Tuesday 14 October 2014

IEEE Computational Intelligence Magazine Special Issue on "Computational Intelligence for Brain Computer Interfaces"

Aims and Scope

Brain Computer Interfaces (BCI) aims at establishing a one or two-way communication protocol between the human brain and an electronic device. The research umbrella of BCI has different names and overlaps with different research areas that evolved under the wider objective of connecting human data to an electronic device of some sort. Some of these areas include: adaptive automation, augmented cognition, brain-machine interface, human-machine symbiosis, and human-computer symbiosis.

The last decade has witnessed a rise in the number of researchers working on BCI. With the advances of sensor technologies, efficient signal processing algorithms, and parallel computing, it was possible to finally realize the dream of many researchers who talked about the concept in one form or another in the sixties and seventies including J.C.R. Licklider, R.B. Rouse, and others. Different sensor and measurement technologies are evolving rapidly from the classical functional magnetic resonance imaging (fMRI), functional near infrared (fNIR), Electroencephalography (EEG), to complex integrated psycho-physiological sensor arrays.

Researchers in Computational Intelligence have been better situated than ever to extract knowledge from these signals, transform it to actionable decisions, and designing the intelligent machine that has long been promised and is now overdue. Success has been seen in many medical applications including assisting people on wheelchairs, stroke rehabilitation, and epileptic seizures. In the non-medical domain, BCI has been used for computer games, authentication in cyber security, and air traffic control.

This special issue aims at showcasing the most exciting and recent advances in BCI and related topics. The guest editors invite submissions of previously unpublished, recent and exciting research on BCI. The special issue welcomes survey, position, and research papers

Topics of Interest include:
  • Adaptive control schemes for BCI
  • Applications
  • Augmented cognition and adaptive aiding using BCI
  • Big data for brain mining
  • Collaborative multi-humans BCI environments
  • Computational intelligence applications for BCI
  • Data and signal processing techniques for BCI applications
  • Evolutionary algorithms for BCI
  • Fusion of heterogeneous psycho-physiological sensors
  • Fuzzy logic for BCI
  • Neuroplasticity induced by brain-computer interactions
  • Neural networks for BCI
  • Novel sensor technologies for BCI
  • Related computational intelligence methods for BCI
  • Situation awareness systems for BCI applications
  • Swarm techniques for BCI
  • Other closely related topics on computational intelligence for BCI

Submission Process

The maximum length for the manuscript is typically 25 pages in single column format with double-spacing, including figures and references. Authors should specify on the first page of their manuscripts the corresponding author’s contact and up to 5 keywords. Submission should be made via https://www.easychair.org/conferences/?conf=ieeecimbci2016

Important Dates (for February 2016 Issue)

15th May, 2015: Submission of Manuscripts
15th July, 2015: Notification of Review Results
15th August, 2015: Submission of Revised Manuscripts
15th September, 2015: Submission of Final Manuscripts
February 2016: Special Issue Publication

Guest Editors

Hussein A. Abbass, The University of New South Wales, School of Engineering and Information Technology, Canberra, ACT 2600, Australia.
Cuntai Guan, Institute for Infocomm Research (I2R), 1 Fusionopolis Way, Fusionopolis, 138632, Singapore.
Kay Chen Tan, National University of Singapore, Department of Electrical and Computer Engineering, 4 Engineering Drive, 117583, Singapore.

