IEEE Transactions on Neural Networks and Learning Systems: Volume 24, Issue 11, November 2013

1. Error Surface of Recurrent Neural Networks
Author(s): Phan, M.C. ; Hagan, M.T.
Pages: 1709-1721
 
2. Single-Channel Blind Separation Using Pseudo-Stereo Mixture and Complex 2-D Histogram
Author(s): Tengtrairat, N. ; Gao, B. ; Woo, W.L. ; Dlay, S.S.
Pages:  1722-1735

3. On the SVMpath Singularity
Author(s): Dai, J. ; Chang, C. ; Mai, F. ; Zhao, D. ; Xu, W.
Pages: 1736-1748

4. Multistability of Two Kinds of Recurrent Neural Networks With Activation Functions Symmetrical About the Origin on the Phase Plane
Author(s): Zeng, Z. ; Zheng, W.X.
Pages: 1749-1762

5. Safety-Aware Semi-Supervised Classification
Author(s): Wang, Y. ; Chen, S.
Pages: 1763-1772

6. Neural Network Approaches for Noisy Language Modeling
Author(s): Li, J. ; Ouazzane, K. ; Kazemian, H.B. ; Afzal, M.S.
Pages: 1773-1784

7. A New Discrete-Continuous Algorithm for Radial Basis Function Networks Construction
Author(s): Zhang, L. ; Li, K. ; He, H. ; Irwin, G.W.
Pages: 1785-1798

8. Finding Potential Support Vectors in Separable Classification Problems
Author(s): Varagnolo, D. ; Del Favero, S. ; Dinuzzo, F. ; Schenato, L. ; Pillonetto, G.
Pages: 1799-1813

9. Nonlinear Systems Identification and Control Via Dynamic Multitime Scales Neural Networks
Author(s): Fu, Z.-J. ; Xie, W.-F. ; Han, X. ; Luo, W.-D.
Pages: 1814-1823

10. Hierarchical Similarity Transformations Between Gaussian Mixtures
Author(s): Rigas, G. ; Nikou, C. ; Goletsis, Y. ; Fotiadis, D.I.
Pages: 1824-1835

11. Negative Correlation Ensemble Learning for Ordinal Regression
Author(s): Fernandez-Navarro, F. ; Gutierrez, P.A. ; Hervas-Martinez, C. ; Yao, X.
Pages: 1836-1849

12. Online Learning of a Dirichlet Process Mixture of Beta-Liouville Distributions Via Variational Inference
Author(s): Fan, W. ; Bouguila, N.
Pages: 1850-1862

13. Transfer Ordinal Label Learning
Author(s): Seah, C.-W. ; Tsang, I.W. ; Ong, Y.-S.
Pages: 1863-1876

14. Pseudo-Orthogonalization of Memory Patterns for Associative Memory
Author(s): Oku, M. ; Makino, T. ; Aihara, K.
Pages: 1877-1887

15. Multilabel Classification Using Error-Correcting Codes of Hard or Soft Bits
Author(s): Ferng, C.-S. ; Lin, H.-T.
Pages: 1888-1900

16. Multiclass Support Vector Machines With Example-Dependent Costs Applied to Plankton Biomass Estimation
Author(s): Gonzalez, P. ; Alvarez, E. ; Barranquero, J. ; Diez, J. ; Gonzalez-Quiros, R. ; Nogueira, E. ; Lopez-Urrutia, A. ; del Coz, J.J.
Pages: 1901-1905

17. Corrections to: “Estimator Design for Discrete-Time Switched Neural Networks With Asynchronous Switching and Time-Varying Delay”
Author(s): Zhang, D. ; Yu, L. ; Wang, Q.-G. ; Ong, C.
Pages:  1906

Call for Papers: WCCI 2014 Special Session "Intelligent Design for Reliable Cloud Computing"

Aim

The rapid progress in science and technology over the recent decade has provided a foundation for the development of advanced complex systems or networks. However, the increasing complexities and sophistications of the problems that we attempt to deal with today have led to new emerging challenges pertaining to design, implementation and evaluation of reliable complex systems or networks.

