Computational and Ambient Intelligence

1. Front Matter

   PDF

2. Theoretical Concepts and Neuro Computational Formulations

   1. Generating Random Deviates Consistent with the Long Term Behavior of Stochastic Search Processes in Global Optimization

      • Arturo Berrones

      Pages 1-7

   2. Dynamics of Neural Networks - Some Qualitative Properties

      • Daniela Danciu, Vladimir Răsvan

      Pages 8-15

   3. A Comparative Study of PCA, ICA and Class-Conditional ICA for Naïve Bayes Classifier

      • Liwei Fan, Kim Leng Poh

      Pages 16-22

   4. Effect of Increasing Inhibitory Inputs on Information Processing Within a Small Network of Spiking Neurons

      • Roberta Sirovich, Laura Sacerdote, Alessandro E. P. Villa

      Pages 23-30

   5. An Efficient VAD Based on a Hang-Over Scheme and a Likelihood Ratio Test

      • O. Pernía, J. M. Górriz, J. Ramírez, C. G. Puntonet, I. Turias

      Pages 31-38

   6. Analysis of Hebbian Models with Lateral Weight Connections

      • Pedro J. Zufiria, J. Andrés Berzal

      Pages 39-46

   7. Power Quality Event Identification Using Higher-Order Statistics and Neural Classifiers

      • Juan-José González de-la-Rosa, Carlos G. Puntonet, Antonio Moreno Muñoz

      Pages 47-54

   8. Bio-inspired Memory Generation by Recurrent Neural Networks

      • Manuel G. Bedia, Juan M. Corchado, Luis F. Castillo

      Pages 55-62

   9. Non-parametric Residual Variance Estimation in Supervised Learning

      • Elia Liitiäinen, Amaury Lendasse, Francesco Corona

      Pages 63-71

   10. A Study on the Use of Statistical Tests for Experimentation with Neural Networks

       • Julián Luengo, Salvador García, Francisco Herrera

       Pages 72-79

3. Improving Models and Learning Procedures

   1. Unified Analysis and Design of ART/SOM Neural Networks and Fuzzy Inference Systems Based on Lattice Theory

      • Vassilis G. Kaburlasos

      Pages 80-93

   2. A Comparison Between ANN Generation and Training Methods and Their Development by Means of Graph Evolution: 2 Sample Problems

      • Daniel Rivero, Julián Dorado, Juan R. Rabuñal, Marcos Gestal

      Pages 94-101

   3. Robust LTS Backpropagation Learning Algorithm

      • Andrzej Rusiecki

      Pages 102-109

   4. Heuristic Search Based Exploration in Reinforcement Learning

      • Ngo Anh Vien, Nguyen Hoang Viet, SeungGwan Lee, TaeChoong Chung

      Pages 110-118

   5. Improving Adaptive Boosting with a Relaxed Equation to Update the Sampling Distribution

      • Joaquín Torres-Sospedra, Carlos Hernández-Espinosa, Mercedes Fernández-Redondo

      Pages 119-126

   6. Automatic Model Selection for Probabilistic PCA

      • Ezequiel López-Rubio, Juan Miguel Ortiz-de-Lazcano-Lobato, Domingo López-Rodríguez, María del Carmen Vargas-González

      Pages 127-134

   7. Probabilistic Aggregation of Classifiers for Incremental Learning

      • Patricia Trejo, Ricardo Ñanculef, Héctor Allende, Claudio Moraga

      Pages 135-143

   8. Behaviour-Based Clustering of Neural Networks Applied to Document Enhancement

      • F. Zamora-Martínez, S. España-Boquera, M. J. Castro-Bleda

      Pages 144-151

   9. Building Automated Negotiation Strategies Enhanced by MLP and GR Neural Networks for Opponent Agent Behaviour Prognosis

      • Ioanna Roussaki, Ioannis Papaioannou, Miltiades Anangostou

      Pages 152-161

We present in this volume the collection of finally accepted papers for the ninth e- tion of the IWANN conference (“International Work-Conference on Artificial Neural Networks”). This biennial meeting focuses on the foundations, theory, models and applications of systems inspired by nature (neural networks, fuzzy logic and evo- tionary systems). Since the first edition of IWANN in Granada (LNCS 540, 1991), the computational intelligence community and the domain itself have matured and evolved. Under the computational intelligent banner we find a very heterogeneous scenario with a main interest and objective: to better understand nature and natural entities for the correct elaboration of theories, models and new algorithms. For scientifics, engineers and professionals working in the area, this is a very good way to get real, solid and c- petitive applications. More and more, these new computational techniques are used in applications that try to bring a new situation of well-being to the user. The conjunction of a more and more miniaturized hardware together with the growing computational intelligence embodied in this hardware leads us towards fully integrated embedded systems-on- chip and opens the door for truly ubiquitous electronics.

• algorithms
• ambient intelligence
• fuzzy
• fuzzy system
• fuzzy systems
• genetic algorithms
• intelligence
• kernel method
• learning
• machine learning
• neural networks
• proving
• robot
• robotics
• speech processing
• algorithm analysis and problem complexity

Policies and ethics