Home Special Sessions
  • Preliminary Accepted Special Sessions

    Title Organizer
    Evolutionary Optimization Tools in Logistics Thomas Hanne and Rolf Dornberger
    Incorporating Swarm-Inspired Social Intelligence into Games Robert G. Reynolds, Yuhui Shi, Gary Yen, and Mostafa Z. Ali


IEEE WCCI 2012 Hybrid Special Sessions:

Computational Intelligence in Communications and Networking

By Chuan-Kang Ting, Jun Zhang, Zhun Fan, and Xiao-Min Hu
With the advent of wireless and communication technologies, communication and computer networks have been growing rapidly and become a powerful medium of information and resources sharing. In view of the increasing scale, complexity, diversity, and mobility, design and optimization of networks become an essential research topic as well as a critical issue in real-world applications.
Computational intelligence (CI) has shown to be effective for a wide range of real-world problems. In particular, CI techniques, including neural network, fuzzy systems, and evolutionary computation, have gained much success and promising results in communications and networking.
The aim of this special session is to reflect the most recent advances of CI in communications and networking, and increase the awareness of the computing and network community at large on this kind of effective technology. This session will allow researchers to share experiences and present their new ways for taking advantage of CI techniques in communications and networking.
[Read more ...]

Computational Intelligence and Measurement Systems

By Richard J. Duro
Measuring has gone from simple one variable measurement machines that produce data to integrated measurement systems that produce user oriented information. These systems acquire and intelligently process and integrate multiple data measurements from multiple sources and, taking into account and adapting to the context, produce usable information which, by intelligently communicating and interacting with other systems and repositories, seamlessly contribute to some user perceived functionality. Obviously, to achieve this end, Computational Intelligence based techniques and their application to measurement systems are a very important avenue of research. It is the objective of this session to address all aspects related to the theory and the development of new intelligent measurement techniques and, in particular, of novel developments and applications of computational intelligence based approaches to this field.
The topics include but are not limited to: intelligent measurement systems; accuracy and precision of neural and fuzzy components; intelligent sensor fusion; intelligent monitoring and control systems; neural, evolutionary and fuzzy technologies for identification, prediction, and control of complex dynamic systems; evolutionary monitoring and control; uncertainty estimation in complex measuring systems; neural, evolutionary and fuzzy signal/image processing for industrial and environmental applications; hybrid systems; fuzzy evolutionary and neural components for embedded systems; hardware implementation of neural, evolutionary and fuzzy systems for measurements; neural, fuzzy and genetic/evolutionary algorithms for system optimization and calibration; neural and fuzzy diagnosis of components and systems; reliability, fault tolerance and testing of fuzzy and neural components; neural and fuzzy techniques for quality measurement.
[Read more ...]

Computational Intelligence for Intelligent Agents

By Hani Hagras and Vincenzo Loia
The intersection between Computational Intelligence and Agent technology opens new significant scenarios in many fields where the representation and management of complex systems play a fundamental role. In the formulation of Agent-based systems, the role of uncertainty is crucial for an efficient and coherent resolution of complex problems. Agents overcome classical programs thanks to their inner capabilities to be autonomous and to adapt their behaviour with the changing of the environment where agents live and interact. This means that inevitably they meet uncertainty during their work, or in many cases, for the high complexity of the problem, the information they handle is (or needs to be) approximate.
Only in recent years there has been a growing awareness that Computational Intelligence handling of uncertainty in agents is equally important as other features of agent paradigm. The aim of this special session is to present top quality research in the area of theory and applications of Intelligent Agents. The session will also provide a forum for the academic community and industry to report on the recent advances on the area We expect high quality original research in the area. Topics include, but are not limited to theory and application of Computational Intelligence mainly Evolutionary Computation, Neural Networks, Fuzzy systems
[Read more ...]

Computational Intelligence in Finance, Economics and Management Sciences (CIFEMS)

By Shu-Heng Chen, Xuezhong (Tony) He, David Quintana, Dirk Van den Poel, Wei Zhang
The Computational Finance and Economics Technical Committee (CFETC) with its six constituents (task forces) will jointly organize special sessions on “Computational Intelligence in Finance, Economics and Management Sciences’’ (CIFEMS). The purpose is to promote the missions of CFETC, as declared in http://ieee-cis.org/technical/cfetc/, more coherently and effectively.  We think that this is a critical moment to have a unified organized event, specifically, within the context of WCCI, so that it can answer the needs of many researchers in this community, namely, out of so many conferences which one to choose. 
Indeed, the popularity of the financial and economic applications of computational intelligence and other related computational paradigms have advanced both in its depth (sophistication and deliberation of the tools) and breath (application domains).  Accordingly, there are too many calls a year, each with different focuses with regards to specific tools (fuzzy logic, neural networks, evolutionary computation, swarm intelligence, hybrid systems) and domains (financial engineering, agent-based computational economics, word computing in financial news and reports, marketing, supply chains, trading agent competition, game theory, on-line decision making with agents, networks, public policy analysis, risk management).  Despite its possible advantages, this diversity has led to the well-known “paradox of choices” as documented by Barry Schwartz, with the implication that more is less. In the end, what is lacking is the scale effect, including a good documentation (post-conference publications) which can significantly impact the future.
Therefore, CFETC should take the action to actively provide the academic community an “all-in-one” event and solve the paradox of choice. This joint action will then make an attempt to organize one of the most agglomerated events so that the limited budgets of each researcher in this field can be used efficiently. To achieve that purpose, in addition to finance and economics, we also include management sciences by noticing that tremendous applications have been employed in marketing, accounting, management of information systems, human resources, and organization and leadership.  We are also open to the various application tools. In addition to fuzzy logic, neural networks and evolutionary computation, other related and novel techniques which can contribute to computational finance, economics and management sciences are also welcome.  By including this large variety of subjects with application tools, we greatly acknowledge the interdisciplinary nature of CIFEMS and appreciate the bidirectional influential relations between tools and problems.
[Read more ...]

Ensemble Methods in Computational Intelligence

By P. N. Suganthan, N. R. Pal, and Wenjia Wang
Ensemble learning attempts to enhance the performance of systems (clustering, classification, prediction, feature selection, search, optimization, rule extraction, etc.) by using multiple models instead of using a single model. This approach is intuitively meaningful as a single model may not always be the best for solving a complex problem while multiple models are more likely to yield results better than each of the constituent models. Although in the past, ensemble methods have been mainly studied in the context of classification and time series prediction, recently they are being used in algorithms in other scenarios such as clustering, fuzzy systems, evolutionary algorithms, dimensionality reduction and so on.
The aim of this special session is to bring together researchers and practitioners who are working in the overlapping fields of ensemble methods and computational intelligence. Papers dealing with theory, algorithms, analysis, and applications of ensemble of computational intelligence methods are sought for this special session. Topics of interest include but are not limited to:
[Read more ...]

Computational Intelligence Applications in Smart Grid and Micro-grids

By Ganesh Kumar Venayagamoorthy and Jung-Wook Park
The new constraints placed by the environmental and economic factors and by the availability of energy resources will bring critical challenges to electric energy security, reliability and sustainability in smart grid and micro-grids.  These challenges require innovative solutions. This special session will focus on the applications of computational intelligence (CI) for planning, implementation, operation, control, and optimization of smart grid and micro-grids, in order to provide better electric energy security, reliability and sustainability as well as efficiency.  The CI techniques include neural networks, fuzzy logic, evolutionary, approximate dynamic programming, multivariate polynomial model, machine learning, adaptive signal processing, pattern recognition, data mining, on-chip learning, biologically inspired computing, multi-agent systems, etc.
The objective of this special session is to bring together the researchers in the fields of computational intelligence and electric power and energy systems (including power electronics devices and systems) from all around the world and to present the latest technology improvement.  The special session invites contributions in the areas including, but not limited to, the following:
[Read more ...]

Industrial Applications of Evolving Fuzzy and Neural systems

By Yaochu Jin, Frank Jiang, Kit Yan Chan, Lin-Cheng Wang, Hak Keung Lam, and Steve S. H. Ling
The congress level hybrid session focuses mainly on the use of evolving fuzzy and neural systems to industrial applications.  It covers the start-of-the-art and the most recent and significant research on this field. This session serves an effective channel to communicate the collective experiences and knowledge of leading researchers in this field. The features in the development of evolving fuzzy and neural systems will be addressed, advanced techniques will be introduced and methodologies will be provided to handle difficulties in development of  evolving fuzzy and neural systems regarding particular industrial applications.
This special session aim to bring together researchers, engineers, developers and practitioners from academia to industry working in multi-disciplinary area and technically converging areas. Topics of interest include, but are not limited to:
[Read more ...]

Computational Intelligence and Games

By Julian Togelius and Phil Hingston
Games are an ideal domain to study computational intelligence methods in that they provide cheap, competitive, dynamic, reproducible environments suitable for testing new search algorithms, pattern-based evaluation methods, or learning concepts. They are also interesting to observe, fun to play, and very attractive to students. Additionally, there is a great potential for CI methods to improve the design and development of both computer games and non-digital games such as board games.
This special session aims at getting together leading researchers and practitioners in this field who study and apply computational intelligence methods to computer games.
Topics of interest include, but are not limited to:
[Read more]

Computational Intelligence on Consumer Games and Graphics Hardware

By W. B. Langdon, Man Leung Wong, Yuji Sato, and Simon Harding
Since it promises huge amounts of cheap computation there is great interest in using mass consumer market commodity hardware for engineering and scientific applications. This tends concentrated upon graphics hardware, particularly GPUs. However there is also increasing interest in using games consoles such as Microsoft's Xbox, Sony's Playstation and the Cell processor, for research and applications.  In future personal computer physics engines, which are intended to provide realistic real time simulation of  multi-body physics for sophisticated games, may also be adapted to serve science (rather than simulate it).  With their blend of computing and sensors, eg 3D real time positioning, mobile cellular telephones, tablets and gaming devices such as the Nintendo Wii, also offer platforms for novel computational intelligence applications.
[Read more ...]

Computational Intelligence in Bioinformatics

By Sheridan Houghten, Michael Lones, Vassilis Plagianakos, and Mihail Popescu
Bioinformatics, computational biology, and bioengineering present a number of complex problems with large search spaces. Recent applications of Computational Intelligence (CI) in this area suggest that they are well-suited to this area of research. This special session will highlight applications of CI to a broad range of topics. Particular interest will be directed towards novel applications of CI approaches to problems in these areas. The scope of this special session includes evolutionary computation, neural computation, fuzzy systems, artificial immune systems, swarm intelligence, ant-colony optimization, simulated annealing, and other CI methods or hybridizations between CI approaches. Applications of these CI methods to bioinformatics, computational biology, and bioengineering problems are the main focus of this hybrid special session. The special session on Computational Intelligence in Bioinformatics is soliciting high quality papers of original research and application papers that have not been published elsewhere and are not under consideration for publication elsewhere. All papers will be rigorously reviewed by at least two reviewers. Accepted papers will be published in the WCCI 2012 proceedings. There is a clear interest in both the Computational Intelligence community and Biology communities for this special session. This hybrid special session is sponsored by the IEEE CIS BBTC (Computational Intelligence Society - Bioinformatics and Bioengineering Technical Committee)
[Read more ...]

Computational Intelligence and Biometrics

By Eliza Yingzi Du, Eric Granger,  and Qinghan Xiao
Biometrics is becoming an important ally to homeland security and law enforcement. Continual improvements in accuracy, transaction speed and affordability have increased their ease of use and cost-effectiveness. However, most existing systems can only perform well with high quality samples of the biometric trait from cooperative users. Low quality samples can greatly affect the recognition accuracy. Samples of a biometric trait are captured from a live person, which cannot be precisely replicated, so that biometric matching always results in uncertainties. In addition to complex operational environments that change over time, biometric systems are typically designed a priori using limited and unbalanced data and knowledge of underlying data distributions. Biometric models are often poor representatives of the biometric trait to be recognized, and should be adapted over time in response to new or changing input features, data samples, priors, and environments.
Computational intelligence (CI), primarily based on neural networks (NN), fuzzy systems (FS), evolutionary computation (EC), etc., is a suitable approach for solving challenging real-world biometric applications. The objective of this special session is to bring researchers from academia and industry together to exchange the latest theoretical and experimental results in the field. This event will provide an interdisciplinary forum for researchers, developers and practitioner especially in the CI field to present state of the art biometric research and technology, as well as the potential problems in real applications. Suggested topic areas include, but are certainly not limited to the following areas:
[Read more ...]

Computational Intelligence in Cyber Security

By Dipankar Dasgupta and Justin Zhan
Computational Intelligence constitutes an umbrella of techniques, has proven to be flexible in decision making in dynamic environment. These techniques typically include Fuzzy Logic, Evolutionary Computation, Neural Networks and other similar computational models. The use of these techniques allowed building efficient online monitoring tools and robust decision support modules, providing cross-linking solutions to different cyber security applications.
In order to protect Internet users from Identity Theft, Phishing, Spam and other cyber infrastructure threats, we need flexible, adaptable and robust cyber defence systems, which can make intelligent decisions (in near real-time) in detecting wide variety of threats and attacks, including active and passive attacks, external attacks and internal misuses, known and unknown attacks, viruses and spam, etc. Computational Intelligent (CI) based techniques appear to be promising to enhance cyber security measures, and have been increasingly applied in the area of information security and information assurance. Moreover, the multi-faceted CI approaches appear to provide a new security paradigm to deal with influx of new threats in a large network of computers.
This special session will cover all the issues, research and development of the state-of-the-art CI-based technologies in solving various computer and information security problems. CI application areas include, but are not limited to:
[Read more ...]

Computational Intelligence for Cognitive Robotics

By Naoyuki Kubota and Honghai Liu
The study on the intelligence, cognition, and self of robots has a long history. Nowadays, we can use various types of human-friendly robots in daily life. This means a robot should have human-like intelligence and cognitive capabilities to co-exist with people. The concepts on adaptation, learning, and cognitive development should be introduced much more in the next generation robotics from the theoretical point of view. The fuzzy, neural, and evolutionary computation plays the important role to realize cognitive development of robots from the methodological point of view. Furthermore, the synthesis of information technology, network technology, and robot technology may bring the brand-new emerging intelligence to robots from the technical point of view. The structurization of information and knowledge is a key topic to support the cognitive development of robots. This special session focuses on the intelligence of cognitive robots emerging from the adaptation, learning, and cognitive development through the interaction with people and dynamic environments from the conceptual, theoretical, methodological, and/or technical points of view.
[Read more ...]

