Parallel and Distributed Evolutionary Computation in the Cloud Era

Recent trend in distributed systems such as cloud computing, grid computing, and peer-to-peer systems, goes toward a global infrastructure of information resources that can be utilized through the Internet. Especially, infrastructure as a service (IaaS) is becoming popular such as Amazon EC2, S3, and so on, to provide with virtually infinite number of virtual machines and storages just by calling a web-service APIs through the Internet.

In evolutionary computation, environment is considered essential to realize “evolution” since it is necessary to have enough resources and complexities in the environment for the individuals to evolve. Cloud systems may even offer tens of thousands of virtual machines, terabytes of memories and exabytes of storages. Current trend toward many-core architecture increases the number of cores even more dramatically: we may have more than a million of cores to offer extremely massive parallelization.

In this special session, we discuss parallel and distributed evolutionary computation in the cloud era such as implementation of massively parallel evolutionary algorithms employing cloud computing systems and services, parallel implementation of evolutionary algorithms on many-core architectures including GPUs, and we also welcome any types of parallel and distributed evolutionary computation on any “informal” types of computing environment in this special session including the following themes.

• Implementation of parallel and distributed evolutionary computation in cloud computing systems and/or services
• Implementation of massively parallel evolutionary computation on many-core architecture such as GPUs
• Parallel and distributed evolutionary machine learning techniques
• Design and theory of scalable evolutionary algorithms
• Development of parallel and distributed evolutionary computation framework in cloud computing systems
• Applications of parallel and evolutionary computation techniques in cloud or other modern computing environment
• Applications of EC and other bioinspired paradigms to peer to peer systems, and distributed EC algorithms that use them.
• Voluntary, sneaky or parasite computing using the browser or other widely available infrastructure. Zero-cost distributed computing.

Organizers:

Masaharu Munetomo, Information Initiative Center, Hokkaido University, Japan. munetomo@iic.hokudai.ac.jp

Masaharu Munetomo is a professor and vice-director of Information Initiative Center, Hokkaido University, and a chief architect of “Hokkaido University Academic Cloud”, the largest academic cloud system in Japan to conduct research projects realizing a national inter-cloud infrastructure. He has published more than 100 papers in the field of evolutionary computation including advanced evolutionary algorithms based on linkage identification, and distributed systems including cloud computing. He co-organized a special session “EC on Many-core Architecture to Solve Large-scale Problems” in CEC2011 at New Orleans, “Parallel and Distributed Evolutionary Computation in the Cloud Era” in CEC2012 at Cancun, and a member of program committee of CEC since 2002.

Juan Julián Merelo Guervós, department of Computer Architecture and Technology of the University of Granada, Spain.
jmerelo@geneura.ugr.es

Juan Julián Merelo Guervós was born in Úbeda, Jaén, España, in March 10th, 1965. Obtained a degree in Physics (majoring in Theoretical Physics) from the University of Granada in 1988 and his PhD in Physics in 1994 from the same University. He is professor from November 2009, attached to the department of Computer Architecture and Technology of the University of Granada. His research topics are mainly within the area of soft computing, including neural networks, evolutionary algorithms, complex networks and combinations of them. He has been working also on implementations of the above mentioned algorithms using overlay networks and other distributed computing methods, such as peer to peer systems. He has been organizer of several workshops, including one on Informal Distributed Evolutionary Computation at CEC 2011, and coorganizer of several Parallel Problem Solving from Nature, including chairing PPSN 2002 which was held at Granada.

Call for Papers: WCCI 2014 Workshop "Advances in Learning from/with Multiple Learners"

