Artificial Neural Networks - ICANN 2010

1. Front Matter

   PDF

2. ANN Applications

   1. IF-Inference Systems Design for Prediction of Ozone Time Series: The Case of Pardubice Micro-region

      • Vladimír Olej, Petr Hájek

      Pages 1-11

      PDF

   2. Superior-Order Curvature-Corrected Voltage Reference Using a Current Generator

      • Cosmin Popa

      Pages 12-21

      PDF

   3. A Neural Network-Based Method for Affine 3D Registration of FMRI Time Series Using Fourier Space Subsets

      • Luis C. Freire, Ana R. Gouveia, Fernando M. Godinho

      Pages 22-31

      PDF

   4. Neural Networks Regression Inductive Conformal Predictor and Its Application to Total Electron Content Prediction

      • Harris Papadopoulos, Haris Haralambous

      Pages 32-41

      PDF

   5. Prediction of Compaction Characteristics of Granular Soils by Neural Networks

      • Marzena Kłos, Zenon Waszczyszyn

      Pages 42-45

      PDF

   6. Modelling Power Output at Nuclear Power Plant by Neural Networks

      • Jaakko Talonen, Miki Sirola, Eimontas Augilius

      Pages 46-49

      PDF

   7. Time Series Forecasting by Evolving Artificial Neural Networks Using “Shuffle”, Cross-Validation and Ensembles

      • Juan Peralta, German Gutierrez, Araceli Sanchis

      Pages 50-53

      PDF

   8. Prediction of Power Consumption for Small Power Region Using Indexing Approach and Neural Network

      • Krzysztof Siwek, Stanisław Osowski, Bartosz Swiderski, Lukasz Mycka

      Pages 54-59

      PDF

   9. Fault Prognosis of Mechanical Components Using On-Line Learning Neural Networks

      • David Martínez-Rego, Oscar Fontenla-Romero, Beatriz Pérez-Sánchez, Amparo Alonso-Betanzos

      Pages 60-66

      PDF

3. Bayesian ANN

   1. Discovery of Exogenous Variables in Data with More Variables Than Observations

      • Yasuhiro Sogawa, Shohei Shimizu, Aapo Hyvärinen, Takashi Washio, Teppei Shimamura, Seiya Imoto

      Pages 67-76

      PDF

   2. Bayesian Joint Optimization for Topic Model and Clustering

      • Tikara Hosino

      Pages 77-86

      PDF

   3. An Incremental Bayesian Approach for Training Multilayer Perceptrons

      • Dimitris Tzikas, Aristidis Likas

      Pages 87-96

      PDF

   4. Application of Semi-Bayesian Neural Networks in the Identification of Load Causing Beam Yielding

      • Bartosz Miller

      Pages 97-100

      PDF

   5. Globally Optimal Structure Learning of Bayesian Networks from Data

      • Kobra Etminani, Mahmoud Naghibzadeh, Amir Reza Razavi

      Pages 101-106

      PDF

4. Bio Inspired – Spiking ANN

   1. Action Potential Bursts Modulate the NMDA-R Mediated Spike Timing Dependent Plasticity in a Biophysical Model

      • Vassilis Cutsuridis

      Pages 107-116

      PDF

   2. Cell Microscopic Segmentation with Spiking Neuron Networks

      • Boudjelal Meftah, Olivier Lezoray, Michel Lecluse, Abdelkader Benyettou

      Pages 117-126

      PDF

   3. Investigation of Brain-Computer Interfaces That Apply Sound-Evoked Event-Related Potentials

      • Masumi Kogure, Shuichi Matsuzaki, Yasuhiro Wada

      Pages 127-134

      PDF

   4. Functional Connectivity Driven by External Stimuli in a Network of Hierarchically Organized Neural Modules

      • Vladyslav Shaposhnyk, Pierre Dutoit, Stephen Perrig, Alessandro E. P. Villa

      Pages 135-144

      PDF

   5. Transmission of Distributed Deterministic Temporal Information through a Diverging/Converging Three-Layers Neural Network

      • Yoshiyuki Asai, Alessandro E. P. Villa

      Pages 145-154

      PDF

th This volume is part of the three-volume proceedings of the 20 International Conference on Arti?cial Neural Networks (ICANN 2010) that was held in Th- saloniki, Greece during September 15–18, 2010. ICANN is an annual meeting sponsored by the European Neural Network Society (ENNS) in cooperation with the International Neural Network So- ety (INNS) and the Japanese Neural Network Society (JNNS). This series of conferences has been held annually since 1991 in Europe, covering the ?eld of neurocomputing, learning systems and other related areas. As in the past 19 events, ICANN 2010 provided a distinguished, lively and interdisciplinary discussion forum for researches and scientists from around the globe. Ito?eredagoodchanceto discussthe latestadvancesofresearchandalso all the developments and applications in the area of Arti?cial Neural Networks (ANNs). ANNs provide an information processing structure inspired by biolo- cal nervous systems and they consist of a large number of highly interconnected processing elements (neurons). Each neuron is a simple processor with a limited computing capacity typically restricted to a rule for combining input signals (utilizing an activation function) in order to calculate the output one. Output signalsmaybesenttootherunitsalongconnectionsknownasweightsthatexcite or inhibit the signal being communicated. ANNs have the ability “to learn” by example (a large volume of cases) through several iterations without requiring a priori ?xed knowledge of the relationships between process parameters.

• CUDA
• EEG
• Hidden Markov Model
• Markov Model
• algorithms
• artificial intelligence
• bayesian neural networks
• biomedical neural networks
• biometrics
• brain-computer interfaces
• classification
• computational neuroscience
• dimensionality reduction
• evolutionary algorithm
• filtering
• algorithm analysis and problem complexity

• Department of Informatics, TEI of Thessaloniki, Sindos, Greece

  Konstantinos Diamantaras

• School of Physics, Astronomy, and Informatics, Department of Informatics, Nicolaus Copernicus University, Torun, Poland

  Wlodek Duch

• Department of Forestry and Management of the Environment and Natural Resources, Democritus University of Thrace, Orestiada, Greece

  Lazaros S. Iliadis

Policies and ethics