Monday 13 October 2014

IEEE TNNLS Special Issue on "Learning in Neuromorphic Systems and Cyborg Intelligence"

Emulating brain-like learning performance has been a key challenge for research in neural networks and learning systems, including recognition, memory and perception. In the last few decades, a variety of approaches for brain-like learning and information processing have been proposed, including approaches based on sparse representations or  hierarchical/deep architectures. While capable of achieving impressive performance, these methods still perform poorly compared to biological systems under a wide variety of conditions. With the availability of neuromorphic hardware providing a fundamentally different technique for data representation, neuromorphic systems, using neural spikes to represent the outputs of sensors and for communication between computing blocks, and using spike timing based learning algorithms, have shown appealing computing characteristics.  However, current neuromorphic learning systems cannot yet achieve the performance figures comparable to what machine learning approaches can offer. Neuromorphic systems are also compatible with another framework called cyborg intelligence. Cyborg intelligence aims to deeply integrate machine intelligence with biological intelligence by connecting machines and living beings via brain-machine interfaces, enhancing strengths and compensating for weaknesses by combining the biological cognition capability with the machine computational capability. In cyborg intelligence, the real-time interaction and exchange of information between biological and artificial neural systems is still an important open challenge, and existing learning approaches would not be able to meet such a challenge. The goal of the special issue is to consolidate the efforts for developing a suitable learning framework for neuromorphic systems and cyborg intelligence and promote research activities in this area.

Scope of the Special Issue

We invite original contributions related to learning in neuromorphic systems and cyborg intelligence, from theories, algorithms, modelling and experiment studies to applications. Topics include but are not limited to: 

  • Cognitive computing and cyborg intelligence
  • Neuromorphic information/signal processing
  • Brain-inspired data representation models
  • Neuromorphic learning and cognitive systems
  • Co-learning in bio-machine systems
  • Spike-based sensing and learning
  • Neuromorphic sensors and hardware systems
  • Intelligence for embedded systems
  • Cognition mechanisms for big data
  • Embodied cognition and neuro-robotics.

Important Dates

15 Nov 2014 – Deadline for manuscript submission
15 Feb 2015 – Notification of authors
15 Apr 2015–  Deadline for submission of revised manuscripts
15 May 2015 – Final decision

Guest Editors

Zhaohui Wu, Zhejiang University, China (wzh@zju.edu.cn)
Ryad Benosman, University of Pierre and Marie Curie, France (ryad.benosman@upmc.fr)
Huajin Tang, Institute for Infocomm Research, Singapore and Sichuan University  (huajin.tang@ieee.org)
Shih-Chii Liu, Institute of Neuroinformatics, University of Zurich and ETH Zurich (shih@ini.phys.ethz.ch)

Submission Instructions

  1. Read the information for Authors at http://cis.ieee.org/tnnls
  2. Submit the manuscript by 15th Nov 2014 at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript has been submitted to the special issue on Learning in Neuromorphic Systems and Cyborg Intelligence. Send also an email to the guest editors with subject “TNNLS special issue submission” to notify about your submission.

Friday 10 October 2014

CFP: Special Issue IEEE Computational Intelligence Magazine on "Computational Intelligence for Changing Environments"

Aims and Scope

Over the past decade or so, computational intelligence techniques have been highly successful for solving big data challenges in changing environments. In particular, there has been growing interest in so called biologically inspired learning (BIL), which refers to a wide range of learning techniques, motivated by biology, that try to mimic specific biological functions or behaviors. Examples include the hierarchy of the brain neocortex and neural circuits, which have resulted in biologically-inspired features for encoding, deep neural networks for classification, and spiking neural networks for general modelling.

To ensure that these models are generalizable to unseen data, it is common to assume that the training and test data are independently sampled from an identical distribution, known as the sample i.i.d. assumption. In dynamic and non-stationary environments, the distribution of data changes over time, resulting in the phenomenon of ‘concept drift’ (also known as population drift or concept shift), which is a generalization of covariance shift in statistics. Over the last five years, transfer learning and multitask learning have been used to tackle this problem. Fundamental analyses using probably approximately correct (PAC) and Rademacher complexity frameworks have explained why appropriate incorporation of context and concept drift can improve generalizability in changing environments.