Applications of Computational Intelligence in Education and Disability to Benefit Society

By Keeley Crockett, Bernadette Bouchon-Meunier, Gérard Dreyfus, Vincenzo Piuri, and Gary Yen
The aim of this session is to focus on new developments in the use of computational intelligence systems in the fields of education and disability which have had an impact on the lives of members of   society.  Disabilities cover limits in activity a human has in performing a task or action, impairments in a specific body function and inability to be involved in a life situation. Educational applications focus on intelligent teaching and learning systems that offer personalized learning to individuals based upon work- life-health balance.
The main objective of the session is to provide a forum to disseminate and discuss recent and significant research efforts in real-world educational  and disability focused applications in Computational Intelligence which have significantly benefited society.
A further objective of the session is to show how recent academic research has been transferred into industrial and public organisational environments. Papers should show how the public has effectively engaged with the application and should consider the consider societal implications and public
attitudes, alongside others, in the conduct and use of research.
New, unusual and hybrid approaches used to create such applications are particularly encouraged and should clearly reflect the benefit to society. The session is therefore open to high quality submissions from researchers who should present original research and applications including innovative results. 
Such applications should utilise the following topic areas of computational intelligence (but are not limited to):
[Read more ...]

Bio-Inspired Developmental Mechanisms

By Angelo Cangelosi and Juyang Weng
Developmental robotics (systems), also known as epigenetic robotics (systems), is a growing approach to the understanding of autonomous mental development in natural systems (e.g., human babies and adults) and artificial systems (e.g., robots and computers) as well as the design and training of robots (systems) by taking direct inspiration from biological developmental mechanisms. This approach is based on the principles of embodied and situated developmental learning.  An emphasis is on the emergence and bootstrapping of representation and intelligent behaviours. The special session will aim at the presentations of the latest developments in all the related fields, such as for the modelling of neural developmental mechanisms for the development of skills for perception, cognition, actions (e.g., locomotion, manipulation, classification, languages), emotional (e.g., pain avoidance, pleasure seeking, novelty seeking), and social interaction.
The special session also encourages submissions from the empirical developmental science disciplines such as child psychology, developmental linguistics and neuroscience.
A special issue in the journal IEEE Transaction in Autonomous Mental Development will be organised, as a follow-up of the special session.
[Read more ...]

Computational Intelligence in Social Media Analysis and Mining

By Basabi Chakraborty and Sushmita Mitra
In recent days, with intensive growth of intelligent computing techniques, a variety of social media (e.g Facebook, Twitter, YouTube, MySpace, Orkut etc.) is rapidly emerging to bring people together in many creative ways. The vast amount of data available in social media provides tremendous challenge to researchers and analysts, who are trying to gain insights into human interaction and collective behavior. Efficient mining and analysis of social data can assist people in different tasks like crisis management, reputation analysis, customer profiling and product survey, thereby leading to new applications related to economy, marketing, education, business or medical science.
Computational intelligence provides powerful and flexible approaches in analyzing real world complex problems involving imprecise and incomplete data.  Intelligent computing techniques, including neural networks, fuzzy sets, evolutionary algorithms, and their hybridizations, can be successfully applied to multimedia social data for efficiently extracting information and embedded knowledge.  The aim of this special session is to explore the research in application of computational intelligence techniques for analyzing and mining multimedia data from social network.
[Read more ...]

Computational Intelligence for Privacy Protection

By Agusti Solanas, Antoni Martinez-Balleste and David Elizondo
The main goal of this special session on Computational Intelligence for Privacy and Security is to gather high-quality articles in which techniques based on computational intelligence (i.e. evolutionary algorithms, neural networks, machine learning ,fuzzy systems, etc.) are used to protect the privacy and security of the users of information and communication technologies.
Topics include but are not limited to Computational Intelligence for Privacy and Security in:
[Read more ...]

Computational Intelligence in Brain Computer Interface

By Li-Wei Ko and Chin-Teng Lin
Brain–computer interface (BCI), sometimes called a direct neural interface or a brain–machine interface (BMI), is a direct communication pathway between the brain and an external device. BCIs are often aimed at assisting, augmenting, or repairing human cognitive or sensory-motor functions. BCI related research is growing at a significant pace and, since the beginning of the 21st century, has seen explosive growth. The technology of BCI enables communication which does not rely on neuromuscular control thereby offering assistance to those who require alternative communicatory and control mechanisms because of neuromuscular deficiencies due to disease, or spinal/brain damage. Other applications of BCI include neuro-feedback for stroke rehabilitation, the treatment of attention deficit disorder, driver alertness detection and electrophysiologically interactive computer systems and gaming.
BCI can also be applied to monitor, maintain, or track human cognitive functions such as their perception, attention, awareness and decision making in daily life activities and BCI based biofeedback can be used to augment human performance. Moreover, how to efficiently and effectively utilize the Computational Intelligence (CI) based techniques and integrate with high-level cognitive functions for augmenting human performance is a grand challenge in the interdisciplinary area. We believe BCI technologies not only can help us to understand the further interpretation of the human cognitive function via the advanced CI techniques, but also can provide us new insights into the understanding of complex cognitive functions and lead to novel application enhancing our productivity and performance in face of real-world complications.
This special session is organized by the IEEE CIS Neural Network Technical Committee (NNTC) and Fuzzy Systems Technical Committee. Past BCI related special sessions related to this special session had ever been approved by 2010 IEEE World Congress on Computational Intelligence in Barcelona, Spain and 2011 International Joint Conference on Neural Networks (IJCNN) in San Jose, USA, and was a natural follow up to the special issue on Brain-Computer Interactions in IEEE Computational Intelligence Magazine, 2009. This special session can also match the three main topics of computational intelligence in BCI for the joint three conferences of 2012 IEEE World Congress on Computational Intelligence.

  1. Neural Networks in Brain Computer Interface
  2. Fuzzy Systems in Brain Computer Interface
  3. Evolution Computation in Brain Computer Interface

Educational Data Mining

By Longbing Cao, Nitesh Chawla, and George Siemens
Education is one of the most important focuses for all countries. How to improve the education quality has always been one big problem for educationists, universities, as well as governments. Computational Intelligence, in particular, Data Mining and Machine Learning, a useful technology to analyse important patterns, sequences and rules from massive data, is able to help educators to discover important factors in educational data that affect education outcomes. Educational Data Mining (EDM), a newly emerging inter-disciplinary research field in the discipline of computational intelligence, focuses on Knowledge Discovery and Data Mining techniques to analyse data from educational settings, including interactive learning systems, intelligent tutoring systems and institutional administration data. The primary goal of EDM is to uncover scientific evidence or patterns that are useful to gain insights and explain educational phenomena.
Educational Data comes from educational settings, e.g. interactive learning environments (multiple choice questions, response time), computer aided collaborative learning (online learning data), and administrative data (demographics, enrolment). It has the following typical characteristics: multiple level of meaningful hierarchy (subject, assignment, and question levels), time, sequence, context (a particular student in a particular class encountering a particular question in a particular problem on a particular computer at a particular time on a particular date), fine-grained (record data at different resolutions to facilitate different analyses, e.g. record data every 20s) and longitudinal (large data recorded for many sessions for a long period of time, e.g. spanning semester land year long courses).
To meet the emerging research interest in educational data mining and learning analytics, we propose this special session in 2012 IEEE World Congress on Computational Intelligence (WCCI2012) for researchers to publish high quality original research papers with various topics in educational data mining and learning analytics. The topics of this special session may include (but not limited to) cohort analysis, attribution analysis, pathway analysis, student modelling, learning and teaching behaviour analysis, learning emotion analysis, educational psychology analysis, student performance prediction, e-learning and learning management system building, learning personalization and recommendation, learning visualization and analysis, social network analysis in educational environment, and coursework construction.
We propose this special session as a hybrid one with WCCI 2012, because the Educational Data Mining and its corresponding area Learning Analytics involve topics of interest relevant to IJCNN, CEC and FUZZY-IEEE. A hybrid special session would mostly benefit the WCCI community.
[Read more ...]

Computational Intelligence in Social Media Analysis and Mining

By Basabi Chakraborty and Sushmita Mitra
In recent days, with intensive growth of ICT, a variety of social media (e.g Facebook, Twitter, YouTube, MySpace, Orkut etc.) is rapidly emerging to bring people together in many creative ways. The vast amount of data available in social media provides tremendous challenge to researchers and analysts, who are trying to gain insights into human interaction and collective behavior. Efficient mining and analysis of social data can assist people in varieties of tasks like crisis management, reputation analysis, customer profiling and product survey, thereby leading to new applications related to economy, marketing, education, business or medical science.
Computational intelligence provides powerful and flexible approaches in analyzing real world complex problems involving imprecise and incomplete data.  Intelligent computing techniques, including neural networks, fuzzy sets, evolutionary algorithms, and their hybridizations, can be successfully applied to multimedia social data for efficiently extracting information and embedded knowledge.  The aim of this special session is to explore the research in application of computational intelligence techniques for analyzing and mining multimedia data from social network.
The topics of interest include but are not limited to:
[Read more ...]

Computational Intelligence for the Digital Economy

By Christian Wagner, Jonathan Garibaldi, and Peter Andras
Digital technologies in the form of the personal computer and the internet have already transformed work, education and entertainment, generating new market opportunities and significant business potential across a wide range of sectors.
The rapid proliferation of new technologies, most significantly, portable, wireless, "always-on" handheld devices from handheld computers to smart phones and the large number of existing and potential new services relying on a myriad of information sources from location sensors to crowd-sourced and social network information is giving rise to significant development potential for applications in this digital economy. Ubiquitous computing is already a fundamental part of the strategies and visions for future transport, energy and healthcare sectors and this trend is expected to continue and intensify over the coming years. Specific examples include the rollout of smart meters with the vision of a smart energy grid and the rapid increase in location-based services offering everything from road-side assistance to directed advertising.
Computational Intelligence techniques are ideally placed to support and leverage the potential of the digital economy by providing the tools to identify and employ valuable knowledge within the vast amounts of information generated, transmitted and stored – both locally, and all the more commonly, in the cloud.
It is the goal of this special session to raise awareness of the significant potential of the digital economy and specifically the large potential for computational intelligence techniques to support it. The session will focus theoretical and practical contributions related to the digital economy and provide a platform for interested parties to network and plan future collaborations.
Submissions to the Special Session should be centred on theoretical results or applications of computational intelligence to the Digital Economy. Specific topics for the special session include but are not limited to:
[Read more ...]

Computational Intelligence for Security, Surveillance and Defence

By Slawo Wesolkowski, Rami Abielmona, and Derek Anderson
Given the current global security environment, there has been increased interest within the security and defense communities in novel techniques for solving challenging problems. The genesis of this interest lies in the fact that repeated attempts of using traditional techniques have left many important problems unsolved, and in some cases, not addressed. New problems have emerged within the broad areas of security and defense that are difficult to tackle with conventional methods, thus requiring new techniques for detecting and adapting to emerging threats.
The purpose of the workshop is to present current and ongoing efforts in computational intelligence (e.g., neural networks, fuzzy systems, evolutionary computation, swarm intelligence, and other emerging learning or optimization techniques) as applied to security and defense problems.
[Read more ...]

IEEE CEC 2012 Special Sessions:

Evolutionary Computer Vision

By Vic Ciesielski, Mario Köppen, and Mengjie Zhang
Computer vision is a major unsolved problem in computer science and engineering. Over the last decade there has been increasing interest in using evolutionary computation approaches to solve vision problems. Computer vision provides a range of problems of varying difficulty for the development and testing of evolutionary algorithms. There have been a relatively large number of papers in evolutionary computer vision in recent CEC and GECCO conferences. It would be beneficial to researchers to have these papers in a special session. Also, a special session would encourage more researchers to continue to work in this field and consider CEC a place for presenting their work.
[Read more ...]

Evolutionary Computation in Scheduling

By Rong Qu and Kay Chen Tan
Due to the challenges of many real world applications in both research and practice, scheduling problems have received a significant amount of attention in a range of disciplines including artificial intelligence, operations research, engineering and computer science. Problems range from classic production scheduling to various applications in education, industry and business sections. Different constraints, objectives as well as problem characteristics have to be considered while developing efficient and intelligent computational methods for these complex and large-scale problems. Evolutionary computation has shown to be one of the most effective intelligent algorithms for solving scheduling problems.
[Read more ...]

Evolutionary Multiobjective Optimization

By Carlos A. Coello Coello
Most real-world problems have several (and normally conflicting) objectives that have to be satisfied at the same time. Such problems are called multi- objective and have become very popular in the last few years.
Vilfredo Pareto stated in 1896 a concept (known today as "Pareto optimum") that constitutes the origin of research in multi-objective optimization. According to this concept, the solution to a multi-objective optimization problem is normally not a single value, but instead a set of values (also called the Pareto set).
The interest of applying evolutionary computation techniques to multi-objective optimization dates back to the 1960s, with Rosenberg's doctoral dissertation. One of the reasons why evolutionary algorithms are so suitable for multi-objective optimization is because they can generate a whole set of solutions (the Pareto set) in a single run rather than requiring an iterative process like traditional mathematical programming techniques.
As reflected by the EMOO repository, the interest on Evolutionary Multiobjective Optimization (EMOO) is made evident by the high volume of publications on this topic that have been produced since its inception, in 1984, (the EMOO repository currently has over 245 PhD theses, more than 2450 journal papers, and more than 2500 conference papers). The main aim of this special session organized within the 2012 IEEE Congress on Evolutionary Computation (CEC'2012) (which will take place within the 2012 IEEE World Congress on Computational Intelligence) is to bring together both experts and newcomers working on EMOO to discuss different issues.
[Read more ...]