Overview
This workshop will cover original and pioneering contributions, theory as well as applications on creating and combining learning models, and aim at an inspiring discussion on the recent progress and the future developments. Learners based on different paradigms can be combined for improved accuracy. Each learning method presupposes some model of the world that comes with a set of assumptions which may lead to error if they do not hold. Lea
rning is an ill-posed
problem and with finite data each algorithm converges to a different soluti
on and fails under
various circumstances. In learning models combinations, it is possible to make
a distinction
between two main modes: ensemble and modular. For an ensemble approach, several solutions to
the same task, or task component, are combined to yield a more reliable es
timate. In the modular
approach, particular aspects of a task are dealt with by specialist c
omponents before being
recombined to form a global solution. In this workshop, the reasons for combining learning
models and the main methods for creating and combining them will be presente
d. Also, the
effectiveness of these methods will be discussed considering the concept
s of diversity and
selection of these approaches.
The workshop will strive to bring together the practitioners of these approaches i
n an attempt to
study a unified framework under which these interactions can be studied, understood,
and
formalized.
Relevant topics
The following is a partial list of relevant topics (not limited to) for the workshop:
·Bagging approaches
· Boosting techniques
· Collaborative clustering
· Collaborative learning
· Cooperative learning
·Ensemble methods
· Hybrid systems
· Mixtures of distributions
· Mixtures of experts
· Modular approaches
·Multi-task learning
· Multi-view learning
· Task decomposition
· Transfer learning with multiple sources
Submission guidelines and special issue
Prospective authors are invited to submit papers according to the IEEE format.
All submissions
should follow the specifications of WCCI 2014. Manuscripts will be submitt
ed through the IEEE
WCCI 2014 paper submission website and will be subject to the same peer-re
view procedure as
the WCCI2014 regular papers. Accepted contributions will be part of the IJCNN confe
rence
proceedings, which will be available in IEEE Xplore.
Authors of the most insightful papers, already accepted for publication, will be
invited to submit
an extended version of their work to a Special Issue of the Neurocomputing journal (IF: 1.634).
Organizers
· Younès Bennani, Paris 13 University
· Guénael Cabanes, Paris 13 University
·Antoine Cornuéjols, AgroParisTech
· Marc Gelgon, Nantes University
· Nistor Grozavu, Paris 13 University
· Cédric Wemmert, University of Strasbourg
Important Dates
· Submission deadline: December 20, 2013
· Notification of acceptance: March 15, 2014
· Camera-ready deadline: April 15, 2014
·
Workshop date: July 5, 2014
Tentative
Program Committe:
Younès Bennani, Paris 13 University, Villetaneuse, France
Guénael Cabanes, Paris 13 University, Villetaneuse, France
Antoine Cornuéjols, AgroParisTech, Paris, France
Marc Gelgon, Nantes University, Nantes, France
Agostino Gibaldi, University of Genova, Italy
Nistor Grozavu, Paris 13 University, Villetaneuse, France
JunBin Gao, Charles Sturt University, Bathurst, Australia
Tomasz Maszczyk, Nicolaus Copernicus University, Toru
, Poland
Vladimir Nikulin, Vyatka State University, Kirov, Russia
Shogo Okada, Tokyo Institute of Technology, Japan
Seiichi Ozawa, Kobe University, Japan
Asim Roy, Arizona State University, USA
Daming Shi, Middlesex University, London, UK
Tatiana Tambouratzis, University of Piraeus, Piraeus, Greece
Draguna Vrabie, UTRC, USA
Cédric Wemmert, University of Strasbourg, Strasbourg, France

Call for Papers: WCCI 2014 Workshop "Computational Energy Management in Smart Grids"

The International Workshop on Computational Energy Management in Smart Grids (CEMiSG 2014) will be held on July 6th, 2014 in Beijing, China as inside the 2014 IEEE World Congress on Computational Intelligence (WCCI 2014). The Workshop is oriented to explore the new frontiers and challenges within the Computational Intelligence research area, including in particular Neural Networks, Evolutionary Computation and Soft Computing based solutions, for the optimal usage and management of energy resources in Smart Grid applicable scenarios. The Workshop will be a proficient discussion table within the WCCI conference, which attracts the most famous researchers in the Computational Intelligence field worldwide.

ORGANIZERS

• Derong Liu, Chinese Academy of Sciences, China
• Stefano Squartini, Università Politecnica delle Marche, Italy
• Francesco Piazza, Università Politecnica delle Marche , Italy
• Dongbin Zhao, Chinese Academy of Sciences, China
• Haibo He, University of Rhode Island, USA

SCOPE

As the world population increases, the sustainable usage of natural resources becomes an issue that humanity and technology are urgently asked to face. Energy represents a relevant example from this perspective and the strong demand coming from developed and developing countries shoved the scientists worldwide to intensify their studies on renewable energy resources. At the same time, due to the increasing complexity of MV and LV distribution grids on which distributed electrical generators based on renewables have to be included, a growing interest has been oriented to the development of smart systems able to optimally manage the usage and the distribution of energy among the population with the objective of minimizing wasting and the economic impact even at family consumption level. This yielded in a flourishing scientific literature on sophisticated algorithms and systems aimed at introducing intelligence within the energy grid, with also several effective solutions already available in the market. The task is surely challenging and multi-faceted. Indeed the different needs of the heterogeneous grid costumers and the different peculiarities of energy sources to be included in the grid itself have to be taken into account. Moreover several ways of intervention are feasible, as the ones indicated in the US Energy Independence and Security Act of 2007 as reference: self-healing capability, fault-tolerance on resisting attack, integration of all energy generation and storage, dynamic optimization of grid operation and resources with full cyber-security, incorporation of demand-response, demand-side resources and energy-efficient resources, actively client participation in the grid operations by providing timely information and control options, improvement of reliability, power quality, security and efficiency of the electricity infrastructure.