Today, cloud computing has become an increasingly important driving platform for business strategies and real world applications. In particular, it is now a major driving force for complex social, financial, environmental, cultural, and organisational events and activities. The reliability of cloud computing is particularly essential and beginning to garner new attentions. Recent incidents pertaining to the failure of mobile network services are excellent examples that illustrate the importance of system reliability in cloud computing. Disruptions in the Hotmail and Gmail services have resulted in significant email data loss by customers. The unintentional leak of sensitive personal information by Facebook has also violated user privacy. The reliability of cloud computing is thus an important but challenging topic that is required to be dealt with a great care. 

For cloud computing, network reliability is a critical issue affecting its overall performance. Network reliability is generally defined as the probability that a given amount of data is successfully delivered from a set of source nodes to a set of sink nodes under particular conditions. The network reliability problem is Non-deterministic Polynomial-time hard (NP-Hard). The computational effort of this problem grows exponentially with the increase of the number of nodes and the number of links in a network. A modern cloud may consist of thousands of nodes, which makes many well-known algorithms and innovative methods impracticable to estimate network reliability within limited time. Notably, cloud computing is dynamic, as network parameters (e.g., bandwidth or speed) often change quickly. Therefore, there is always a need to evaluate and predict the performance reliability of cloud computing against time-variant responses

To solve NP-Hard problems and to achieve better quality solutions, modern computational intelligence (e.g., evolutionary, Swarm intelligent and artificial neural network) have been proposed for complex optimization problems. Despite a significant amount of research on computational intelligence, there remain many open issues and intriguing challenges in the field. The aims of this symposium are to reflect on the latest advances in intelligent design for reliable network, to explore the emerging or future directions of reliability research and cloud computing in computational intelligence, and to raise the awareness of the computing community at large on this effective technology of intelligent design for reliable cloud computing. Specifically, we endeavor to demonstrate the current state-of-the-art concepts, theory and practice of intelligent and reliable design.

Scope

• Topics relevant to this special session include, but are not limited to, the following applications of computational intelligence, including Artificial Neural Networks, Fuzzy Systems, and Evolutionary Algorithms: Novel competitive, collaborative and cooperative frameworks of clouding computing model,
• Analytical and/or theoretical studies that enhance our understanding on the behaviors of Intelligent Design, 
• Intelligent Redundancy allocation Design,
• Formal and Probabilistic Single/Multi-Objective Intelligent Design, 
• Cognitive, Brain, individual learning, and social learning inspired Intelligent Design,
• Partial or full or meta-Lamarckian/Baldwinian, meta-learning, agent based computational intelligence in designing reliable clouding computing,
• Computational intelligence frameworks using surrogate or approximation methods in designing reliable clouding computing, 
• Computational intelligence for computationally expensive problems and real-world applications,
• Knowledge incorporation in clouding computing.

Deadline

The deadline for submissions to this special session is 20 December 2013.

Information for Authors

1)    Information on the format and templates for papers can be found here:
       http://www.ieee-wcci2014.org/Paper%20Submission.htm
2)    Papers should be submitted via the IJCNN 2014 paper submission site:
       http://ieee-cis.org/conferences/ijcnn2014/upload.php
3    Select the Special Session name in the Main Research topic dropdown list
4)    Fill out the input fields, upload the PDF file of your paper and finalize your submission by the deadline of December 20, 2013

Organisers

• Dr. Wei-Chang Yeh, National Tsing Hua University, Taiwan. yeh@ieee.org
• Dr. G. Levitin, The Israel Electric Corp., Israel. levitin@iec.co.il
• Dr. Hoang Pham, Rutgers, United State. hopham@rci.rutgers.edu
• Dr. Jiankun Hu, University of New South Wales, Australia. J.Hu@adfa.edu.au
• Dr. Jinjun Chen, University of Technology, Sydney. Jinjun.Chen@uts.edu.au

Call for Papers: WCCI 2014 Special Session "Evolutionary Developmental Systems"

Motivation and Scope

Computational modeling of biological development has received increasing interests in evolutionary computation, artificial life and computational systems biology. In the evolutionary computation community, evolutionary algorithms using an indirect coding or generative coding are believed to be more scalable in evolving highly complex systems, compared to those using a direct coding. A variety of developmental and generative models have been proposed, ranging from a set of re-writing rules to gene regulatory network model including metabolic reactions.