Bilevel Optimization

By Kalyanmoy Deb and Ankur Sinha
Bilevel optimization problems are special kind of optimization problems which require every feasible upperlevel solution to satisfy the optimality conditions of a lower-level optimization problem. These problems are commonly found in many practical problem solving tasks which include optimal control, process optimization, game-playing strategy development, transportation problems, coordination of multi-divisional firms, and others. Bilevel programming is also useful for optimal parameter setting in neural networks and fuzzy systems. Due to the computational overhead and other difficulties involved in handling such problems, they are often handled using approximate solution procedures. These problems are challenging to solve and there is a need for theoretical as well as methodological advancements to handle such problems efficiently.
IEEE Congress on Evolutionary Computation (CEC) being one of the leading conferences in evolutionary computation will give an opportunity to researchers and practitioners to discuss and exchange ideas for handling bilevel problems, which have yet not been widely explored by the evolutionary computation community. The special session on Bilevel Optimization will bring together researchers working on following topics:
[Read more ...]

Hardware Aspects of Bio-Inspired Architectures and Systems

By Andy M.Tyrrell and Martin A.Trefzer
The current wave of technological developments is defined by mobile embedded systems that operate in a distributed,decentralised fashion. In fact everyone who owns a smart phone is carrying a highly integrated, power efficient platform in his/her pocket, which provides a considerable amount of computational performance, a number of high-end sensors and various facilities of wireless communication and user interaction.The design challenges facing industry in order to achieve such systems range from transistor level hardware design optimisation over system planning and integration to the implementation of mechanisms for scheduling, networking and fault management. At the same time, manufacturers provide software development kits that enable and facilitate access to hardware facilities of these systems (SDKs for smart phones and FPGAs, programming libraries for GPUs, performance primitives for microprocessors). This provides new opportunities for the area of bio-inspired hardware design and optimisation to create novel and competitive real-world applications, supported by state of the art electronic devices. Furthermore, this research area offers the possibility to explore and master emerging technologies on various levels in addition to and beyond standard engineering approaches.
[Read more ...]

Evolutionary based Hyper-Heuristics and Their Applications

By Rong Qu and S. Sima Uyer
Hyper-heuristics have recently attracted an increasing research attention in a wide range of disciplines including artificial intelligence, operations research, engineering and computer science. Researchers in hyper-heuristics aim to design and develop general solvers for a range of problems, rather than dedicated algorithms for specific problems or problem instances. Due to its efficiency and generality in providing “good enough, fast enough” solutions in solving various problems with less amount of tuning effort, hyper-heuristics have been applied to a range of domains including function optimization, combinatorial optimization, as well as scheduling, timetabling and planning.
This special session is being organized as an activity of the Intelligent Systems Applications Technical Committee of the Computational Intelligence Society of IEEE and aims to bring together advanced developments in both research and practice of hyper-heuristics and widen the existing applications on various problems in education, industry, engineering, management and business, etc.
[Read more ...]

Surrogate-Assisted Evolutionary Optimization of Expensive Problems

By Xiaoyan Sun, Yew Soon Ong and Yaochu Jin
Surrogate-assisted evolutionary optimization of computationally expensive problems is an area of research that has grown rapidly in recent years. The motivation for this interest is that constructing a surrogate model to approximate an expensive function can substantially reduce the computational cost for fitness evaluations in evolutionary optimization and improve the optimization search performance. This is of significant importance, as in many real-world problems fitness evaluations are computationally expensive.
The aim of this special session is to bring together researchers from different application fields working on evolutionary optimizations assisted by surrogate models. The main focus is to review and discuss about the state of the art in the theory and practice of using surrogate-assisted evolutionary computation for computationally expensive real-world problems, including engineering design, qualitative optimizations with interactive evolutionary computation, and chemical process optimizations, to name a few. Interested topics
[Read more ...]

Quantum Computing and Evolutionary Computation

By William N. N. Hung, Marek Perkowski, and Hanwu Chen
Although quantum computing is still in its nascent days, there are experiments that successfully perform quantum computation on a small number of qubits. Recently, researchers at the NIST demonstrated continuous quantum operations using a trapped-ion processor. Other researchers have discovered a way to make quantum devices using technology common in our current chip-making industry. Historically, classical computer concepts and underlying technologies have been invented by mathematicians and physicists rather than engineers. It was engineers, however, who took basic concepts and ideas and created the practical powerful and inexpensive computers of today. We believe that the same will happen in case of quantum computing.
As quantum information and computation research continues to develop, we will see increasing interest in adapting the philosophy of quantum computing, information theory and ideology into other, more traditional aspects of computational research. Although the hardware technology to realize quantum computing still yet to be materialized, research about the theoretical aspects of quantum computing and its ideology has enjoyed some success with artificial and computational intelligence.
This special session focus on combining various aspects of quantum computing, information theory, and other aspects with existing fields in artificial intelligence, especially evolutionary computation. For example, quantum computing has inspired ideas in evolutionary algorithms. Quantum probability is important because probability is inherently used in evolutionary and other stochastic algorithms. Quantum entanglement can further revolutionize the above algorithmic approaches. Quantum information theory also has great potential as many research have correlated information theory with evolution. Quantum complexity theory is also closely related to algorithm complexity.
[Read more ...]

Simulation Model Based Evolutionary Computation and Its Application

In many engineering design applications, the evaluation of candidate solutions often requires computer simulation and/or physical experiments. One cannot directly apply traditional evolutionary algorithms since simulation and experiments can be very expensive or inaccurate. Thus simulation techniques and modeling methods need to be carefully designed and appropriately embedded in evolutionary algorithm frameworks. Recently, simulation model based evolutionary computation has been becoming a very active research area. This special session aims at bringing researchers who are interested in this area together to review the current state-of-art, exchange the latest ideas and explore future directions.
Topics of interests include but not limited to:
[Read more ...]

Evolutionary Robotics

By Patricia A. Vargas, Dario Floreano, and Phil Husbands
Evolutionary Robotics (ER) aims to apply evolutionary computation techniques, inspired by Darwin’s principle of selective reproduction of the fittest, to automatically design the control and/or hardware of both real and simulated autonomous robots. Having an intrinsic interdisciplinary character, ER is being employed towards the development of many fields of research, among which we can highlight neuroscience, cognitive science, evolutionary biology and robotics. Hence the objective of this special session is to assemble a set of high?quality original contributions that reflect and advance the state?of?the?art in the area of Evolutionary Robotics, with an emphasis on the cross?fertilization between ER and the aforementioned research areas, ranging from theoretical analysis to reallife applications.
[Read more ...]

Evolutionary Computation for Large Scale Global Optimization

By Ke Tang, Zhenyu Yang, and Thomas Weise
In the past two decades, different kinds of nature-inspired optimization algorithms have been developed and applied to solve optimization problems, including Simulated Annealing (SA), Evolutionary Algorithms (EAs), Differential Evolution (DE), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Estimation of Distribution Algorithms (EDA), etc. Although these approaches have shown excellent search abilities when applying to some small or medium size problems, many of them will encounter severe difficulties when applying to large scale problems, e.g., problems with up to thousands of variables. The reasons appear to be two-fold. First, the complexity of a problem usually increases with the number of decision variables, number of constraints, or even number of objectives (for multi-objective optimization). This emergent complexity might prevent a previously successful search strategy from finding the optimal solution. Second, the solution space of the problem increases exponentially with the number of decision variables, and a more efficient search strategy is required to explore all the promising regions with limited computational resources.

Historically, scaling up EAs to large scale problems has attracted much interest, including both theoretical and practical studies. However, existing work in the areas of EAs are still limited given the significance of the scalability issue. Due to this fact, this special session is devoted to highlight the recent advances in EAs for large scale optimization problems, involving single objective or multiple objectives, unconstrained or constrained problems, binary or discrete or real or mixed decision variables. Specifically, we encourage interested researchers to submit their latest work on:
[Read more ...]

Evolutionary Computation in Dynamic and Uncertain Environments

By David Pelta, Shengxiang Yang and Yaochu Jin
Many real-world optimization problems are subjected to dynamism and uncertainties that are often impossible to avoid in practice. For instance, the fitness function is uncertain or noisy as a result of simulation/ measurement errors or approximation errors (in the case where surrogates are used in place of the computationally expensive high fidelity fitness function). In addition, the design variables or environmental conditions can be perturbed or they change over time.
The tools to solve these dynamic and uncertain optimization problems (DOP) should be flexible, able to tolerate uncertainties, fast to allow reaction to changes and adaptive. Moreover, the objective of such tools is no longer to simply locate the global optimum solution, but to continuously track the optimum in dynamic environments, or to find a robust solution that operates properly in the presence of uncertainties.
The last decade has witnessed increasing research efforts on handling dynamic and uncertain optimization problems using evolutionary algorithms and other metaheuristics, and a variety of methods have been reported across a broad range of application backgrounds.
This special session aims at bringing together researchers from both academia and industry to review the latest advances and explore future directions in this field. Topics of interest include but are not limited to:
[Read more ...]

Evolutionary Computation for Intelligent Network Systems

By Shengxiang Yang, Jun Zhang, Franz Rothlauf, and Biliana Alexandrova-Kabadjova
The impact of optimization in network environments on the modern economy and society has been growing steadily over the last few decades. The worldwide division of labor, the connection of distributed centers, and the increased mobility of individuals and devices lead to an increased demand for efficient solutions to solve optimization problems in network systems. Along with the development of more powerful computer systems, design and optimization techniques like computational intelligence approaches have been developed that allow us to use computer systems for the systematic design, optimization, and improvement of different network systems.
The aim of the special session is to promote research on the applications of Evolutionary Computation, including evolutionary computation, nature-inspired computational models, meta-heuristic techniques, and other intelligent methods, to the solution of problems in network systems.  Topics of interest include, but are not limited to: 
[Read more ...]

Swarm Intelligence in Data Mining

By Yuhui Shi and Ying Tan
With the advances of information technology, the amount of data being collected every day grows exponentially.  How to analyze and extract useful information, pattern, and/or knowledge from this huge amount of data is very critical to bring intelligence into the systems we are using, being built, and to be built.  Data mining techniques are the commonly used tools to process the huge data to retrieve useful information. Recently, there is a trend to utilize swarm intelligence algorithms as data mining techniques. 
The aims of the special session are to provide a platform for researchers to exchange their unpublished research work related to swarm intelligence techniques and their applications to data mining, and to explore new advances on swarm intelligence techniques and their applications to analyze and extract information and/or knowledge from huge data. Topics of interest include, but are not limited to:
[Read more ...]

Evolutionary Computation for Creative Intelligence

By Chuan-Kang Ting, Francisco Fernández de Vega, and Palle Dahlstedt
Evolutionary computation (EC) techniques, including genetic algorithm, evolution strategies, genetic programming, particle swarm optimization, ant colony optimization, differential evolution, and memetic algorithms, have shown to be effective for search and optimization problems. Recently, EC gained several promising results and becomes an important tool in Computational Creativity, such as in music, visual art, literature, architecture, and industrial design.
The aim of this special session is to reflect the most recent advances of EC for Computational Creativity, with the goal to enhance autonomous creative systems as well as human creativity. This session will allow researchers to share experiences and present their new ways for taking advantage of EC techniques in Creativity. Topics of interest include, but are not limited to, EC technologies in the following aspects:
[Read more ...]

Nature-Inspired Constrained Optimization

By Efrén Mezura-Montes and Helio J.C. Barbosa
In their original versions, nature-inspired algorithms for optimization such as evolutionary algorithms (EAs) and swarm intelligence (SI) are designed to sample unconstrained search spaces.Therefore, a considerable amount of research has been dedicated to adapt them to deal with constrained search spaces. The objective of the session is to present the most recent advances in constrained optimization using different nature-inspired techniques. The session seeks to promote the discussion and presentation of novel works related with (but not limited to) the following issues:
[Read more ...]

Nature Inspired Computing for Air Transportation

By Sameer Alam and Lam Bui
Air Transportation is a complex, multi-dimensional, highly-distributed yet highly interdependent dynamical system. Research problems in Air transportation are often discontinuous, non-differential, multi-modal, noisy and not well defined. From trajectory optimization to air traffic flow management, from scheduling of flights to conflict detection & resolution, Nature Inspired techniques such as Evolutionary Computation, Genetic Algorithms, Swarm Intelligence, Evolutionary Neural Networks, Machine Learning, Evolutionary Fuzzy Systems  have emerged as important tools to address complex problems of the Air Transportation domain to which traditional methodologies and approaches are ineffective or infeasible. Typical problems are highly nonlinear with large search space where finding a feasible solution by traditional methods is not practical. Nature Inspired techniques in Air Transportation can provide new approaches into solving such problems and can provide new insights.
[Read more ...]

Evolutionary Algorithms with Statistical & Machine Learning Techniques

By Aimin Zhou, Qingfu Zhang, Jose A. Lozano, and Pedro Larrañaga
An evolutionary optimization algorithm can be viewed as a learning process-it learns properties of the problem in question and locates the optimal solution. Therefore, it is very natural to introduce statistical & machine learning techniques (SML) into evolutionary algorithms (EA). Much effort has been made along this line. Examples of EAs with SML include: estimation of distribution algorithms, ant colony optimization, cross entropy methods, evolutionary algorithms based on statistical surrogate models, to name a few. Combination of EAs and SML has been proven to be an efficient strategy for dealing with hard optimization problems. This special session aims at bringing researchers who are interested in this area together to review the current state-of-art, exchange the latest ideas and explore future directions.
[Read more ...]

Complex Networks and Evolutionary Computation

By Jing Liu
The application of complex networks to evolutionary computation (EC) has received considerable attention from the EC community in recent years. The most well-known study should be the attempt of using complex networks, such as small-world networks and scale-free networks, as the potential population structures in evolutionary algorithms (EAs). Structured populations have been proposed to as a means for improving the search properties because several researchers have suggested that EAs populations might have structures endowed with spatial features, like many natural populations. Moreover, empirical results suggest that using structured populations is often beneficial owing to better diversity maintenance, formation of niches, and lower selection pressures in the population favouring the slow spreading of solutions and relieving premature convergence and stagnation. Moreover, the study of using complex networks to analyse fitness landscapes and designing predictive problem difficulty measures is also attracting increasing attentions. On the other hand, using EAs to solve problems related to complex networks, such as community detection, is also a popular topic.
This special session seeks to bring together the researchers from around the globe for a creative discussion on recent advances and challenges in combining complex networks and EAs. The special session will focus on, but not limited to, the following topics:
[Read more ...]