It is possible to use human-level processing power to tackle concept drift in changing enviroments. Concept drift is a real-world problem, usually associated with online and concept learning, where the relationships between input data and target variables dynamically change over time. Traditional learning schemes do not adequately address this issue, either because they are offline or because they avoid dynamic learning. However, BIL seems to possess properties that would be helpful for solving concept drift problems in changing environments. Intuitively, the human capacity to deal with concept drift is innate to cognitive processes, and the learning problems susceptible to concept drift seem to share some of the dynamic demands placed on plastic neural areas in the brain. Using improved biological models in neural networks can provide insight into cognitive computational phenomena.

However, a main outstanding issue in using computational intelligence for changing enviroments and domain adaptation is how to build complex networks, or how networks should be connected to the features, samples, and distribution drifts. Manual design and building of these networks are beyond current human capabilities. Recently, computational intelligence methods has been used to address concept drift in changing enviroments, with promising results. A Hebbian learning model has been used to handle random, as well as correlated, concept drift. Neural networks have been used for concept drift detection, and the influence of latent variables on concept drift in a neural network has been studied. In another study, a timing-dependent synapse model has been applied to concept drift. These works mainly apply biologically-plausible computational models to concept drift problems. Although these results are still in their infancy, they open up new possibilities to achieve brain-like intelligence for solving concept drift problems in changing environments.

Taking the current state of research in computational intelligence for changing environments into account, the objective of this special issue is to collate this research to help unify the concepts and terminology of computational intelligence in changing environments, and to survey state-of-the-art computational intelligence methodologies and the key techniques investigated to date. Therefore, this special issue invites submissions on the most recent developments in computational intelligence for changing enviroments algorithms and architectures, theoretical foundations, and representations, and their application to real-world problems. We also welcome timely surveys and review papers.

Topics of Interest include (but are not limited to):

  • Computational intelligence methodologies and implementation for changing environments
  • Transfer learning
  • Multitask learning
  • Domain adaption
  • Incremental Learning architectures
  • Incremental Unsupervised and semi-supervised learning architectures
  • Incremental Incremental Representation learning and disentangling
  • Incremental Knowledge augmentation
  • Incremental Adaptive Neuro-fuzzy systems
  • Incremental and single-pass data mining
  • Incremental Neural Clustering
  • Incremental Neural regression
  • Incremental Adaptive decision systems
  • Incremental Feature selection and reduction
  • Incremental Constructive Learning
  • Novelty detection in Incremental learning

 Submission Process

The maximum length for the manuscript is typically 25 pages in single column format with double-spacing, including figures and references. Authors should specify in the first page of their manuscripts the corresponding author’s contact and up to 5 keywords. Submission should be made via

https://www.easychair.org/conferences/?conf=ieeecimcdbil2015.

Important Dates (for August 2015 Issue)

15th November, 2014: Submission of Manuscripts
15th January, 2015: Notification of Review Results
15th Faburary, 2015: Submission of Revised Manuscripts
15th March, 2015: Submission of Final Manuscripts
August 2015: Publication

Guest Editors

Professor Amir Hussain,
University of Stirling,
Stirling FK9 4LA SCOTLAND, UK
Email: ahu@cs.stir.ac.uk

Professor Dacheng Tao,
University of Technology, Sydney
235 Jones Street, Ultimo, NSW 2007, Australia
Email: dacheng.tao@uts.edu.au

Professor Jonathan Wu
University of Windsor
401 Sunset Avenue, Windsor, ON, Canada
Email: jwu@uwindsor.ca

Professor Dongbin Zhao
Institute of Automation, Chinese Academy of Sciences,
No. 95, Zhongguancun East Road, Beijing 100190, China
E-mail: dongbin.zhao@gmail.com

Tuesday 7 October 2014

IEEE Transactions on Evolutionary Computation, Volume 18, Number 5, October 2014

SPECIAL ISSUE ON THEORETICAL FOUNDATIONS OF EVOLUTIONARY COMPUTATION

GUEST EDITORIAL

1. Editorial for the Special Issue on Theoretical Foundations of Evolutionary Computation
Author(s): F. Neumann, B. Doerr, P. K. Lehre, and P. C. Haddow
Pages: 625-627