Evolutionary  developmental  systems  (Evo-Devo)  are  of  great  interest  not  only  to  efficient optimization of large-scale systems, but also to the understanding of the evolution of the body plan and neural control in living systems. This special session aims to promote cross-disciplinary research in evolutionary computation, artificial life, computational neuroscience and computational systems biology. Topics of the special session include but are not limited to:

• Scalable evolutionary algorithms using indirect or generative encoding
• Evolution of computational models for morphological development
• Evolutionary development of neural systems, neural plasticity
• Morphogenetic self-organizing systems, morphogenetic robotics
• Analysis of evolvability and robustness of developmental systems
• Evolutionary reconstruction of gene regulatory networks
• Benchmarking evolutionary developmental systems

Submission:

All papers are to be submitted electronically at:     http://ieee-cis.org/conferences/cec2014/upload.php. Please choose “Special Session on Evolutionary Developmental Systems" as the topic of your paper. Please also notify the organizers of your submission. Submission deadline: December 20, 2013.

Special Session Organizers:

Dr Hyondong Oh
Department of Computing, University of Surrey
Guildford, GU2 7XH, United Kingdom
Email:  h.oh@surrey.ac.uk

Prof. Yaochu Jin
Department of Computing, University of Surrey
Guildford, GU2 7XH, United Kingdom
Email:  yaochu.jin@surrey.ac.uk

Prof. Larry Bull
Department of Computer Science and Creative Technologies
University of the West of England Bristol, BS16 1QY, United Kingdom
Email:  Larry.Bull@uwe.ac.uk

Call for Papers: WCCI 2014 Special Session "Dynamic Multi-objective Optimization"

Aim

Most real-world optimization problems have more than one objective, with at least two objectives that are in conflict with one another. The conflicting objectives of the optimization problem lead to an optimization problem where a single solution does not exist, as is the case with single-objective optimization problems (SOOPs). In stead of a single solution, a set of optimal trade-off solutions exists, referred to as the Pareto-optimal front (POF) or Pareto front. This kind of optimization problems are referred to as multi-objective optimization problems (MOOPs).

In many real-world situations the environment does not remain static, but is dynamic and changes over time. However, in recent years most research focussed on either static MOOPs or dynamic SOOPs. When solving dynamic multi-objective optimization problems (DMOOPs) an algorithm has to track the changing POF over time, while finding solutions as close as possible to the true POF and maintaining a diverse set of solutions. Some of the major challenges in the field of dynamic multi-objective optimization (DMOO) are a lack of a standard set of benchmark functions, a lack of standard performance measures, issues with performance measures currently being used for DMOO and a lack of a comprehensive analysis of existing algorithms applied to DMOO.

Therefore, this special session aims to highlight the latest developments in DMOO in order to bring together researchers from both academia and industry to address the above mentioned challenges and to explore future research directions for the field of DMOO.

Scope

We invite authors to submit original and unpublished work on DMOO. Topics of interest include, but are not limited to:

• DMOO Benchmark functions
• Performance measures for DMOO
• Constrained DMOO
•  New DMOO algorithms
• Comparative studies of DMOO algorithms
• Theoretical aspects of DMOO algorithms
• Real-world applications of DMOO algorithms
• Approaches to handle outlier solutions

It should be noted that approaches that change the DMOOP to a DSOOP are outside the scope of this special session.

Deadline

Paper submission deadline is 20 December 2013.

Information for Authors

• Papers should be submitted via the CEC 2014 paper submission site: http://ieee-cis.org/conferences/cec2014/upload.php 
• Select the Special Session name in the Main Research Topic dropdown list. 
• Information on the format and templates for papers can be found at:  http://www.ieee-wcci2014.org/Paper%20Submission.htm 
• Information on the Special Session can be found at: https://sites.google.com/site/cec2014dmooss

Organizers

Dr. Mardé Helbig
Meraka Institute
Council for Scientific and Industrial Research (CSIR)
Pretoria, 0184, South Africa
Email: mhelbig@csir.co.za