Memetic Computing

By Ferrante Neri, Zhu Zexuan, and Ruhul Sarker
Memetic Computing is a broad subject which studies complex and dynamic computing structures composed of interacting modules (memes) whose evolution dynamics is inspired by the diffusion of ideas. Memes are simple strategies whose harmonic coordination allows the solution of various problems.
The use of sophisticated computational intelligence approaches for solving complex problems in science and engineering has increased steadily over the last 20 years. Within this growing trend, which relies heavily on state-of-the-art optimisation and design strategies, the methodology known as Memetic Computing is, perhaps, one of the recent most successful stories. From the word "mimeme" of Greek origin, Dawkins coined the term "meme" in his 1976 book on "The Selfish Gene" (Dawkins 1976). He defined it as being "the basic unit of cultural transmission or imitation".
In computational science the concept of meme has been introduced within Memetic Algorithms, i.e. a class of algorithms composed of an evolutionary framework and a set of local search components integrated within the generation cycle or the external framework. Subsequently, the concept meme in Computer Science has been expanded and abstracted to generic structures composed of linked operators. The interaction amongst these operators allows the functioning of the entire structure.
This special session focuses on Memetic Computing, Memetic Algorithms, hybrid approaches, and any algorithm which can be seen as a linked structure of diverse operators, such as hyper-heuristics, co- evolutionary and self-adaptive approaches. A
special attention will be given to automatic generation of algorithms and to research works focused on the algorithmic coordination of diverse algorithmic components.
[Read more ...]

Process Mining: Applying Evolutionary Computation Techniques to Process Mining

By Moe Thandar Wynn, Jan Vanthienen, Zbigniew Michalewicz, and Adam Ghandar
The goal of this special session is to join experts in the area of process mining to present new techniques and applications. The session is organized by the IEEE Task Force on Process Mining.
Process mining is a relatively young research discipline that sits between computational intelligence and data mining on the one hand and process modeling and analysis on the other hand. The idea of process mining is to discover, monitor and improve real processes (i.e., not assumed processes) by extracting knowledge from event logs readily available in today's systems. Process mining provides an important bridge between data mining and business process modeling and analysis. Process mining research at TU/e started in the late nineties. At that time there was little event data available and the process mining techniques were extremely naive and hence unusable. Over the last decade event data has become readily available and process mining techniques have matured. Moreover, process mining algorithms have been implemented in various academic and commercial systems. Today, there is an active group of researchers working on process mining and it has become one of the”hot topics” in BPM research. There is also a huge interest from industry in process mining. More and more business and operations software vendors are adding process mining functionalities to their tools. 
In the light of these trends, a special session focusing specifically on process mining promotes awareness of the unique issues involved, and aims to attract publications in this large and growing field. Furthermore, the diverse range of computational intelligence approaches and methodologies are well suited to approaches combining process mining and other computational intelligence adaptive business systems.
[Read more ...]

Differential Evolution: Past, Present and Future

By Kai Qin, Kenneth V. Price, Uday K. Chakraborty, Ponnuthurai Nagaratnam Suganthan, Jouni Lampinen
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:
[Read more ...]

Autonomous Evolutionary Optimization

By Kai Qin, Ke Tang, Yew Soon Ong
Nowadays, numerous evolutionary algorithms (EAs) have been proposed, while new algorithms still come up incessantly. Although EAs have demonstrated strong efficacy in many real-world applications, practitioners often encounter the difficulty of determining a most effective algorithm configuration and parameter setting to solve a specific problem at hand, especially given little prior knowledge about this problem. Note that algorithm configuration indicates algorithm framework and component operators, which can inherently distinguish between EAs. Furthermore, even a well-calibrated EA cannot guarantee consistent competence at different searching stages since sub-regions of the search space explored at varying searching stages may not always favors one single EA.
Last decades have witnessed a rapidly growing research interest in autonomous evolutionary optimization (AEO). Such techniques are characterized by intelligent adaptation and adjustment of algorithm configurations and parameter settings to automatically accommodate diverse problem characteristics and changing problem conditions, which aim at avoiding the improper choices made subjectively by practitioners and the incompetence of one single well-calibrated EA for the entire searching course. AEO techniques usually employ neuro-fuzzy, statistical and machine learning techniques to discover promising configurations that can lead to desirable optimization performances on some well-studied problems from different domains and utilize these discoveries as the external knowledge in the design of AEO techniques, and moreover to exploit the run-time accumulated searching experience to derive promising adaptation rules that can enlighten the ongoing course of search. Although AEO techniques typically involves the time-consuming learning and adapting procedures based on a large volume of evaluated candidate solutions, recent breakthroughs on massively parallel systems (e.g. graphics processing units) may significantly accelerate their computation speed and accordingly boost their practical efficacy.
This special session aims to highlight the latest development in this rapidly emerging research area by bringing together researchers from both academia and industry. Authors are invited to submit their original and unpublished work in the areas including, but not limited to:
[Read more ...]

Graph-Based Evolutionary Computation

By Hisashi Handa, Shinichi Shirakawa, and Shingo Mabu
Recently, graph-based evolutionary computation (GBEC) has attracted much attention due to the flexible representation capability of graphs. The growing computational resources available today make the GBEC practical against real-world problems. We have various kinds of practical application areas which should be with graph representations: the graph mining from large-scaled protein databases, the knowledge extraction from web or SNS, complex network design and so on. This
special session aims at discussing various aspects of the use of graphs in Evolutionary computation: practical applications, coding methods, genetic operation, and evolutionary algorithms with graphs. This session will also explore future directions of this approach.
[Read more ...]

Artificial Bee Colony Algorithm

By M. Fatih Tasgetiren and Quan-Ke Pan
Swarm intelligence is a branch of evolutionary computation, which models the behaviors of the self-organizing individuals performing collective intelligence. Honey bees are a typical example of self-organizing individuals carrying out global tasks collectively without supervision. Foraging which is performed based on self organization and division of labor is one of the crucial tasks of a bee colony. Karaboga described an algorithm called artificial bee colony-ABC which simulates the foraging behavior of honey bees and used this algorithm to solve numeric optimization problems. In ABC, the foraging labor is divided over three categories of bees: employed bees exploiting a certain food source and sharing their information about the rich sources with their mates, onlooker bees waiting in the hive to watch the employed bees and being recruited to rich sources depending on the information provided by employed bees, and scout bees searching the environment randomly to find an undiscovered food source. In ABC approach, the position of a food source represents a possible solution to the optimization problem addressed and the profitability of the source corresponds to the quality of the solution. ABC algorithm starts the optimization process (foraging behavior) with a population of randomly generated solutions (food source positions) and then iteratively improves this population to discover better solutions (more profitable sources). The improvement process consists of three phases: sending employed bees to their solutions and recruiting onlooker bees to the solutions probabilistically depending on their fitness values for improving them; and after determining the exhausted sources, converting their employed bees into scouts discovering new solutions randomly for the exhausted ones.
The session is mainly intended to bring together colleagues working on the Artificial Bee Colony (ABC) algorithm and its applications. Topics of interest include but are not limited to:
[Read more ...]

Applications of Evolutionary Computation in Biomedical Engineering

By John McCall and Lilian Tang
Biomedical Engineering aims to apply engineering principles to biomedical systems. A biomedical system may be very broadly defined as any engineered device or apparatus that interacts with a biological entity to achieve a medical purpose. This is a fast-growing research area which is throwing up many complex problems as researchers grapple with the need to model complex systems and interpret massive biomedical datasets.
In this session, we invite contributions from researchers who have applied techniques in evolutionary computation to real-world problems in biomedical engineering. Techniques may come from the whole range of evolutionary computing, including (but not limited to) Genetic Algorithms, Evolution Strategies, Particle Swarm Optimisation, Differential Evolution, Ant Colony Optimisation, Estimation of Distribution Algorithms, and hybrids with other approaches. Application areas may include: medical diagnostic systems; theranostics; medical imaging; advanced prosthetics; biosensors; telemedicine;  treatment or equipment design and optimisation; or any other biomedical engineering application.
[Read more ...]

Fast Evolutionary Metaheuristic Algorithms for Combinatorial Optimization Problems

By Chu-Sing Yang, Tzung-Pei Hong, Ming-Chao Chiang, and Chun-Wei Tsai
Metaheuristic algorithms provide an efficient method to find an acceptable solution for combinatorial optimization problems in a reasonable time. Among them are evolutionary algorithms, ant colony optimization, particle swarm optimization, and so on. These algorithms have been widely and successfully used in solving many complex problems. Recently, many studies have paid particular attention to reduce the computation time of metaheuristic algorithms (e.g., by reducing the number of dimensions of each pattern or by reducing the number of patterns) because many data sets created in our daily life have become not only larger but also higher dimensional.
This special session will be focusing on the application of metaheuristic algorithms to solve combinatorial optimization problem. Authors are encouraged to submit both theoretical and practical articles to this special session. The topics include, but not limited to, the following:
[Read more ...]

Evolutionary Computation in Social Network Analysis and Applications

By Di Wang and Xiao-Jun Zeng
Social networks have created a new communication culture and behavior for 21st century. With the highly developed electronic facilities (computer, iPod, smart phone etc) and mature virtual communication environment (facebook, twitter, forum, video conference, etc) in the recent decade, social networking has shown more and more significant impact to almost every aspect of human life, from the most common online shopping, social relations to the extreme terrorism and riots. The great importance of the social networks provides a great and can-not-miss opportunity to the Evolutionary Computation community. 
Social networking is complicated, evolving and dynamic. The traditional social network analysis based on static graph theory is far from enough to handle these challenges whereas evolution computation techniques show great promising. The existing research of evolutionary computation in social network analysis and mining includes analyzing commercial and e-commercial activities, social learning, financial exchange and stock forecasting, diffusion of novelty, belief networks, happiness and friendship evolving analysis etc. To promote the further research and applications of evolutionary computation in social network analysis, this special section will provide the a forum to bring together cutting edge research in applying the evolutionary computation to social network analysis and mining as well as related real applications. It will help develop novel approaches, discover new problems, share application experiences, and enhance the research efforts and awareness in this important area.
[Read more ...]

Social Intelligence in Games

By Robert G. Reynolds, Mostafa Ali, Yuhui Shi, and Gary Yen
This special session will examine the application of various socially motivated approaches to the incorporation of social intelligence into Computer Games. These approaches include Particle Swarms, Ant Colonies, and Cultural Algorithms among others.
Some example applications include:
[Read more ...]

FUZZ-IEEE 2012 Special Sessions:

Type-2 Fuzzy Logic Theory

By Jerry M. Mendel and Robert John
Fuzzy logic is credited as an adequate methodology for building systems that deliver satisfactory performance in the face of uncertainty and imprecision. Real world fuzzy applications suffer from numerous sources of uncertainty from sensors, actuators and the meaning of the fuzzy sets, e.g., the definition of say fast will change under different conditions, or the experts designing the fuzzy system may have differing ideas about what constitutes fast.
To date most fuzzy systems rely on type-1 fuzzy sets which have precise membership functions which can not, by definition, model uncertainty as the membership functions are totally precise.
Type-2 fuzzy logic is an emerging paradigm that seeks to overcome this limitation of type-1 fuzzy logic. Type-2 systems use type-2 fuzzy sets characterised by a fuzzy membership function. The membership functions of type-2 fuzzy sets are three-dimensional and include a footprint of uncertainty. This extra dimension provides additional degrees of freedom that make it possible to directly model and handle uncertainties.
There remains a great deal of deep research to be done exploring the strengths of type-2 fuzzy logic. The aim of this special session is to present top quality research in the area of type-2 fuzzy logic theory. The session will also provide a forum for the academic community and industry to report on the recent advances in type-2 fuzzy logic theory.
[Read more ...]

Applications of Type-2 Fuzzy Systems

By Hani Hagras and Simon Coupland
Type-2 fuzzy logic is an emerging paradigm which seeks realize computationally efficient fuzzy systems with the ability to give excellent performance in the face of highly uncertain conditions. Type-2 fuzzy systems attempt to achieve this by directly modelling the uncertainties in a problem with an additional degree of freedom in the definition of membership functions.
The aim of this special session is to present top quality research in the areas related to the practical aspects and applications of type-2 fuzzy systems. The session will also provide a forum for the academic community and industry to report on the recent advances on the type-2 fuzzy logic system research in the various domains of type-2 fuzzy logic.
[Read more ...]

Type-2 Fuzzy Logic Control

By Christian Wagner and Dongrui Wu
Type-2 fuzzy logic control is a paradigm which takes the fundamental concepts in control from type-1 fuzzy logic and expands upon them in order to deal with the high levels of uncertainty present in a vast number of real world control problems. A wide variety of traditional areas in control (that have also been addressed through type-1 fuzzy logic control) have already been addressed with type-2 fuzzy logic, from the control in steel production plants to the control of marine diesel engines and robotic control. In many applications, it has been shown that type-2 fuzzy logic can provide benefits over both traditional forms of control as well as type-1 fuzzy logic and it is the aim of this special session to attract a comprehensive selection of high quality current research in this area of type-2 control, motivating further collaboration and providing a platform for the discussion on future directions of type-2 fuzzy logic control by researchers active in the field.
The interest in type-2 fuzzy logic, specifically in both its "flavours": interval type-2 and general type-2 fuzzy logic, has steadily grown over recent years. This rise in interest has been fuelled both by the realization that type-2 fuzzy logic can indeed provide benefits in dealing with situations subject to high levels of uncertainty as well as a stream of new theoretical results which have served to make type-2 fuzzy logic more efficient, more accessible and more applicable to real world systems – in particular control where computational performance is a fundamental criterion.
This special session will address advances in interval type-2 as well as general type-2 fuzzy logic control, including different types of fuzzy logic control such as Mamdani and TSK based fuzzy systems. As such, the session aims to provide both an overview of the current top quality research in the area, as well as a window into the future of type-2 fuzzy logic control.
[Read more ...]

Inter-Relation Between Interval and Fuzzy Techniques

By Vladik Kreinovich and Karen Villaverde
The relation between fuzzy and interval techniques is well known; e.g., due to the fact that a fuzzy number can be represented as a nested family of intervals (alpha-cuts), level-by-level interval techniques are often used to process fuzzy data.
At present, researchers in fuzzy data processing mainly used interval techniques originally designed for non-fuzzy applications, techniques which are often taken from textbooks and are, therefore, already outperformed by more recent and more efficient methods.
One of the main objectives of the proposed special session is to make the fuzzy community at-large better acquainted with the latest, most efficient interval techniques, especially with techniques specifically developed for solving fuzzy-related problems.
Another objective is to combine fuzzy and interval techniques, so that we will be able to use the combined techniques in (frequent) practical situations where both types of uncertainty are present: for example, when some quantities are known with interval uncertainty (e.g., coming from measurements), while other quantities are known with fuzzy uncertainty (coming from expert estimates).
[Read more ...]