A multi-disciplinary coordinated action is required to the scientific communities operating in the Electrical and Electronic engineering, Computational Intelligence, Digital Signal Processing and Telecommunications research fields to provide adequate technological solutions to these issues having in mind the more and more stringent constraints we have to consider in terms of environment sustainability. In particular, the organizers of this Workshop wants to explore the new frontiers and challenges within the Computational Intelligence research area, including in particular Neural Networks, Evolutionary Computation and Soft Computing based solutions, for the optimal usage and management of energy resources in Smart Grid applicative scenarios.

TOPICS

Workshop topics include, but are not limited to:

• Smart Home Energy Management
• Computational Intelligence for Smart Grids
• Learning Systems for Smart Grid Optimization Tasks
• Neural Networks based algorithms for Complex Energy Systems
• Evolutionary Algorithms in Energy Applications
• Soft Computing in Renewable Energy Systems
• Energy Resource and Task Scheduling
• Building Energy Consumption Forecasting
• Demand-side Management
• Short-term Load Forecasting
• Neural Networks for Time Series Prediction in Smart Grid Applications
• Non-intrusive Electrical Load Analysis
• Hybrid Battery Management
• Brain inspired algorithms for Energy Efficiency

TECHNICAL PROGRAMME COMMITTE

• Pietro Burrascano, University of Terni, Italy
• Zhaohui Hu, Chinese Academy of Sciences, China
• Robert John, University of Nottingham, UK
• Elias Kyriadikes, University of Cyprus, Cyprus
• Andrew Kusiak, University of Iowa, USA
• Chengdong Li,  Shandong Jianzhu University, China
• Kang Li, Queen’s University Belfast, UK
• Honghai Liu, University of Portsmouth, UK
• Sauro Longhi, Polytechnic University of Marche, Italy
• Danilo Mandic, Imperial College, UK
• Stephen G. Matthews, University of Bristol, UK
• Michael Negnevitsky, University of Tasmania, Australia
• Peter Palensky, Austrian Institute of Technology, Austria
• Dianwei Qian, North China Electric Power University, China
• Wei Qiao, University of Nebraska–Lincoln, USA
• Manuel Roveri, Polytechnic of Milan, Italy
• Pierluigi Siano, University of Salerno, Italy
• Gerard Smit, University of Twente, Netherlands
• Dipti Srinivasan, National University of Singapore, Singapore
• Zita Vale, Polytechnic of Porto, Portugal
• Qinglai Wei, Chinese Academy of Sciences, China
• Jinyu Wen, Huazhong University of Science and Technology, China

SUBMISSION GUIDELINES

Prospective authors are invited to submit papers according to the IEEE format. All submissions should be according to the specifications of the IEEE WCCI 2014. Manuscripts will be submitted through the IEEE WCCI 2014 paper submission website and will be subject to the same peer-review review procedure as the IEEE WCCI2014 regular papers. Accepted contributions will be part of the IJCNN conference proceedings, which will be available in IEEE Xplore. A Special Issue of the Neurocomputing journal (IF: 1.634) is also foreseen.

IMPORTANT DATES

• Submission deadline: December 20, 2013
• Notification of acceptance: March 15, 2014
• Camera-ready deadline: April 15, 2014
• Workshop date: July 5, 2014

How to publish your research: Video of Professor Garrison Greenwood

Professor Garrison Greenwood talks about how to publish your research in the IEEE Transactions on Evolutionary Computation. This talk was part of a panel session at the CEC 2013 conference.

Call for Papers: WCCI 2014 Special Session "Complex Fuzzy Sets and Logic"

Organizers: Scott Dick, Dan Tamir

Complex fuzzy sets are an extension to type-1 fuzzy sets in which membership grades are complex numbers. Likewise, complex fuzzy logic is an isomorphic family of multi-valued logics whose truth values are complex numbers. In the ten years since these concepts were first introduced, further theoretical investigations and a number of applications have made complex fuzzy sets and logic a lively and growing research area. This special session will provide a forum to consolidate the community of researchers in this area, share our current ideas, reflect on future directions, and communicate our ideas and vision to the larger Computational Intelligence community. As such, we welcome submissions on all aspects of complex fuzzy sets or complex fuzzy logic, including but not limited to:

• Theory of complex fuzzy logic
• Complex fuzzy sets
• Complex fuzzy inferential systems
• Elicitation of complex fuzzy rules
• Machine learning for complex fuzzy inferential systems
• Hybridizations of complex fuzzy sets and logic with other CI technologies
• Data mining with complex fuzzy sets and logic
• Applications of complex fuzzy sets and logic
• Complex fuzzy logic hardware

AUTHOR INSTRUCTIONS

Papers for the special session are limited to a maximum of 8 pages in length, prepared using the standard WCCI paper templates (double-column format), available at http://www.ieee-wcci2014.org/Paper%20Submission.htm

When you are ready to submit your paper, please proceed to the FUZZ-IEEE submission sub-site at http://ieee-cis.org/conferences/fuzzieee2014/upload.php, and upload your paper there. From the “Main Research Topic” drop-down menu, select “S11. FZ11: Complex Fuzzy Sets and Logic.” Your paper will then proceed through the standard reviewing process for all WCCI papers.

IMPORTANT DATES

All special sessions at WCCI adhere to the same deadlines as regular papers, as follows:
Paper Submission: Dec. 20, 2013
Notification of Acceptance: Mar. 15, 2014
Final Submission: Apr. 15, 2014
Early Registration: Apr. 15, 2014

IEEE Transactions on Neural Networks and Learning Systems: Volume 24, Issue 12, December 2013

1. Canonical Correlation Analysis on Data With Censoring and Error Information
Author(s): Sun, J. ; Keates, S.
Pages: 1909-1919

2. Highly Accurate Moving Object Detection in Variable Bit Rate Video-Based Traffic Monitoring Systems
Author(s): Huang, S.-C. ; Chen, B.-H.
Pages: 1920-1931

3. Recurrent Neural Collective Classification
Author(s): Monner, D.D. ; Reggia, J.A.
Pages: 1932-1943

4. Online Selective Kernel-Based Temporal Difference Learning
Author(s): Chen, X. ; Gao, Y. ; Wang, R.
Pages: 1944-1956

5. Stability and Synchronization of Discrete-Time Neural Networks With Switching Parameters and Time-Varying Delays
Author(s): Wu, L. ; Feng, Z. ; Lam, J.
Pages: 1957-1972

6. Artificial Endocrine Controller for Power Management in Robotic Systems
Author(s): Sauze, C. ; Neal, M.
Pages: 1973-1985

7. Operator Control of Interneural Computing Machines
Author(s): Shih, M.-H. ; Tsai, F.-S.
Pages: 1986-1998

8. Multiple Graph Label Propagation by Sparse Integration
Author(s): Karasuyama, M. ; Mamitsuka, H.
Pages: 1999-2012

9. Universal Blind Image Quality Assessment Metrics Via Natural Scene Statistics and Multiple Kernel Learning
Author(s): Gao, X. ; Gao, F. ; Tao, D. ; Li, X.
Pages: 2013-2026

10. H_{\infty } State Estimation for Complex Networks With Uncertain Inner Coupling and Incomplete Measurements
Author(s): Shen, B. ; Wang, Z. ; Ding, D. ; Shu, H.
Pages: 2027-2037

11. Goal Representation Heuristic Dynamic Programming on Maze Navigation
Author(s): Ni, Z. ; He, H. ; Wen, J. ; Xu, X.
Pages: 2038-2050

12. Accelerated Canonical Polyadic Decomposition Using Mode Reduction
Author(s): Zhou, G. ; Cichocki, A. ; Xie, S.
Pages: 2051-2062

13. Hardware Friendly Probabilistic Spiking Neural Network With Long-Term and Short-Term Plasticity
Author(s): Hsieh, H.-Y. ; Tang, K.-T.
Pages: 2063-2074

14. Neural Network Architecture for Cognitive Navigation in Dynamic Environments
Author(s): Villacorta-Atienza, J.A. ; Makarov, V.A.
Pages: 2075-2087

15. An Equivalence Between Adaptive Dynamic Programming With a Critic and Backpropagation Through Time
Author(s): Fairbank, M. ; Alonso, E. ; Prokhorov, D.
Pages: 2088-2100

16. Semisupervised Multitask Learning With Gaussian Processes
Author(s): Skolidis, G. ; Sanguinetti, G.
Pages: 2101-2112

17. Nonlinear Projection Trick in Kernel Methods: An Alternative to the Kernel Trick
Author(s): Kwak, N.
Pages: 2113-2119

How to publish your research: Video of Professor Kay Chen Tan

A video of a talk by Professor Kay Chen Tan as part of a panel session at the CEC 2013 conference. In this video he describes the IEEE CIS Computational Intelligence Magazine.