SPECIAL ISSUE PAPERS

2. Transforming Evolutionary Search into Higher-Level Evolutionary Search by Capturing Problem Structure
Author(s): R. Mills, T. Jansen, and R. A. Watson
Pages: 628-642

3. Convergence of Hypervolume-Based Archiving Algorithms
Author(s): K. Bringmann and T. Friedrich
Pages: 643-657

4. Asymptotic Properties of a Generalized Cross-Entropy Optimization Algorithm
Author(s): Z. Wu and M. Kolonko
Pages: 658-673

5. Reevaluating Immune-Inspired Hypermutations Using the Fixed Budget Perspective
Author(s): T. Jansen and C. Zarges
Pages: 674-688

REGULAR ISSUE PAPERS

6. Differential Evolution With Dynamic Parameters Selection for Optimization Problems
Author(s): R. A. Sarker, S. M. Elsayed, and T. Ray
Pages: 689-707

7. Automated Map Generation for the Physical Traveling Salesman Problem
Author(s): D. Perez, J. Togelius, S. Samothrakis, P. Rohlfshagen, and S. M. Lucas
Pages: 708-720

8. Multilocal Search and Adaptive Niching Based Memetic Algorithm With a Consensus Criterion for Data Clustering
Author(s): W. Sheng, S. Chen, M. Fairhurst, G. Xiao, and J. Mao
Pages: 721-741

9. A Knowledge-Based Evolutionary Multiobjective Approach for Stochastic Extended Resource Investment Project Scheduling
Author(s): J. Xiong, J. Liu, Y. Chen, and H. A. Abbass
Pages: 742-765

10. The Dynamics of Self-Adaptive Multirecombinant Evolution Strategies on the General Ellipsoid Model
Author(s): H.-G. Beyer and A. Melkozerov
Pages: 764-778

11. Genetic Algorithms for Evolving Computer Chess Programs
Author(s): O. E. David, H. J. van den Herik, M. Koppel, and N. S. Netanyahu
Pages: 779-789

COMMENTARY

12. A Comment on “Correlation as a Heuristic for Accurate and Comprehensible Ant Colony Optimization-Based Classifiers”
Author(s): B. Minnaert and D. Martens
Pages: 790

Monday 6 October 2014

IEEE Transactions on Neural Networks and Learning Systems, Volume 25, Number 10, October 2014

REGULAR PAPERS

1. A New Learning Algorithm for a Fully Connected Neuro-Fuzzy Inference System
Author(s): C. L. P. Chen, J. Wang, C.-H. Wang, and L. Chen
Pages: 1741-1757

2. Synchronization of Stochastic Dynamical Networks Under Impulsive Control With Time Delays
Author(s): W. Zhang, Y. Tang, Q. Miao, and J.-A. Fang
Pages: 1758-1768

3. Stochastic Learning via Optimizing the Variational Inequalities
Author(s): Q. Tao, Q.-K. Gao, D.-J. Chu, and G.-W. Wu
Pages: 1769-1778

4. Sparse Alignment for Robust Tensor Learning
Author(s): Z. Lai, W. K. Wong, Y. Xu, C. Zhao, and M. Sun
Pages: 1779-1792

5. An Incremental Design of Radial Basis Function Networks
Author(s): H. Yu, P. D. Reiner, T. Xie, T. Bartczak, and B. M. Wilamowski
Pages: 1793-1803

6. Pinning Distributed Synchronization of Stochastic Dynamical Networks: A Mixed Optimization Approach
Author(s): Y. Tang, H. Gao, J. Lu, and J. Kurths
Pages: 1804-1815