Ambient Intelligence and Fuzzy Logic: Methodologies and Applications

By Leonard Barolli and Vincenzo Loia
Intelligent environments are opening unprecedented scenarios where people interact with electronic devices embedded in environments that are sensitive and responsive to the presence of people. The term “Ambient Intelligence” (or more shortly, AmI) reflects this tendency. The emphasis of AmI is on greater user-friendliness, more efficiency in services’ support, user empowerment and support for human interactions. People are surrounded by smart pro-active devices that are embedded in all kinds of objects: an AmI environment is capable of recognizing and responding to the presence of different individuals, working in a seamless, unobtrusive and often invisible way. Computation Intelligence plays a fundamental role for the design of advanced AmI systems, thanks to its ability in bringing together human expertise and deals with the uncertainties and imprecision typical of complex  adaptive environments. In environments based on ambient intelligence needs, features, and the environment itself may not be always characterized precisely, and accurately, thus demanding for the ability of fuzzy description. This special session is focused to attract original contributions that discuss how Fuzzy Logic, both from theoretical and practical issues and even in a hybrid framework exploiting Computational Intelligence, may play a strategic role in solving problems around Ambient Intelligence.
[Read more ...]

Soft data analysis based knowledge discovery

By Mika Sato-Ilic and Lakhmi C. Jain
While the amount of data is growing at an exponential rate, we are faced with the challenge of analysing, processing and extracting useful information from it.
“Soft data analysis” (SDA) is based on soft computing which is a consortium of complementary methodologies including fuzzy logic, neural networks, probabilistic reasoning, genetic algorithms, and chaotic systems. Soft computing reflects the pervasiveness of imprecision and uncertainty in the real world which hard computing does not reflect. The guiding principal of soft computing is to exploit the tolerance of imprecision and uncertainty in order to achieve tractability, robustness, and low solution cost.
In data modeling, recently, there has been a paradigm shift from conventional computational statistics to machine learning based on “knowledge discovery”.
This session provides novel techniques to the soft data analysis paradigms. It summarizes the successful and possible applications of the soft computing analysis paradigms based on knowledge discovery.
Topics of interest include, but are not limited to:
[Read more ...]

Evolving and Adaptive Fuzzy Systems: Towards Autonomous Learning

By P. Angelov, D. Filev, and N. Kasabov
The concept of evolving and adaptive fuzzy systems was established during the last decade as a synergy between fuzzy rule-based systems as structures for information representation and real time methods for autonomous machine learning. This emerging area of research targets non-stationary processes by developing novel and efficient on-line learning methods and computationally efficient algorithms for real-time applications.
One of the important research challenges today is to develop methodologies, concepts, algorithms and techniques towards the design of systems with a higher level of their structure and knowledge of the environment. That is, the system must be able to evolve, to self-develop, to self sensor networks, assisted ambient intelligence, embedded soft computing diagnostics prognostics algorithms, intelligent agents, smart evolving sensors; autonomous robotic systems etc. are some of the natural implementation areas of evolving and adaptive intelligent systems.
This special session aims to bring together old friends and experienced industry-based and academic researchers with enthusiastic newcomers. It supported and organised by the Adaptive and Evolving Fuzzy Systems (AEFS) Task Force (www.fee.unicamp.br/IEEE_AFS/ ) Computational Intelligence Society, IEEE.
[Read more...]

Fuzzy Ontologies and Fuzzy Markup Language Applications

By Chang-Shing Lee and Giovanni Acampora
It is widely pointed out that classical ontology is not sufficient to deal with imprecise and vague knowledge for some real world applications like personal diabetic diet recommendation. On the other hand, fuzzy ontology can effectively help to handle and process uncertain data and knowledge. Recently, the research on the ontology has been spread widely to be critical components in the knowledge management, Semantic Web, business-to-business applications, and several other application areas. Ontologies are a suitable way for representing complex knowledge and facilitating knowledge share and reuse. The concept of ontology has been widely embraced by the fuzzy research community by playing an important role in the development of distributed systems and the composition reveals a vital strategy for enterprise collaboration. In this context, the Fuzzy Markup Language (FML) is one of the most important results because it allows fuzzy scientists to express their ideas in abstract and interoperable way by improving their productivity and, at the same time, increasing the average quality of their works. This special session invites high-quality conceptual, analytical and empirical articles representing intelligent agent and knowledge mining information systems and their integration. The objective of the proposed special issue is to highlight an ongoing research on fuzzy and FML approaches for ontology applications as well as their applications on various domains.
[Read more ...]

Bridging Theory and Application in Clustering - Fuzzy Clustering, Inductive Clustering, Data Privacy, Classifier, Collaborative Filtering

By Yuchi Kanzawa and Yasunori Endo
Crisp and fuzzy clustering are the most important tools in the field of data mining and machine learning, and many algorithms thus have been proposed so far. In terms of  theory, new methodologies including Inductive Clustering, Data Privacy, and Data with Tolerance recently attract researchers' attention. In addition, clustering has been developed into various applications including Classifier, Collaborative Filtering and so on.
In this special session, leading-edge works of crisp/fuzzy clustering with the new methodologies will be described and discussed. Moreover, some useful applications in the real world will be shown.
[Read more...]

Fuzzy Approaches in Database Management and Information Retrieval

By Guy De Tré, Janusz Kacprzyk, Olivier Pivert, and S?awomir Zadro?ny
One of the most crucial challenges raised by modern Database Management Systems, and by Information Systems in general, concerns – first – their ability to support a huge volume of data which can be heterogeneous, imprecise, uncertain, incomplete and/or inconsistent, and – second – to provide tools and techniques to make appropriate use of them. From a user's point of view, it is thus very desirable for such systems to possess a human centric functionality, and a high flexibility.
Flexibility in such a context might be understood in several ways, among which the following ones are most important:
i)    the capability of querying large amount of data in a user-friendly way so as to retrieve the information which is the most relevant to specific user needs;
ii)    the capability of representation, management and exploitation of imprecise, partially known, and uncertain data.
Fuzzy Logic and Soft Computing have, for a long time, constituted an important source of inspiration for numerous research works aimed at dealing with various facets of flexibility in Databases and Information Systems. The primary purpose of this special session is to highlight the latest scientific advances within the Fuzzy Logic and Soft Computing fields applied to Databases and Information Systems.
This special session will be an exciting opportunity to exchange ideas and to discuss theoretical and experimental results in this research domain. Hopefully, it will contribute to identifying new promising directions of research and unsolved problems in this area.
[Read more ...]

Granularity and Uncertainity

By T.Y. Lin
Lotfi Zadeh explained the concept of granular mathematics informally as follows: If we view classical mathematics (CM) as mathematics of points, denoted by MATH(points), then granular mathematics (GrM) is mathematics of granule, denoted by MATH(granules), So MATH(points) is a mathematics that has the capability of specifying a point upto infinite precision, while MATH(granule) can only described a point upto a granule. GrM intrinsically is mathematics of uncertainty. With recent axiomatization of GrM (GrC2011), we can foresee many intensive development of formal theory and applications. For examples, GrM has unified various concepts of generalized rough sets, and provides a formal base (this may not be the only way) for Zadeh's recent notion of f-geometry, including the classical digital geometry. We are expecting that f-geometry and hence GrM will play a significant role in the rise game development in social networks, and etc. In conclusion, it is important to have special sessions to provide researchers from universities, laboratories and industry to discuss various views, methodologies and applications in handling the granularity and uncertainty.
[Read more ...]

New Directions in Fuzzy Adaptive Control

By Valentina E. Balas and Tsung-Chih Lin
The aim of this special session is to present the state-of-the-art results in the area of adaptive intelligent control theory and applications and to get together researchers in this area.
Adaptive control is a technique of applying some methods to obtain a model of the process and using this model to design a controller. Especially,   fuzzy   adaptive control has been an   important area of active research for over  three decades now. Significant   developments   have   been   seen,   including theoretical   success   and   practical   design.   One   of   the   reasons   for   the rapid growth of fuzzy adaptive control is its ability to control plants with uncertainties during its operation.
The papers in this special session present the most advanced techniques and algorithms of adaptive control. These include various   robust   techniques,   performance   enhancement  techniques,   techniques   with   less   a-priori   knowledge   and   nonlinear intelligent adaptive control techniques.
This special session aims to provide an opportunity for international researchers to share and review recent advances in the foundations, integration architectures and applications of hybrid and adaptive systems.
[Read more ...]

Aggregation Operators

By Gleb Beliakov, Humberto Bustince and Gang Li
Aggregation Operators (AGOPs) play a key role in fuzzy sets theory as fuzzy logic connectives. Many advances in theoretical and applied research are being produced in this field. Traditional aggregation operations such as the weighted average are now acknowledged as particular cases of more general families of aggregation operations, such as Choquet integrals. Triangular norms and conorms, uninorms, symmetric sums, OWA to name a few, are widely used families of AGOP. Along theoretical aspects, an increasing interest to practical applications in now emerging. This requires to face new challenges, regarding computational and domain specific issues.
This special session will be dedicated to theoretical and practical aspects of AGOPs. Specific topics would include: practical constructions of AGOP, real-world applications, relationships to random sets, identification of fuzzy measures, weighting functions for AGOP, AGOP with specific properties, and parameter learning.
[Read more ...]

Aggregation operators in image processing

By Gleb Beliakov, Humberto Bustince, and Javier Fernandez
Image processing is nowadays a very active area of research in the scientific community. Due to the wide variety of applications that can be considered in this field, many different techniques are considered. One of the most successful ones is the use of aggregation functions and related concepts (including fuzzy connectives) in order to handle images. These kind of techniques have provided very good results in many different problems, from segmentation to edge detection, and including binocular vision, content based image retrieval, object tracking, pattern or texture recognition, among others.
The main goal of this special session is to present a state-of-the-art in aggregation functions and, more specifically, their applications in image processing. In this sense, this session is complimentary to the Aggregation Operators special session, allowing researchers to share the theoretical results, applications and techniques they have developed for image processing in its wider sense, using aggregation functions and other fuzzy logic connectives.
[Read more ...]

Evolutionary Fuzzy Systems

By Yusuke Nojima, Rafael Alcalá, Hisao Ishibuchi, Francisco Herrera
After almost twenty years of efforts towards augmenting fuzzy systems with learning and adaptation capabilities, one of the most prominent approaches to do so has resulted in the emergence of Evolutionary Fuzzy Systems. These kinds of hybrid systems meld the approximate reasoning method of fuzzy systems with the adaptation capabilities of evolutionary algorithms. On the one hand, fuzzy systems have demonstrated the ability to formalize in a computationally efficient manner the approximate reasoning typical of humans. On the other hand, genetic (and in general evolution-inspired) algorithms constitute a robust technique in complex optimization, identification, learning, and adaptation problems. In this way, their confluence leads to increased capabilities for the design and optimization of fuzzy systems.
The aim of the session is to provide a forum to disseminate and discuss recent and significant research efforts on Evolutionary Fuzzy Systems in order to deal with current challenges on this topic. The session is therefore open to any high quality submission from researchers working at the particular intersection of evolutionary algorithms and fuzzy systems. The topics of this special session are as follows:
[Read more ...]

Software for Soft Computing

By Jesús Alcalá-Fdez and Jose M. Alonso
The term Soft Computing is usually used in reference to a family of several preexisting techniques (Fuzzy Logic,Neuro-computing, Probabilistic Reasoning, Evolutionary Computation, etc.) able to work in a cooperative way, taking profit from the main advantages of each individual technique, in order to solve lots of complex real-world problems for which other classical techniques are not quite well suited.
In the last few years, many software tools have been developed for Soft Computing. Although a lot of them are commercially distributed, unfortunately only a few tools are available as open source software. In the field of evolutionary computation, JCLEC (Java Class Library for Evolutionary Computation), KEEL (Knowledge Extraction based on Evolutionary Learning), and JMetal (Metaheuristic Algorithms in Java) provide nice examples of frameworks for both evolutionary and multi-objective optimization. JavaNNS (Java version of Stuttgart Neural Network Simulator) is probably the best free suite for neural networks. Regarding fuzzy modeling, Xfuzzy (a development environment for fuzzy-inference-based systems), FisPro (Fuzzy Inference System Professional), and GUAJE (Generating Understandable and Accurate fuzzy models in a Java Environment) represent very useful tools. Regarding neuro-fuzzy algorithms we can point out to NEFCLASS (Neuro-Fuzzy Classification). Finally, FrIDA (Free Intelligent Data Analysis Toolbox) and KNIME (Konstanz Information Miner) are examples of user-friendly open-source software which offer several individual tools for data processing, analysis and exploration/visualization. Please, notice that such open tools have recently reached a high level of development. As a result, they are ready to play an important role for industry and academia research.
The aim of this session is to provide a forum to disseminate and discuss Software for Soft Computing, with special attention to Fuzzy System Software. We want to offer an opportunity for researchers and practitioners to identify new promising research directions in this area.
[Read more ...]

Grey Systems–Theory and Applications

By Sifeng Liu, Yingjie Yang, Jeffrey Forrest, Robert John
Grey Systems theory has been one of new theories of systems science. Related research is mainly on the systems with “small samples”, “poor information”, and uncertainty. The theory has been established by Prof. Deng Ju-Long and his followers since early 1980s. More specifically, Grey Systems theory is a new method to study unascertained problems with a few data and poor information. Grey Systems theory works on unascertained systems with partially known and partially unknown information, and by drawing out valuable information from the generating and developing of the partially known information, it can describe correctly and monitor effectively the systematic operation behaviour.
In our daily social economic and scientific research activities, we often face situations of incomplete information, and this increases many difficulties in practice. However, the character of dealing with unascertained systems with partially known and partially unknown information has made Grey Systems theory become transect across with strong capabilities and permeate into various traditional scientific fields and disciplines. In the past 26 years, Grey Systems theory has been developed astonishingly and is maturing rapidly.
Now it has been widely applied to analysis, modelling, predictions, decision making, and control of various systems including society, economy, scientific and technological systems, agriculture, industry, transportation, mechanical, petrologic, meteorological, ecological, hydrological, legal, geological, financial, medical, military systems.
[Read more ...]