Prof. Andries Engelbrecht
South African Research Chair in Artificial Intelligence
Department of Computer Science, School of Information Technology
University of Pretoria
Pretoria, 0002, South Africa
Email: engel@cs.up.ac.za

Call for Papers: WCCI 2014 Special Session "Evolutionary Computation for Grouping and Graph-based Clustering"

Organizers

David Camacho    (Universidad Autonoma de Madrid, Spain)
Sancho Salcedo-Sanz     (Universidad de Alcalá, Spain)

A. The topic

This special session will look for high quality papers where evolutionary-based algorithms have been applied into real, complex problems related to groups and clusters detection, specially in dynamic environments (i.e. communities in social-based computing, traffic in wireless sensor networks, and so many others). Therefore, the main goals of this special session will be two-fold: On the one hand, to look for new algorithms and techniques proposals based on EC, which could be applied to problems related to grouping and clustering problems. On the other hand, to look for new application domains, and real problems, where the application of EC have demonstrated an outstanding performance against other traditional approaches.

Paper acceptance and publication will be judged on the basis of their quality and relevance to the symposium themes, clarity of presentation, originality and accuracy of results and proposed solutions.

Topics include, but are not limited to:

• Evolutionary Grouping and Clustering.
• Practical evolutionary applications for grouping and communities detection (i.e. social-based mining, …).
• Data mining and knowledge discovery in distributed settings based on evolutionary and graph-based techniques.
• EC computation and grouping/clustering methods in real problems (videogames, unmanned systems, e-business/e-commerce, e-learning, e-health, e-science, e-government, crisis management, etc…).
• Swarm Intelligence and Evolutionary Computation in grouping and graph-based clustering problems.
• Theoretical models for grouping and graph-based clustering based on EC computation.
• Evolutionary Grouping and Clustering focused on semantic applications such as automatic summarization, recommender systems, topic identification, etc.
• Computational Intelligence graph-based applications.

B. Submission Guidelines for Special Session Papers

The authors intended to contribute to IEEE WCCI 2014 Special Sessions are kindly recommended to follow the manuscript style information and templates of regular IEEE WCCI 2014 papers (http://www.ieee-wcci2014.org/Paper%20Submission.htm).

Please note that each Special Session is specifically and exclusively related to one of the three conferences composing the IEEE WCCI 2014: IJCNN2014, FUZZ-IEEE2014, and IEEE CEC 2014.

When submitting your manuscripts, authors are recommended to follow these steps:

1.    Identify the conference associated to the Special Session. For this session: IEEE CEC 2014;
2.    Go to the related conference submission website (http://ieee-cis.org/conferences/cec2014/upload.php);
3.    Select the Special Session name in the Main Research topic dropdown list (SS30. EC30: Evolutionary Computation for Grouping and Graph-based Clustering);
4.    Fill out the input fields, upload the pdf file and finalize the submission by December 20, 2013.

C. Important deadlines:

December 20, 2013    Paper submission deadline
March 15, 2014          Author notification of acceptance or rejection
April 15, 2014             Deadline for receipt of final manuscript

D. Contact information:

If you have any questions related to this special session, please send an email to:
david.camacho@uam.es

Call for Papers: WCCI 2014 Special Session "Differential Evolution: Past, Present and Future"

Aim and Scope

Differential evolution (DE) emerged as a simple and powerful stochastic real-parameter optimizer more than a decade ago and has now developed into one of the most promising research areas in the field of evolutionary computation. The success of DE has been ubiquitously evidenced in various problem domains, e.g., continuous, combinatorial, mixed continuous-discrete, single-objective, multi-objective, constrained, large-scale, multimodal, dynamic and uncertain optimization problems. Furthermore, the remarkable efficacy of DE in real-world applications significantly boosts its popularity.

Over the past decades, numerous studies on DE have been carried out to improve the performance of DE, to give a theoretical explanation of the behavior of DE, to apply DE and its derivatives to solve various scientific and engineering problems, as demonstrated by a huge number of research publications on DE in the forms of monographs, edited volumes and archival articles. Consequently, DE related algorithms have frequently demonstrated superior performance in challenging tasks. It is worth noting that DE has always been one of the top performers in previous competitions held at the IEEE Congress on Evolutionary Computation. Nonetheless, the lack of systematic benchmarking of the DE related algorithms in different problem domains, the existence of many open problems in DE, and the emergence of new application areas call for an in-depth investigation of DE.