7. Deep Networks are Effective Encoders of Periodicity
Author(s): L. Szymanski and B. McCane
Pages: 1816-1827

8. Parsimonious Extreme Learning Machine Using Recursive Orthogonal Least Squares
Author(s): N. Wang, M. J. Er, and M. Han
Pages: 1828-1841

9. LI-MLC: A Label Inference Methodology for Addressing High Dimensionality in the Label Space for Multilabel Classification
Author(s): F. Charte, A. J. Rivera, M. J. del Jesus, and F. Herrera
Pages: 1842-1854

10. A Fast Algorithm for Nonnegative Matrix Factorization and Its Convergence
Author(s): L.-X. Li, L. Wu, H.-S. Zhang, and F.-X. Wu
Pages: 1855-1863

11. Memristor Crossbar-Based Neuromorphic Computing System: A Case Study
Author(s): M. Hu, H. Li, Y. Chen, Q. Wu, G. S. Rose, and R. W. Linderman
Pages: 1864-1878

12. Multiobjective Optimization for Model Selection in Kernel Methods in Regression
Author(s): D. You, C. F. Benitez-Quiroz, and A. M. Martinez
Pages: 1879-1893

13. Separation of Synchronous Sources Through Phase Locked Matrix Factorization
Author(s): M. S. B. Almeida, R. Vigário, and J. Bioucas-Dias
Pages: 1894-1908

14. Clipping in Neurocontrol by Adaptive Dynamic Programming
Author(s): M. Fairbank, D. Prokhorov, and E. Alonso
Pages: 1909-1920

BRIEF PAPERS

15. Consensus Acceleration in a Class of Predictive Networks
Author(s): H.-T. Zhang and Z. Chen
Pages: 1921-1927

16. H-infinity Output Tracking Control of Discrete-Time Nonlinear Systems via Standard Neural Network Models
Author(s): M. Liu, S. Zhang, H. Chen, and W. Sheng
Pages: 1928-1935

17. Extended Dissipative Analysis for Neural Networks With Time-Varying Delays
Author(s): T. H. Lee, M.-J. Park, J. H. Park, O.-M. Kwon, and S.-M. Lee
Pages: 1936-1941

18. Multilinear Sparse Principal Component Analysis
Author(s): Z. Lai, Y. Xu, Q. Chen, J. Yang, and D. Zhang
Pages: 1942

Friday 3 October 2014

IEEE Transactions on Fuzzy Systems: Issue 5, Volume 22, October 2014

REGULAR PAPERS

1. Partial Tracking Error Constrained Fuzzy Dynamic Surface Control for a Strict Feedback Nonlinear Dynamic System
Author(s): S.I. Han and J.M. Lee
Pages: 1049-1061

2. Non-L-R Type Fuzzy Parameters in Mathematical Programming Problems
Author(s): C.-F. Hu, M. Adivar, and S.-C. Fang
Pages: 1062-1073

3. A Novel Evolutionary Kernel Intuitionistic Fuzzy C-means Clustering Algorithm
Author(s): K.-P. Lin
Pages: 1074-1087

4. A Dynamic Decoupling Approach to Robust T–S Fuzzy Model-Based Control
Author(s): C.-S. Chiu
1088-1100

5. Relaxed Stability and Stabilization Conditions of Networked Fuzzy Control Systems Subject to Asynchronous Grades of Membership
Author(s): C. Peng, D. Yue, and M.-R. Fei
Pages: 1101-1112

6. Fuzzy n-Ellipsoid Numbers and Representations of Uncertain Multichannel Digital Information
Author(s): G. Wang, P. Shi, B.Wang, and J. Zhang
Pages: 1113-1126