Computational Intelligence and Affective Computing

By Anton Nijholt and Dongrui Wu
Computational intelligence is a set of Nature-inspired computational methodologies and approaches to address complex real world problems to which traditional methodologies and approaches (first principles, probabilistic, black-box, etc.) are ineffective or infeasible. It includes neural networks, fuzzy logic systems, evolutionary computation, swarm intelligence, chaos theory, etc.
Affective computing is computing that relates to, arises from, or deliberately influences affects. It has been gaining popularity rapidly in the last decade because it has great potential in the next generation of human-computer interfaces. One goal of affective computing is to design a computer system that responds in a rational and strategic fashion to real-time changes in user affect (e.g., happiness, sadness, etc), cognition (e.g., frustration, boredom, etc) and motivation, as represented by speech, facial expressions, physiological signals, neurocognitive performance, etc.
Affective computing raises many new challenges for signal processing and machine learning. Especially, the body signals used for emotion recognition are very noisy and subject-dependent. Computational intelligence methods, particularly fuzzy logic systems, may be used to build intuitive and robust emotion recognition algorithms. On the other hand, emotions, which are intrinsic to human beings, may also inspire some new computational intelligence algorithms, just like how human brains inspired neural networks and population-based sexual evolution through reproduction of generation inspired evolutionary computation.
The Computational Intelligence and Affective Computing special session aims at bringing together researchers from both areas to discuss how computational intelligence algorithm can be used to solve challenging affective computing problems, and how affects (emotions) can inspire new computational intelligence algorithms. Topics of interest for this special session include but are not limited to:
[Read more ...]

Fuzzy Logic and Intelligent Web

By Sabrina Senatore and Marek Reformat
In complex and dynamic environments such as Internet, the exigency of tools supporting human desiderata is a granted feature. Web applications, as well as web services, are developed using enhanced techniques capable of intelligent processing of information. They offer features based on data patterns and relationships that could be hard to discover manually.
The Web is an open network that lends itself to applications enabling extensive and multi-level collaboration. At the same time, the web represents a global repository of information, or in general knowledge, stored in different languages, formats and locations.  This knowledge is available but not always directly usable. Intelligent web solutions that manage complex and distributed data need to be developed.  They should understand intended semantics of the data  use intelligent techniques and mechanisms to process it, and make it accessible. Applications of standards and protocols should reduce ambiguity and allow for application of automated reasoning techniques. Yet, intelligent web applications are often not designed to express and deal with uncertainties and vagueness – the unquestionable components of the real world knowledge representation.
Fuzzy logic represents a flexible infrastructure that is able to deal with the semantics of data and handle the intrinsic ambiguity in data model-theoretic representations. It provides an intelligent computing layer for enhanced data elaboration and reasoning, and fills the gap between soft human-understanding and hard machine-processing. Intelligent Web systems can benefit from these abilities by modeling ambiguity using methods and techniques more suitable for handling uncertainty and representing continuous data, as well as reasoning techniques that mimic human-like thinking processes.
This Special Session aims at providing contributions about approaches, methodologies, and tools that lead to a seamless integration of fuzzy techniques and web applications in order to achieve a truly intelligent systems. We invite original contributions that provide novel solutions to challenging problems and addressing theoretical or practical aspects of developing web intelligent systems by means of fuzzy logic–based techniques and methods.
[Read more ...]

Recent results in Takagi-Sugeno based control and observation

By Jun Yoneyama and Kevin Guelton
The so-called Takagi-Sugeno (TS) fuzzy models have been the subject of intensive research these last years. Numerous literatures are now available (see for example the international journals as Fuzzy Sets and Systems, IEEE Transactions on Fuzzy Systems, International Journal of System Science, but also some papers are now appearing in Automatica, IEEE Transactions on Automatic Control, IEEE SMC…) and a lot of papers are still submitted. The area covered concerns in both continuous and discrete cases: modeling of non-linear systems, control and observation of non-linear models, including uncertainties, Hinf and/or H2 specifications, state or input delays… Among the recent results, some are concerned with theoretical aspects and the others are concerned with applications. The goal of this special session is to get together well-known and recognized researchers to make a kind of “where are we now” meeting regarding to theoretical aspects as well as application studies of Takagi-Sugeno fuzzy model based control and observation.
[Read more ...]

Fuzzy Interpolation

By Qiang Shen, Laszlo Koczy and Shyi-Ming Chen
Fuzzy interpolation provides a flexible means to perform reasoning in the presence of insufficient knowledge that is represented as sparse fuzzy rule bases. It enables approximate inferences to be carried out from a rule base that does not cover a given observation. Fuzzy interpolation also provides a way to simplify complex systems models and/or the process of fuzzy rule generation. It allows the reduction of the number of rules needed, thereby speeding up parameter optimisation and runtime efficiency.
[Read more ...]

Fuzzy Logic on Medical, Immune and Health Technology

By Yutaka Hata
The proposed special session aims to concentrate the efforts of the community of researchers that aim development of new system to solve real biological, medical, Immunology, and health problems by designing methods, techniques, algorithms, software and implementations of Fuzzy Systems. The interest topics include but are not limited to the medical systems, health care systems, and biological and biometrics related data processing.
[Read more ...]

Fuzzy Logic and Fuzzy Systems for Very Large Data

By Marimuthu Palaniswami and Timothy Havens
Since the early 1990's, the ubiquity of personal computing technology has produced an abundance of staggeringly large data sets—the Library of Congress has stored over 160 terabytes of web data and it is estimated that Facebook alone logs over 25 terabytes of data per day.  To compound this fact, these data sets are populated from disparate, often unknown, sources and are in a wide-range of formats.  There is a great need for systems and algorithms by which one can elucidate meaning from these data sets.
Are computational complexity, storage, or memory requirements concerns in your work?  Then your paper belongs in our session!
[Read more ...]

Data Mining with Hierarchical Fuzzy Systems

By Kevin Wong and Sumudu Mendis
Fuzzy systems, such as hierarchical fuzzy systems, fuzzy signatures, and hierarchical applications of fuzzy Markovian models and fuzzy integrals, are useful to deal with real world data sets with high dimensionality or complex structure. This usefulness is derived from their ability to avoid the combinatorial explosion most traditional fuzzy approaches suffer, or by modelling the complex nature of some data sets effectively. In general, the area of data mining abounds with high dimensional or complex structured data. On the other hand, industrial data mining applications need to overcome scalability issues when dealing with very large data sets. In this session, focus on fuzzy and related approaches to such data mining tasks.
[Read more ...]

Fuzzy algebraic and relational structures – theory and applications

By Arsham Borumand Saeid, Branimir Seselja, and Andreja Tepavcevic
Since the beginning of fuzzy era algebraic and relational structures have been investigated in this new framework. Dealing with substructures and relations as subsets of the  domain's square, researchers were generalizing these to functions with values in the unit interval and lately in various lattices. Along with theoretical investigations,  applications turn out to be widely used. E.g., fuzzy semigroups and monoids are used in automata theory, in  formal languages, for linguistic variables etc.; fuzzy relational structures are applied in fuzzy controllers, and generally in artificial intelligence. In particular, new methods concerning different fuzzy products of relations and solutions of relational equations are shown to be very effective in the mentioned applications.  Finally the lattice valued approach, with residuated and connected lattices as the structure of membership values turn out to be more suitable in this framework, generalizing the unit interval as the co-domain.
The aim of the session is to bring together researchers dealing with fuzzy algebras and relational structures (especially  related to many valued logic) in order to discuss new results and problems, in both theory and applications i.e.  to amalgamate some recent theoretical and empirical contributions that reflect current results in these areas.
[Read more ...]

Computing With Words

By Sergio Guadarrama and Dongrui Wu
The term Computing with words (CW or CWW or CWP) was introduced by Lotfi Zadeh in 1996, then expanded to the Computational Theory of Perceptions (CTP) in 2000, to Precisiated Natural Language (PNL) in 2004, and more recently to Computation with Information Described in Natural Language (NL-Computation) in 2007.
The aims of this special session are to highlight recent advances on the theory and applications of CWW, to identify future research directions, and to publicize CWW to a wider audience. The special session will be a forum to exchange ideas, approaches, problems and solutions, and to share, discuss and present the latest research results.
[Read more ...]

Fuzzy Applications to Text Analysis for Awareness Promotion

By Kiyota Hashimoto
There has been a growing interest in various applications of fuzzy logic-based techniques to knowledge discovery and management to achieve the promotion of better awareness on the part of both machines and people. Awareness promotion is to help and support human and machine awareness of critical information of the self and the situation, and thus to help them to be more keen on critical information. For that purpose, each technical application is to be reconsidered from the viewpoint of usefulness and efficacy, with a special focus on innovative discoveries of hidden knowledge and wisdom. Following the success of the special session on applications of fuzzy logic to awareness promotion in FUZZ-IEEE 2011, this special session will focus on text analysis, from foundational natural language processing to web analyses to text mining, since text analysis, particularly analyses of unstructured text, is increasingly becoming the key for better knowledge discovery and management. We will then cover various related issues of text analysis in advanced applications of fuzzy logic and other computationally intelligent techniques to practical systems for knowledge discovery and management including, but not limited to, the following topics:
[Read more ...]

Fuzzy systems and control: Stability analysis and controller design

By Hiroshi Ohtake and Jun Yoneyama
Intelligent control systems, which include fuzzy systems, neural networks, piecewise systems and so on, are an active area of research in recent years. These systems can represent a wide class of nonlinear control systems, and have been started applying to not only electrical and mechanical systems including power plant, automobile, flying vehicle and robot, but also biological and biomedical systems. Especially, fuzzy model-based control approach can systematically achieve stability analysis and controller design, and a large number of studies on fuzzy model-based control have been reported. It is expected that the intelligent control approach leads many successful applications hereafter.
This special session provides recent results on stability analysis and controller design of intelligent control systems.
Topics of interest include, but are not limited to:
[Read more ...]

Human Symbiotic Systems

By Yoichiro Maeda and Daisuke Katagami
This special session aims at discussing the basic principles and methods of designing intelligent interaction  with the bidirectional communication based on the effective collaboration and symbiosis between the human and the artifact, i.e. robots, agents, computer and so on. We aims at encouraging the academic and industrial discussion about the research on Human-Agent Interaction (HAI), Human-Robot Interaction (HRI), and Human-Computer Interaction (HCI) concerning Symbiotic Systems. Reflecting the fact that this society covers a wide range of topics, in this session we invite the related researchers from a variety of fields including intelligent robotics, human-machine interface, Kansei engineering and so on.
[Read more ...]

Fuzzy Regression Analysis and Its Applications

By Mashaallah Mashinchi, Mehmet Orgun, Witold Pedrycz, and Hadi Mashinchi
Fuzzy regression is a powerful tool to estimate the relationship among variables in environments where uncertainty exists. In real-world applications this uncertainty may derive from the granularity of information for generalization purposes, the influence of human subjective judgement and partially available information, due to miss-recording or inaccurate measurements. One of the effective ways of capturing the useful information in such environments is with the application of fuzzy regression models. This special session aims at discussing fuzzy regression analysis either with probabilistic or least squared approaches with their applications to engineering problems. As for probabilistic and least squared approaches, introducing new approaches based on linear programming and designing new similarity measures are of interest. Due to the existence of outliers and noise in data in many real-world applications, fuzzy regression models which are capable of detecting outliers and not being effected by noise are highly in demand. Since fuzzy regression is widely applicable in operations research and complex systems analysis, we invite all the related researchers from the fields of computer science and engineering, economy, finance, marketing, social sciences, and healthcare.
[Read more ...]

Fuzzy Systems in Social Network Analysis and Applications

By Di Wang and Xiao-Jun Zeng
Social networks have created a new communication culture and behavior for 21st century. With the highly developed electronic facilities (computer, iPod, smart phone etc) and mature virtual communication environment (facebook, twitter, forum, video conference, etc) in the recent decade, social networking has shown more and more significant impact to almost every aspect of human life, from the most common online shopping, social relations to the extreme terrorism and riots. The great importance of the social networks provides a great and can-not-miss opportunity to the Fuzzy System community.
Social networking is complicated and full of uncertainties. The traditional social network analysis based on static graph theory is far from enough to handle these challenges whereas fuzzy logic and fuzzy systems show great promising to solve these uncertainties. The existing research of in social network analysis and mining includes analyzing commercial and e-commercial activities, social learning, financial exchange and stock forecasting, diffusion of novelty, belief networks, happiness and friendship evolving analysis etc. To promote the further research and applications of fuzzy system in social network analysis, this special section will provide the a forum to bring together cutting edge research in applying the fuzzy system to social network analysis and mining as well as related real applications. It will help develop novel approaches, discover new problems, share application experiences, and enhance the research efforts and awareness in this important area.
[Read more ...]

Emerging trends in Fuzzy Cognitive Maps

By Jose L. Salmeron, Elpiniki I. Papageorgiou, and Roberto Furfaro
Fuzzy Cognitive Map is an efficient soft computing technique for modeling complex causal relationships easily, both qualitatively and quantitatively. During the past decade, FCMs played a vital role in the applications of diverse scientific areas, such as social and political sciences, engineering, information technology, robotics, expert systems, medicine, education, prediction, environment etc. FCMs combine fuzzy logic and neural networks inheriting their main advantages. From an Arti?cial Intelligence perspective, FCMs are dynamic networks with learning capabilities, whereas more and more data is available to model the problem, the system becomes better at adapting itself and reaching a solution. They gained momentum due to their dynamic characteristics and learning capabilities. These capabilities make them essential for modeling and decision making tasks as they improve the performance of these tasks.
The proposed special session aims to present highly technical papers describing emerging FCM models and methodologies addressing any of the following specific topics: theoretical aspects, innovative applications and FCMs extensions.
[Read more ...]

