Volume II covers neural networks, data analysis, pattern recognition, and more
Neural Networks, Semantic Web Technologies and Multimedia Analysis (Special Session).- The Core Method: Connectionist Model Generation.- A Neural Scheme for Robust Detection of Transparent Logos in TV Programs.- A Neural Network to Retrieve Images from Text Queries.- Techniques for Still Image Scene Classification and Object Detection.- Adaptation of Weighted Fuzzy Programs.- Classified Ranking of Semantic Content Filtered Output Using Self-organizing Neural Networks.- Classifier Fusion: Combination Methods For Semantic Indexing in Video Content.- Bridging the Semantic Gap in Multimedia Machine Learning Approaches (Special Session).- Retrieval of Multimedia Objects by Combining Semantic Information from Visual and Textual Descriptors.- A Relevance Feedback Approach for Content Based Image Retrieval Using Gaussian Mixture Models.- Video Representation and Retrieval Using Spatio-temporal Descriptors and Region Relations.- Bridging the Syntactic and the Semantic Web Search.- Content-Based Coin Retrieval Using Invariant Features and Self-organizing Maps.- Signal and Time Series Processing (I).- Learning Time-Series Similarity with a Neural Network by Combining Similarity Measures.- Prediction Improvement via Smooth Component Analysis and Neural Network Mixing.- Missing Value Estimation for DNA Microarrays with Mutliresolution Schemes.- Applying REC Analysis to Ensembles of Sigma-Point Kalman Filters.- Analysis of Fast Input Selection: Application in Time Series Prediction.- A Linguistic Approach to a Human-Consistent Summarization of Time Series Using a SOM Learned with a LVQ-Type Algorithm.- Signal and Time Series Processing (II).- Long-Term Prediction of Time Series Using State-Space Models.- Time Series Prediction Using Fuzzy Wavelet Neural Network Model.- OFDM Channel Equalization Based on Radial Basis Function Networks.- A Quasi-stochastic Gradient Algorithm for Variance-Dependent Component Analysis.- Two ICA Algorithms Applied to BSS in Non-destructive Vibratory Tests.- Reference-Based Extraction of Phase Synchronous Components.- Data Analysis (I).- Analytic Solution of Hierarchical Variational Bayes in Linear Inverse Problem.- Nonnegative Matrix Factorization for Motor Imagery EEG Classification.- Local Factor Analysis with Automatic Model Selection: A Comparative Study and Digits Recognition Application.- Interpolating Support Information Granules.- Feature Selection Based on Kernel Discriminant Analysis.- Local Selection of Model Parameters in Probability Density Function Estimation.- The Sphere-Concatenate Method for Gaussian Process Canonical Correlation Analysis.- Theory of a Probabilistic-Dependence Measure of Dissimilarity Among Multiple Clusters.- Kernel PCA as a Visualization Tools for Clusters Identifications.- Data Analysis (II).- A Fast Fixed-Point Algorithm for Two-Class Discriminative Feature Extraction.- Feature Extraction with Weighted Samples Based on Independent Component Analysis.- Discriminant Analysis by a Neural Network with Mahalanobis Distance.- Assessment of an Unsupervised Feature Selection Method for Generative Topographic Mapping.- A Model Selection Method Based on Bound of Learning Coefficient.- Pattern Recognition.- Sequential Learning with LS-SVM for Large-Scale Data Sets.- A Nearest Features Classifier Using a Self-organizing Map for Memory Base Evaluation.- A Multisensor Fusion System for the Detection of Plant Viruses by Combining Artificial Neural Networks.- A Novel Connectionist-Oriented Feature Normalization Technique.- An Evolutionary Approach to Automatic Kernel Construction.- A Leave-K-Out Cross-Validation Scheme for Unsupervised Kernel Regression.- Neural Network Clustering Based on Distances Between Objects.- Rotation-Invariant Pattern Recognition: A Procedure Slightly Inspired on Olfactory System and Based on Kohonen Network.- Pattern Classification Using Composite Features.- Visual Attention Algorithms and Architectures for Perceptional Understanding and Video Coding (Special Session).- Towards a Control Theory of Attention.- Localization of Attended Multi-feature Stimuli: Tracing Back Feed-Forward Activation Using Localized Saliency Computations.- An Attention Based Similarity Measure for Colour Images.- Learning by Integrating Information Within and Across Fixations.- Feature Conjunctions in Visual Search.