7. Prioritized Measure-Guided Aggregation Operators
Author(s): L. Chen, Z. Xu, and X. Yu
Pages: 1127-1138

8. A Fuzzy Measure Approach to Systems Reliability Modeling
Author(s): R. R. Yager
Pages: 1139-1150

9. Fuzzy Concept Hierarchies and Evidence Resolution
Author(s): F. E. Petry and R. R. Yager
Pages: 1151-1161

10. General Type-2 Fuzzy Logic Systems Made Simple: A Tutorial
Author(s): J. M. Mendel
Pages: 1162-1182

11. Nonfragile Control With Guaranteed Cost of T–S Fuzzy Singular Systems Based on Parallel Distributed Compensation
Author(s): C. Han, L. Wu, H.K. Lam, and Q. Zeng
Pages: 1183-1196

12. On the Monotonicity of Interval Type-2 Fuzzy Logic Systems
Author(s): C. Li, J. Yi, and G. Zhang
Pages: 1197-1212

13. Robust Model Predictive Control for Discrete-Time Takagi–Sugeno Fuzzy Systems With Structured Uncertainties and Persistent Disturbances
Author(s): W. Yang, G. Feng, and T. Zhang
Pages: 1213-1228

14. Accelerating Fuzzy-C Means Using an Estimated Subsample Size
Author(s): J. K. Parker and L. O. Hall
Pages: 1229-1244

15. On Advanced Computing With Words Using the Generalized Extension Principle for Type-1 Fuzzy Sets
Author(s): M.R. Rajati and J.M. Mendel
Pages: 1245-1261

16. Adaptive Sliding-Mode Antisway Control of Uncertain Overhead Cranes With High-Speed Hoisting Motion
Author(s): M.-S. Park, D. Chwa, and M. Eom
Pages: 1262-1271

17. The Neuro-Fuzzy Computing System With the Capacity of Implementation on a Memristor Crossbar and Optimization-Free Hardware Training
Author(s): F. Merrikh-Bayat, F. Merrikh-Bayat, and S. B. Shouraki
Pages: 1272-1287

18. Adaptive Fuzzy Control for MIMO Nonlinear Systems With Nonsymmetric Control Gain Matrix and Unknown Control Direction
Author(s): W. Shi
Pages: 1288-1300

19. Two-mode Indirect Adaptive Control Approach for the Synchronization of Uncertain Chaotic Systems by the Use of a Hierarchical Interval Type-2 Fuzzy Neural Network
Author(s): A. Mohammadzadeh, O. Kaynak, and M. Teshnehlab
Pages: 1301-1312

20. Fuzzy Control Design for Nonlinear ODE-Hyperbolic PDE-Cascaded Systems: A Fuzzy and Entropy-Like Lyapunov Function Approach
Author(s): J.-W. Wang, H.-N. Wu, and H.-X. Li
Pages: 1313-1324

21. Attribute Reduction for Heterogeneous Data Based on the Combination of Classical and Fuzzy Rough Set Models
Author(s): D. Chen and Y. Yang
Pages: 1325-1334

SHORT PAPERS

22. On Computing Normalized Interval Type-2 Fuzzy Sets
Author(s): J. M. Mendel and M. R. Rajati
Pages: 1335-1340

23. Adaptive Fuzzy Output-Feedback Control of Pure-Feedback Uncertain Nonlinear Systems With Unknown Dead Zone
Author(s): Y. Li and S. Tong
Pages: 1341-1346

24. A Heuristic Method to Compute the Approximate Postinverses of a Fuzzy Matrix
Author(s): P. Li
Pages: 1347-1351

25. Removal of High-Density Salt-and-Pepper Noise in Images With an Iterative Adaptive Fuzzy Filter Using Alpha-Trimmed Mean
Author(s): F. Ahmed and S. Das
Pages: 1352-1358

26. Adaptive Fuzzy Control for a Class of Nonlinear Discrete-Time Systems With Backlash
Author(s): Y.-J. Liu and S. Tong
Pages: 1359-1364

27. Adaptive Fuzzy Decentralized Output Stabilization for Stochastic Nonlinear Large-Scale Systems With Unknown Control Directions
Author(s): S. Tong, S. Sui, and Y. Li
Pages: 1365