Fuzzy Systems for Renewable Energy

Renewable power generation systems in general include wind, photovoltaic (PV), fuel cell and biomass power generation systems. They have been getting more attention recently due to cost competitiveness and environment friendly, as compared to fossil fuel and nuclear power generations. Owing to the relatively higher investment cost of renewable power generation systems, it is important to operate the systems near their maximum power output point, especially for the wind and solar PV generation systems. Thus, maximum power point tracking (MPPT) techniques are often required. Moreover, since the wind and solar PV power resources are intermittent, accurate predictions and modeling of wind speed and solar insolation are necessary, though difficult. Plus, to have a more reliable power supply, renewable power generation systems are usually interconnected with the electrical network. As a result, modeling and controlling the electrical network using smart-grid techniques, such as smart meter, micro-grid, and distribution automations become very important issues. On the other hand, due to the highly nonlinear and time-varying nature with unmodeling dynamics, effective uses of computational intelligence techniques such as fuzzy systems for the controlling and modeling of renewable power generation in a smart-grid system turn out to be very crucial for successful operations of the systems. Hence, topics of interest of the special session on Fuzzy Systems of Renewable Energy would cover the whole range of researches and applications of fuzzy systems in renewable power generations and smart grid systems.

[Read more ...]

IEEE IJCNN 20102 Special Sessions:

Hybrid Neural Intelligent Systems

By Patricia Melin and Oscar Castillo
This Special Session is being organized as one of the main activities of the Task Force on Hybrid Intelligent Systems of the Neural Networks Technical Committee (NNTC) and will consist of papers that integrate different Soft Computing (SC) methodologies for the development of hybrid neural intelligent systems for modeling, simulation and control of non-linear dynamical systems. The goal of the special session is to promote research on hybrid neural systems all over the world, and researchers working on this area are welcome to submit their papers. The Special Session will consider applications on the following areas: Pattern Recognition, Control of Non-linear Plants, Manufacturing Systems, and Time Series Prediction.
[Read more ...]

Meta-learning and hybrid systems for computational intelligence algorithms

By Norbert Jankowski and W?odzis?aw Duch
This session will be devoted to approaches that integrate in an intelligent way various learning algorithms used in computational intelligence, especially in meta-learning and hybrid systems.
Integration of machine learning algorithms becomes increasingly more important, especially in applications to hard problems which still wait to be solved, where application of specialized methods that do not use additional knowledge has led to limited success. Data mining packages contain hundreds of algorithms that may be composed in millions of ways, and are able to beat the "no-free lunch" theorem, but automatization of this process requires analysis of learning algorithms at the meta-level. Methods that extract various forms of useful knowledge, share and integrate it for intelligent information processing, are necessary to solve hard problems. Such methods may be inspired by the organization of the brain, or may be based on formal algorithms. One promissing direction is to use methods that construct new features, learning from successes of divers algorithms, extracting knowledge from indirect, partial learning and using it to build final potential solutions. Another interesting aspect in construction of complex computational intelligence methods is dealing with different levels of abstraction; useful meta-knowledge may come in the form of highly abstract heuristic knowledge directing search process for optimal model, or may be hidden in details of algorithm implementation.
[Read more ...]

Active, Incremental and Autonomous Learning: Algorithms and Applications (AIAL)

By José García-Rodríguez, Alexandra Psarrou, Andrew Lewis, Natasha Angelopoulou, and Vincent Lemaire
Much of machine learning and data mining has been so far concentrating on analyzing data already collected, rather than collecting data. While experimental design is a well-developed discipline of statistics, data collection practitioners often neglect to apply its principled methods. As a result, data collected and made available to data analysts, in charge of explaining them and building predictive models, are not always of good quality and are plagued by experimental artifacts. Solving the problems involved in data collection and classification will lead to the development of new machine learning algorithms able to address more realistic problems in autonomous and incremental learning.
This special session aims to offer a meeting opportunity for academics and industry-related researchers, belonging to the various communities of *Computational Intelligence*, *Machine Learning*, *Vision systems*, *Experimental Design*, *Data Visualization* and *Data Mining* to discuss new areas of active, incremental and autonomous learning, and to bridge the gap between data acquisition or experimentation and model building. Research papers about algorithms acceleration with hardware are also welcome.
[Read more ...]

Concept Drift, Domain Adaptation and Learning in Dynamic Environments

By Robi Polikar
One of the fundamental goals in computational intelligence is to achieve brain like intelligence, a remarkable property of which is the ability to incrementally learn from noisy and incomplete data, and ability to adapt to changing environments. The ability of a computational model to learn under various environments have been well-researched with promising progress, but a vast majority of these efforts make two fundamental assumptions: i) there is sufficient and representative training data; and ii) such data are drawn from a fixed – albeit unknown – distribution. Alas, these assumptions often do not hold in many applications of practical importance. Recent efforts towards  incremental and online learning may allow us to relax the “sufficiency” requirement by continuously updating a model to learn from small batches of data. Yet,  in many incremental learning algorithms the second assumption  still remains: the data that may incrementally become available are still drawn from a fixed – but yet unknown – distribution. More recently, other incremental approaches – such as concept drift and domain adaptation algorithms - have attempted to remove   this   assumption,   by   allowing   a   stream   or   batches   of   data   whose   underlying   distribution   change   over   time. These early approaches, however, make other assumptions such as restricting the type of change in the distribution, are primarily of heuristic in nature with many free parameters requiring fine-tuning, and have not been evaluated on large scale real-world applications.

Considering that our ultimate goal in computational intelligence is to attain brain-like intelligence, and that the plasticity of brain-like intelligence can, and routinely does, learn incrementally and in nonstationary dynamic environments, the need for a framework for learning from – and adapting to – a nonstationary environment is very real. Combined with a growing number of real-world applications that can immediately benefit from such algorithms, such as learning from financial data, climate data, etc., it is clear that there is much work to be done for solving the nonstationary learning problems.
[Read more ...]

Complex-Valued Neural Networks

By Igor Aizenberg, Akira Hirose, Danilo Mandic, and Jacek M. Zurada
Papers that are, or might be, related to all aspects of the CVNNs are invited. We welcome contributions on theoretical advances as well as contributions of applied nature. We also welcome interdisciplinary contributions from other areas that are on the borders of the proposed scope. Topics include, but are not limited to:
•    Theoretical Aspects of CVNNs and Complex-Valued Activation Functions
•    Learning Algorithms for CVNNs
•    Complex-Valued Associative Memories
•    Pattern Recognition, Classification and Time Series Prediction using CVCNNs
•    CVNNs in Nonlinear Filtering
•    Dynamics of Complex-Valued Neurons
•    Learning Algorithms for CVCNNs
•    Chaos in Complex Domain
•    Feedforward CVCNNs
•    Spatiotemporal CVNNs Processing
•    Frequency Domain CVNNs Processing
•    Phase-Sensitive Signal Processing
•    Applications of CVNNs in Image Processing, Speech Processing and Bioinformatics
•    Quantum Computation and Quantum Neural Networks
•    CVNNs in Robotics
•    Quaternion and Clifford Networks

[Read more ...]

Time Series Prediction

By Teresa Ludermir and Marley Vellasco
Time series modeling and forecasting is an old discipline that comes from the classic statistical field. The past decade has witnessed a vast growth of the amount of computational intelligence methods in time series forecasting. However hybrid intelligent systems are becoming popular due to their capabilities in handling many real world complex problems, involving imprecision, uncertainty, vagueness and high-dimensionality. Hybrid intelligent techniques facilitate the use of fuzzy logic, neuro-computing, evolutionary computing and probabilistic computing in combination, leading to the concept and application of hybrid intelligent systems.
This special session of IJCNN 2011 will cover all aspects of hybrid intelligent systems for time series data, particularly forecasting, classification and clustering of time series. Topics for submission include, but are not limited to:
[Read more ...]

Computational Intelligence for Image, Multimedia, Signal and Vision Processing

By Khan M. Iftekharuddin
Constructive understanding of computational principles of image, multimedia, signal and visual information processing, perception and cognition is one of the most fundamental challenges of contemporary science. Deeper insight into such computational intelligence helps to advance intelligent systems research to achieve robust performance. Implementing integrated principles in artificial systems may help us achieve better, faster and more efficient intelligent systems.
The Symposium will address theory and applications of non-traditional computational intelligence approaches in image, multimedia, signal and vision processing.
[Read more ...]

Machine Learning for Computer Vision

By Siddhivinayak Kulkarni
There is a great interest of machine learning algorithms among the computer vision researchers. Many machine learning algorithms have successfully demonstrated the capability of solving real world problems in computer vision field. The purpose of the special session on Machine Learning for Computer Vision is to address the latest developments of machine learning algorithms for numerous applications in the computer vision.
This session aims to bring together machine learning and computer vision researchers to demonstrate latest progress, emphasize new research questions and collaborate for promising future research direction.
[Read more...]

Brain inspired models of cognitive memory

By Kiruthika Ramanathan, Tang Huajin, and Ning Ning
Current memory technologies have experienced significant progress in terms of storage capacity, operation speed, integration capability, etc. However, their functions are highly constrained in storing and transferring data in space and time, prompting the need for improvement. Is there any available memory system that has multiple functions besides only data storage? Nature gives the firm answer: yes, it is human memory.
In contrast to physical memories, the biological counterpart has versatile functions. For instance, it stores data associatively such that different modalities of data could be retrieved simultaneously; it can learn different concepts, categorize and store them in an organized manner; it can process and store data concurrently and in a distributed fashion; it can restore content even if some part is damaged; it can perceive the stimulus and predict the next event; it can adapt to the environment and perform selective storage. Functions such as adaptation, learning, perception, self-organization and prediction make human memory have distinct cognitive features. Can we change the way data is currently being stored in computational systems by building a physical memory device that has cognitive functions like human memory?
The scope of the question transcends several interdisciplinary boundaries and combines efforts in both hardware and software engineering. It has prompted us to organize the special session on brain inspired memory models, and aims to offer a meeting opportunity for researchers belonging to the various communities of computational intelligence, machine learning, cognitive modelling, as well as researchers in hardware (circuit level) implementation of cognitive systems and those working at materials level research, such as memristors and phase change materials. Research papers that focus on how these technologies can be used to develop a memory based intelligent system will contribute to this special session
[Read more ...]

Unsupervised model-based learning from high dimensional and functional data

By Faicel Chamroukhi
Autonomous learning approaches aim at the acquisition of knowledge from raw data for analysis, interpretation and to develop reliable autonomous systems that make accurate decisions and predictions for future data. To ensure such reliability of decision based only on the raw data, there is therefore an important need to understand the processes generating the data. This in general leads us to generative learning approaches which will be in the core of this session. Generative model-based approaches are very useful well-established statistical models that explicit the processes generating the data. Such approaches are naturally tailored for an exploratory data analysis through unsupervised learning as they learn the conditional jointly with the prior, the posterior being taken with the Bayes rule. In particular, latent data models, including mixtures and hidden Markov models with the EM algorithms are at the basis of the majority of developed model-based approaches for unsupervised learning. As these well-established models are likely to be very beneficial in many domains, there is namely a growing investigation of adapting them to the context of functional data and in high dimensionality problems, as well as for large-scale data sets through online implementations. Such models have proved their efficiency in many applications domains including signals, text, speech, image, etc.
This session will therefore be dedicated to new theoretical propositions concerning unsupervised generative learning approaches that investigate vectorial high dimensional data, as well as for functional data when the inputs are functions rather than finite size vectors.  The frameworks will in particular concern data representation, classification/clustering and dimensionality reduction. Articles will cover these approaches when the data are taken under an independence assumption, as well as in a sequential analysis context.
[Read more ...]

Neural Computing for Human Friendly Robot Applications

By ChuKiong Loo, Masuta Hiroyuki
Recently, various types of intelligent robots have been developed for the society of the next generation. In particular, intelligent robots should continue to perform tasks in real environments such as houses, commercial facilities and public facilities. The growing need to automate daily tasks combined with new robot technologies are driving the development of human-friendly robots, i.e., safe and dependable machines, operating in the close vicinity to humans or directly interacting with persons in a wide range of domains. The technology shift from classical industrial robots, which are safely kept away from humans in cages, to robots, which will be used in close collaboration with humans, requires major technological challenges that need to be overcome. Neural computing is very important to provide human-friendly services by robots. The session will provide a robot for human-friendly services based on innovation in neural computing.
[Read more ...]

Nonnegative Matrix factorization paradigm for unsupervised learning

By Younès BENNANI, Nistor GROZAVU, Nicoleta ROGOVSCHI, and Mohamed NADIF
This special session will cover original and pioneering contributions, theory as well as applications on nonnegative matrix factorization (NMF) paradigm for unsupervised learning, and aim at an inspiring discussion on the recent progress and the future development.
A fundamental problem in many machine learning tasks is to find a suitable representation of the data. A useful representation typically makes latent structure in the data explicit, and often reduces the dimensionality of the data so that further computational methods can be applied.
NMF is a commonly used approach to understanding the latent structure of the observed matrix for various applications. NMF methods have attracted increasing attention in recent years because of their mathematical elegance and encouraging empirical results.
There are many forms of NMF. Previous work has shown that by respecting the nonnegativity, the factorization results will be easier to interpret while being comparable to, or better than, other techniques like SVD on effectiveness NMF has been successfully applied to a variety of applications, including face detection and recognition, audio and speech processing, text mining, biomedical image analysis, bioinformatics, and so on.
[Read more ...]

Machine Learning for Business

By André C. P. L. F. de Carvalho, Carlos Soares, Ricardo B. C. Prudêncio, and Teresa B. Ludermir
Business, government and science organizations are increasingly moving towards decision-making processes that are based on information. In parallel, the amount of data representing the activities of organizations that is stored in databases is also growing. Therefore, the pressure to extract as much useful information as possible from this data is very strong. Many tools for Data Mining (DM) and Business Intelligence have been developed for that purpose. Neural Networks and other Machine Learning (ML)  methods are increasingly being integrated into other information systems and tools (e.g., customer relationship management, database management systems, network security tools). Despite the maturity of the field, new problems and applications are continuously challenging both researchers and practitioners. The successful development of solutions for those problems requires that companies and universities work in close contact. Feedback from people with a business-oriented perspective is useful to assess current research results and to provide researchers with new challenges to work on. On the other hand, practitioners as well as decision makers in general need to be in touch with state-of-the-art research. Otherwise, they will not be able to provide the best solutions to their problems or to the problems of their clients. However, contact between these two communities is not as frequent as would be desirable. Although data mining, knowledge discovery and machine learning conferences provide an important contribution, they mostly attract an audience with a more technical and research background. The goal of this workshop is to bring together practitioners and researchers both from companies, government and academia, therefore promoting the exchange of experiences, ideas and challenges.
This special session will serve to share the recent developments and experiences in the field as well as to identify new challenges and directions for research. Topics for submission include, but are not limited to the application of Neural Networks and other Machine Learning techniques to:
[Read more ...]