- A Biologically Motivated System for Unconstrained Online Learning of Visual Objects.- Second-Order (Non-Fourier) Attention-Based Face Detection.- Requirements for the Transmission of Streaming Video in Mobile Wireless Networks.- Wavelet Based Estimation of Saliency Maps in Visual Attention Algorithms.- Vision and Image Processing (I).- Selective Tuning: Feature Binding Through Selective Attention.- Rotation Invariant Recognition of Road Signs with Ensemble of 1-NN Neural Classifiers.- Computer Aided Classification of Mammographic Tissue Using Independent Component Analysis and Support Vector Machines.- Growing Neural Gas for Vision Tasks with Time Restrictions.- A Fixed-Point Algorithm of Topographic ICA.- Image Compression by Vector Quantization with Recurrent Discrete Networks.- Vision and Image Processing (II).- Feature Extraction Using Class-Augmented Principal Component Analysis (CA-PCA).- A Comparative Study of the Objectionable Video Classification Approaches Using Single and Group Frame Features.- Human Facial Expression Recognition Using Hybrid Network of PCA and RBFN.- Extracting Motion Primitives from Natural Handwriting Data.- Including Metric Space Topology in Neural Networks Training by Ordering Patterns.- Computational Finance and Economics (Special Session).- A Technical Trading Indicator Based on Dynamical Consistent Neural Networks.- Testing the Random Walk Hypothesis with Neural Networks.- Financial Application of Neural Networks: Two Case Studies in Greece.- Credit Risk Analysis Using a Reliability-Based Neural Network Ensemble Model.- Competitive and Collaborative Mixtures of Experts for Financial Risk Analysis.- Neural Computing in Energy Engineering (Special Session).- Kernel Regression Based Short-Term Load Forecasting.- Electricity Load Forecasting Using Self Organizing Maps.- A Hybrid Neural Model in Long-Term Electrical Load Forecasting.- Application of Radial Basis Function Networks for Wind Power Forecasting.- The Application of Neural Networks to Electric Power Grid Simulation.- Early Detection of Winding Faults in Windmill Generators Using Wavelet Transform and ANN Classification.- Combining Artificial Neural Networks and Heuristic Rules in a Hybrid Intelligent Load Forecast System.- New Phenemenon on Power Transformers and Fault Identification Using Artificial Neural Networks.- Applications to Biomedicine and Bioinformatics.- Neural Network Based Algorithm for Radiation Dose Evaluation in Heterogeneous Environments.- Exploring the Intrinsic Structure of Magnetic Resonance Spectra Tumor Data Based on Independent Component Analysis and Correlation Analysis.- Fusing Biomedical Multi-modal Data for Exploratory Data Analysis.- Semi-supervised Significance Score of Differential Gene Expressions.- Semi Supervised Fuzzy Clustering Networks for Constrained Analysis of Time-Series Gene Expression Data.- Evolutionary Optimization of Sequence Kernels for Detection of Bacterial Gene Starts.- Tree-Dependent Components of Gene Expression Data for Clustering.- Applications to Security and Market Analysis.- A Neural Model in Anti-spam Systems.- A Neural Model in Intrusion Detection Systems.- Improved Kernel Based Intrusion Detection System.- Testing the Fraud Detection Ability of Different User Profiles by Means of FF-NN Classifiers.- Predicting User’s Movement with a Combination of Self-Organizing Map and Markov Model.- Learning Manifolds in Forensic Data.- A Comparison of Target Customers in Asian Online Game Markets: Marketing Applications of a Two-Level SOM.- Real World Applications (I).- A Neural Network Approach to Study O3 and PM10 Concentration in Environmental Pollution.- ROC Analysis as a Useful Tool for Performance Evaluation of Artificial Neural Networks.- NewPR-Combining TFIDF with Pagerank.- A Fast Algorithm for Words Reordering Based on Language Model.- Phonetic Feature Discovery in Speech Using Snap-Drift Learning.- A New Neuro-Dominance Rule for Single Machine Tardiness Problem with Unequal Release Dates.- Real World Applications (II).- A Competitive Approach to Neural Device Modeling: Support Vector Machines.- Non-destructive Testing for Assessing Structures by Using Soft-Computing.- Neural Unit Element Application for in Use Microwave Circuitry.- An Artificial Neural Network Based Simulation Metamodeling Approach for Dual Resource Constrained Assembly Line.- A Packet Routing Method Using Chaotic Neurodynamics for Complex Networks.