This special session aims at bringing together researchers and practitioners to review and re-analyze past achievements, to report and discuss latest advances, and to explore and propose future directions in this rapidly emerging research area. Authors are invited to submit their original and unpublished work in the areas including, but not limited to:

• DE for continuous, discrete, mixed continuous-discrete, single-objective, multi-objective, constrained, large-scale, multiple optima seeking, dynamic and uncertain optimization
• Review, comparison and analysis of DE in different problem domains
• Experimental design and analysis of DE
• Studies on initialization, reproduction and selection schemes in DE
• Studies on control parameters (e.g. scale factor, crossover rate, population size) in DE
• Self-adaptive and tuning-free DE
• Parallel and distributed DE
• Theory of DE
• Synergy between DE and learning techniques 
• Hybridization of DE with other optimization techniques
• Interactive DE
• Application of DE in real-world applications

Important Dates

Paper submissions    December 20, 2013
Notification of acceptance    March 15, 2014
Please refer to: http://www.ieee-wcci2014.org/ for the latest information.

Paper Submission

All papers should be submitted electronically through:
http://ieee-cis.org/conferences/cec2014/upload.php
When you submit your papers to our special session, please select "SS18.EC18: Differential Evolution: Past, Present and Future" as the Main research topic*.

Organizers

Kai Qin
RMIT University, Australia
Email: kai.qin@rmit.edu.au

Kenneth V. Price
Consultant, USA
Email: kvprice@jccomp.com

Swagatam Das
Electronics and Communication Sciences Unit, Indian Statistical Institute, India
Email: swagatamdas19@yahoo.co.in

Jouni Lampinen
Department of Computer Science, University of Vaasa, Finland
Email: jouni.lampinen@uwasa.fi

Call for Papers: WCCI 2014 Special Session "Fuzzy decision-making: Consensus and Missing Preferences"

Aim: 

The development of formal mathematical models to support experts in making decisions is of great importance to assure the validity of the actions derived from a decision outcome is theoretically sound. This is of special relevance in decision contexts where the information on the problem at hand is not amenable to be modelled in a quantitative and precise way. Another issue to be addressed is that of inconsistency of information and the dynamic nature of the decision making process itself. This type of decision-making is now being described as decision-making under uncertainty in inconsistent and dynamic environments.

This special session aims at gathering researchers with an interest in the research area described above. Specifically, we are interested in contributions towards the development of consensus models for such decision-making problems, as well as formal approaches that are able to support incomplete or missing information. Contributions to this special session are expected to pay special attention to the rigorous motivation of the approaches put forward and to support all aspects of the models developed with a corresponding theoretical sound framework. Straight approaches lacking such scientific approach are discouraged.

Scope:  

Indicative, but not complete, lists of topics covered in this focus session include:

• Consensus in group decision-making
• Consistency in fuzz preference modeling
• Missing preferences in fuzzy decision-making
• Aggregation of fuzzy preferences
• Consensus measures
• Consensus and fuzzy ontologies
• Consensus software tools
• Fuzzy decision in Web 2.0

Deadline

The deadline for submissions to this special session is 20 December 2013.

Information for Authors

1.    Information on the format and templates for papers can be found here:
       http://www.ieee-wcci2014.org/Paper%20Submission.htm
2.    Papers should be submitted via the IJCNN 2014 paper submission site:
       http://ieee-cis.org/conferences/fuzzieee2014/upload.php
3.    Select the Special Session name (FZ08) in the Main Research topic dropdown list
4.    Fill out the input fields, upload the PDF file of your paper and finalize your submission by the deadline of December 20, 2013

Organisers

Professor Francisco Chiclana (http://tinyurl.com/fchiclana), De Montfort University, Leicester, UK, chiclana@dmu.ac.uk
Professor Enrique Herrera-Viedma (http://tinyurl.com/herrera-viedma), University of Granada, Spain, viedma@decsai.ugr.es
Associate Professor Jian Wu (http://tinyurl.com/jianwu), Zhejiang Normal University, China, jyajian@163.com