Spiking Neural Networks for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition: Methods, Systems, Applications

By Nikola K. Kasabov
Spatio- and spectro-temporal data (SSTD) are the most common type of data collected in many domain areas, including engineering, bioinformatics, neuroinformatics, ecology, environment, medicine, economics, etc. However, there is lack of efficient methods for the analysis of such data, for the discovery of complex spatio-temporal patterns in it and for spatio-temporal pattern recognition (STPR), especially for on-line and real time applications. The brain functions as a spatio-temporal information processing machine and deals extremely well with spatio-temporal data. Its organisation and functions have been the inspiration for the development of new methods for SSTD analysis and STPR called spiking neural networks (SNN). They are considered the third generation of neural networks and a promising paradigm for the creation of new intelligent ICT for SSTD. This new generation of computational models and systems are potentially capable of modelling complex information processes due to their ability to represent and integrate different information dimensions, such as time, space, frequency, phase, and to deal with large volumes of data in an adaptive and self-organising manner. The proposed special session is aiming at presenting the state-of-the art in this new area of science and technology, including methods, software and hardware realisations and applications across domain areas.
[Read more ...]

Interactive Data Analysis and Visualization

By Barbara Hammer, Oliver Obst, and Yasufumi Takama
By offering automated information extraction tools from data, machine learning has revolutionized the way in which humans can cope with electronic data volumes. The ever increasing complexity of the settings continues to pose challenges to the field: often, it is no longer possible to specify a priori a formal learning task; complex parameter choices can severely influence the outcome; and an appropriate encoding of data is not clear at all. More and more often, the human constitutes an important step in the loop to interactively decide about an appropriate learning model, model parameters, and data representation. Because of this fact, intuitive models and model parameters, and human understandable interfaces to the model and data are needed. In this frame, interesting new technologies have been developed such as high quality data visualization tools, sparse interpretable data representation and models, informed priors, active learning, and similar.
[Read more ...]

Awareness Computing Theory and Applications

By Robert Kozma, Qiangfu Zhao, Goutam Chakraborty, and Tadahiko Murata
Prospective authors are invited to submit original papers to the Special Session. Awareness is the ability to be conscious of, feel or perceive, according to Wikipedia. It implies vigilance in observing or alertness in drawing inferences from what one experiences. The ultimate goal of aware computing is to create computing systems that are able to be aware. Application examples include safety/security awareness, context awareness, situation/background awareness, power awareness, location/position awareness, weakness/risk/danger awareness, chance/opportunity awareness, etc. An aware system may not be as intelligent as a human, but it will certainly be more autonomous and more human-like than conventional systems.
This special session provides a forum for researchers, engineers, and scientists to discuss on awareness science and engineering and to exchange ideas, opinions, and the latest results in this emerging field. The Special Session is organized by the Awareness Task Force of the IEEE CIS Neural Network Technical Committee, and it relies on the close interaction with the research community in this field, including the conference series ICAST: International Conference on Awareness Science And Technology, recently held in Dalian, China.
[Read more ...]

Neuromorphic Science Technology and Implementations

By Robinson E. Pino and Robert Kozma
The main objective of this special session is to provide forum for the discussion on the state of the art in neuromorphic computing systems, applications, computing architectures and novel hardware research. At this special session, various technological aspects of neuromorphic computing will be covered. Examples include, but not limited to:
[Read more ...]

Learning in Spiking Neural Networks: Beyond Hebbian Learning

By Andre Gruning, Scott Notley and Yaochu Jin
Today much evidence has been revealed in neuroscience that learning in biological neural networks is correlation-based (Hebbian-style, e.g. spike time dependent plasticity (STDP)). However cognitive behaviour is often considered to be target-driven, which indicates a supervised approach to learning rather than pure correlation-based learning.
Whereas a large number of both supervised and unsupervised efficient learning algorithms have been developed and a wide range of applications have been found for artificial neural networks, most learning algorithms for spiking neural networks are still correlation-based with few exceptions and limited success has been reported on applying spiking neural networks to solving real-world problems.
This special session aims at bringing together researchers from computational neuroscience, computational intelligence, machine learning and cognitive science to discuss new ideas and present efficient learning algorithms that go beyond Hebbian learning for feed-forward, recurrent and reservoir based spiking neural networks. Topics of interest include but are not limited to:
[Read more ...]

Neural networks and Intelligent Techniques for Difficult Document Computing

By Tom Gedeon and Dingyun Zhu
Document computing including document processing, management, information retrieval and knowledge extraction is an increasingly significant area of research as the tidal wave of digital information is growing exponentially and threatens to overwhelm us. In addition, the situation complexity increases when pre-digital and non-standard documents are taken into account. The issues are due to unstructured formats, obsolete or eclectic characters, hand written text and disintegrated media due to age and wear. This session is focussed on difficult problems in this area which can be solved or start to be addressed by neural and intelligent techniques. Difficult document computing can range from the structure of documents, to the nature of the documents, and the complexity of the document computing task.
This special session aims to foster research in neural networks and related paradigms with potential for application to difficult documents.
Topics of interest include, but are not limited to:
[Read more ...]

Neural networks for Human Centred Computing

By Lance C.C Fung and Thitipong Nandhabiwat
Computerised understanding of normal human interaction behaviour is the last major frontier of human computer interaction. In this session we are interested in neural and related approaches used for human centred computing, including but not limited to the use of eye gaze, facial expression, gestures and EEG and other sensors which are used to predict a human's internal state analogous to the way we understand each other. So, for example, my unconscious smile or frown for search engine results could be used as labels for a supervised neural network to learn to improve search results.
This special session aims to foster research in neural networks applied to human interaction with computers.
Topics of interest include, but are not limited to the use of neural networks for/with:
[Read more ...]

Computational Intelligence in Healthcare and Sports Engineering

By Daniel T. H. Lai, Alistair Shilton, and M. Planiswami
The healthcare industry is a growing industry estimated to consume 9% of the GDP for most countries in the world. Healthcare encompasses the diagnosis, treatment and prevention of disorders through the innovation of new medical practices and medical technology. Preventive medical practices could include nutrition, sports, exercise and active living programs. New preventive technologies in the area of health and sports are consistently being researched on. For example, the convergence of sensors and microelectronics has led to new portable medical devices which monitor physiological and movement parameters. The data obtained from these devices requires further postprocessing and modelling which is challenging to accomplish with explicit mathematical modelling.
This session looks at the application of novel computational intelligence techniques to the healthcare and sport industry in a variety of areas ranging from intelligent medical diagnosis, clinical data analysis, intelligent data management, patient management and smart medical devices. In the sports field, this includes intelligent human performance analysis, optimization of skill acquisition and rehabitilation assessment. This special session will encompass the application of computational intelligence techniques including (but not limited to):
[Read more ...]

Cell Representations in the Brain

By Asim Roy and Juyang Weng
There have been an increasing number of brain-recording experiments that report that single cells in some brain areas are highly selective, seemingly abstract, and invariant to some factors in their responses to natural stimuli.  The authors call these cells “concept cells.” All such studies were based on recordings of the brains of epilepsy patients at University of California at Los Angeles.  The authors reported finding a hippocampal cell that responded only to photos of actress Jennifer Aniston, but not to pictures of other blonde women or actresses.  And a cell can be triple invariant, responding not only to the image of a person or object, but also to the person’s spoken and written names. Their study also reported that the firing of a cell can be changed by the conscious mental activities of the human subject.
These studies raise many questions.   How locally can a miroelectrode pick signals in the vicinity of many cells?  What role does a single cell play in representation of information?  And what kind of information does a cell represent?  How does such a role change?  How do individual cells give rise to the global brain representation?  How does the brain generate behavior from its overall internal representations?
This special session opens up the discussion and debate about recent experimental and theoretical work on the issues of emergence, representation, learning, behavior, abstraction, and other processes in the brain. We invite papers on the following topics:
[Read more ...]

Data Regularisation, Fault and Anomaly Detection, Isolation and Mitigation

By Peter Tino, Huanhuan Chen and Xin Yao
Modern societies rely on smooth operation of complex systems often operating in uncertain challenging environments producing data of diverse character - e.g. multidimensional, multi-scale and spatially distributed - often corrupted with significant noise or with observational gaps. In addition, the environment may be subject to non-stationary phenomena and the measurement devices prone to permanent or transient faults, ageing effects or thermal drifts. This poses significant challenges to intelligent systems operating on such data where it is no longer possible to rely on stable re-emerging patterns to take advantage of. Examples include data coming from distributed monitoring and actuating systems such as water distribution networks, manufacturing processes, transportation systems, robotic systems, intelligent buildings, etc.
The aim of this special session is to foster research on robust learning/control/monitoring in such challenging scenarios. It will be a platform to exchange ideas on novel approaches to fault tolerant modeling, monitoring and/or control that can learn characteristics of the monitored environment and adapt their behaviour as well as successfully deal with missing or perturbed data.
[Read more ...]

Neural Systems and Algorithms for Very Large Data

By Marimuthu Palaniswami and Timothy Havens
Since the early 1990's, the ubiquity of personal computing technology has produced an abundance of staggeringly large data sets—the Library of Congress has stored over 160 terabytes of web data and it is estimated that Facebook alone logs over 25 terabytes of data per day.  To compound this fact, these data sets are populated from disparate, often unknown, sources and are in a wide-range of formats.  There is a great need for systems and algorithms by which one can elucidate meaning from these data sets.
Are computational complexity, storage, or memory requirements concerns in your work?  Then your paper belongs in our session!
We invite papers on the following topics:
[Read more ...]

Neuro fuzzy systems for pattern recognition

By Adel M. Alimi and Tarek M. Hamdani
Learning neuro fuzzy systems is now using sophisticated methods with online and offline techniques. Such developed methods are applied successfully to the pattern recognition contexts. Moreover, using neuro fuzzy systems stills promoting high performance systems in different steps of the pattern recognition process. Finding high quality supervised and unsupervised learning models for online and offline neuro fuzzy systems is a very actual challenge which is much related to modern problems.
Due to the multiplicity of researches for neural learning and for the specific field of neuro fuzzy systems, we were motivated to propose such session. We aim to collect recent works in online and offline learning methods for pattern recognition to identify and define new application ways and future involvement of the addressed filed.
Several applications in our modern life need online and offline adaptive neuro fuzzy systems and researchers are proposing new ways of thinking. The proposed special session can be an occasion to promote these advances and encourage researchers to go further in applying online and offline learning neuro fuzzy system for pattern recognition.
The principal aim of this special session is to collect the most recent advances addressing all aspects related to the theoretical and applications using neuro fuzzy online and offline learning systems for pattern recognition. This will be an occasion to host multiple frameworks and researchers on this working area and will allow them to share and discuss their present advancement and possible subsequent issues.
[Read more ...]

Soft Computing and Pattern Recognition Algorithms for Structured Patterns: Towards Parallel Computing Approaches

By Antonello Rizzi and Alireza Sadeghian
Structured patterns, such as graphs and sequences, are widely adopted to represent complex objects and are usually semantically more related to the physical modeled pattern than a classical real valued feature vector representation. For instance, a chemical compound, being basically composed of atoms organized in a 3D structure, finds an intuitive representation through a labeled graph, where the vertices represent the atoms and the edges retain their mutual spatial relations and chemical bond type. Indeed, a labeled graph is able to encode also semantic information of the pattern, through the related characteristic labels of both vertices and edges. For this purpose, more intuitive and well studied examples could be made, such as segmented images, social networks, computing networks, biological metabolic pathways, circuits, and so on. For what concerns graphs, the first key problem to deal with is the well known Inexact Graph Matching problem. It basically consists in the definition of a suitable (dis)similarity measure between arbitrarily-labeled graphs. Any data driven modeling system that have to deal with graphs as input patterns must deal with this issue in order to define a proper inductive logic inference. The same type of issues arise when dealing with sequences as input patterns of the system. Due to the general high computational demand of these techniques and the increasing interest for large patterns/datasets analysis, different Parallel Computing systems are employed and specialized for this purpose.
This special session invites researchers interested in Computational Intelligence techniques for graph-based and sequence-based Pattern Recognition and Soft Computing problems, seen also from the Parallel Computing point of view, to propose interesting and cutting edge articles related to any aspect, theoretical, experimental or applicative, concerning this scientific context.
[Read more ...]

Real World Applications of Reinforcement Learning

By Matteo Gagliolo, Peter Vrancx, and Ann Nowé
Reinforcement Learning (RL) algorithms have long left the tiny grid worlds of the early years. From robot control to autonomous navigation, research labs have been applying RL to address increasingly difficult problems, showing that this paradigm is ready for the real world. In recent years, a number of papers have shown successful practical applications, in fields as diverse as roduction control, finance, scheduling, communications, autonomous vehicle control. While such examples are relevant, they do not abound, and RL is still far from being routinely applied as more mature supervised machine learning techniques are. Moreover, conferences and journals tend to dismiss “mere application” papers which do not carry relevant contributions at the theoretical level. 
With this special session, we intend to gather recent examples of the application of RL to real-world problems, focusing in particular on the practical difficulties of applying existing RL algorithms, rather than on theoretical innovations. The aim is to give an updated picture of the state of the art of real world applications of RL..
[Read more ...]

Robust Learning with Kernel Methods

By Franck Dufrenois and Carlos Alzate
The main objectives of robust techniques in the framework of machine learning are the characterization of the structure underlying the bulk of the data and the detection of outlying structures deviating greatly from the majority of the data.  These outlying patterns should have a reduced influence on the results of a robust model. Kernel-based learning methods have become a well-established foundation for machine learning and data mining problems. The main idea of kernel methods in machine learning is to perform linear estimation in a high dimensional (even infinite dimensional) feature space which is nonlinearly related to the original input space. The kernel function induces a high dimensional feature space, which is never computed explicitly via the application of Mercer’s theorem.
This special session focuses on original contributions of kernel-based approaches for robust learning.  The topics of interest include (but are not limited to):
[Read more ...]

Contents by Vinh Quang Bui, DSARC, UNSW@ADFA, Australia / Template by Next Level Design