The newly established concept of evolving intelligent systems (eIS) is a result of the synergy between conventional systems, neural networks and fuzzy systems as structures for information representation and real time methods for machine learning. This emerging area targets non-stationary processes by developing novel 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 intelligent systems with a higher level of flexibility and autonomy, so that the systems can evolve their structure and knowledge of the environment and ultimately – evolve their intelligence. To address the problems of modelling, control, prediction, classification and data processing in a dynamically changing and evolving environment, a system must be able to fully adapt its structure and adjust its parameters, rather than use a pre-trained and a fixed structure. That is, the system must be able to evolve, to self-develop, to self-organize, to self-evaluate and to self-improve. Wireless sensor networks, assisted ambient intelligence, embedded soft computing diagnostics and prognostics algorithms, intelligent agents, smart evolving sensors; autonomous robotic systems etc. are some of the natural implementation areas of eIS as a realistic and practical tool for design of real time intelligent systems.

EIS’10 continues the tradition set by the previous forums (EFS’06, GEFS’08, and ESDIS’09) dedicated to serving the needs of academics and practitioners in computational intelligence focusing on evolving and self-adaptive systems. It will also be supported and organised by the Adaptive Fuzzy Systems Task Force, FSTC, CIS, IEEE. The objective of the proposed Workshop is to facilitate the promotion of novel problems, research, results and future directions in the emerging area of eIS. the proposed Workshop will provide an opportunity to meet old friends, making new contacts and exchange ideas as well as to establish links with other related areas in the WCCI’10 grand event.

José de Jesus Rubio Ávila, Achmed Bouchachia, Fernando Gomide, Witold Pedrycz, Gancho Vachkov, Edwin Lughofer, Ronald R. Yager, Meng Jo Er, C. T. Lin, Trevor Martin

Computer Go has been developing for the past several years. In 1998, Martin Muller won despite 29 handicap stones against the computer Go "Many Faces of Go". In August 2008, the computer Go "MoGo" has won with an advantage of "only" 9 handicap stones against top-level human players in 19x19 Go—Myung-Wan Kim, who won the 2008 US Open with Korean 8th Dan Pro (8P). Additionally, another computer Go "CrazyStone" won with handicaps of 8 and 7 stones against Kaori Aoba, a Japanese 4th Dan Pro (4P) in December 2008. Due to the development of the Computational Intelligence, computer Go has made considerable progress for the past 10 years. Programs are currently competitive at the professional level in 9x9 Go. To strengthen computer Go programs and advocate research, development and application of computer games' related fields, Taiwan hosted the "2008 Computational Intelligence Forum and World 9x9 Computer Go Championship (http://go.nutn.edu.tw)" on September 25-27, 2008, "2009 Invited Games for MoGo vs. Taiwan Professional Go Players (Taiwan Open 2009, http://go.nutn.edu.tw/2009/)" on February 10-13, 2009, and "FUZZ-IEEE 2009: Panel, Invited Sessions, and Human vs. Computer Go Competition" (http://oase.nutn.edu.tw/FUZZ_IEEE_2009/index.htm) on August 20-23, 2009. The 2008 and 2009 events were widely reported by the several international mass media such as USA, Germany, France, and Japan (http://www.ireport.com/docs/DOC-214010 and http://web.nutn.edu.tw/gac600/2009go-report-english.htm and http://www.ireport.com/people/leecs ).

The game of Go is one of the last board game where the strongest humans are still able to easily win against Computer Go program. But researchers have discovered new performing algorithms and computers are catching up really fast. Taiwan Open 2009 has been ended with a success in making two world records. The Go program MoGo made two new world records by winning a 19 by 19 game with 7 handicap stones against the 9P professional Go player Jun-Xun Zhou and a 19 by 19 game with 6 handicap stones against the 1P professional Go player Li-Chen Chien. If computers continue to improve at this rate, one more human stronghold may fall in front of machines in less than 10 years. Afterwards, the development team of MoGo will definitely continue to enhance the strength and improve the weakness of MoGo by learning more knowledge and strategy from professional Go players in the future. In order to enhance the fun in Go playing by human interaction with computer programs and to stimulate the development and researches of computer Go programs. The objective of the proposed panel and invited session is to highlight an ongoing research on Computational Intelligence approaches as well as their applications on game domains. In addition, it is also hoped that the advances in computational intelligence will make more progress in the field of computer Go than before to achieve as much as computer chess or Chinese chess in the future.

Hani Hagras, Olivier Teytaud, Martin Muller, Vincenzo Loia

The objective 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. Topics of interest include but are not limited to:

• Intelligence Gathering and Exploitation
• Situation Assessment and Knowledge Discovery
• Multi-Sensor Exploration and Integration Mission Planning
• Execution and Resource Management
• Information Handling, Extraction and Fusion Classification
• Target Tracking and Localization
• Decision Support in Security and Defence
• Automated Unmanned Vehicle (AUV) Control
• Multiple AUV Coordination
• Control and Task Allocation Stationary or Mobile Object Detection
• Recognition and Classification

Emil Petriu, James Keller

The current state of the art in the development of search methodologies is focused around the human design of bespoke systems, which are specifically tailored to the problem solving environment in hand. A particularly challenging goal is to develop intelligent systems which are capable of automatically building (and/or selecting) new systems. A paradigm shift has emerged in search methodologies over the past few years. Instead of taking the short term approach of dealing with single problems, there is a growing body of work that aims to raise the level of generality by adopting the long term approach of providing a more broadly applicable solution. These types of “systems to build systems” have the potential to significantly reduce the resource cost that is often associated with developing bespoke systems, since the search process is automated through adaptation/learning.

The main purpose of the workshop is to bring researchers and practitioners together from the computer science, artificial intelligence and operational research fields, in order to discuss new ideas, recent advances, methodologies, frameworks, challenges and opportunities within the context of systems to build systems.

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

• Systems to build systems (e.g. hyper-heuristics)- automated (computer aided) design of heuristics (e.g., by genetic programming, grammatical evolution, etc.)
  • applications and new challenging domains
  • classifications or categorizations of approaches
  • use of machine learning techniques (e.g. data mining, reinforcement learning, classifier systems, neural networks, and others)
  • foundational studies towards the understanding of systems to build systems
  • fuzzy systems to build systems
  • scalability issues
  • issues in multi-objective, discrete and continuous optimization
  • parallel and distributed frameworks
• Related topics
  • adaptive and self-tuning methodologies
  • multi-meme algorithms
  • adaptive operator selection
  • algorithm portfolios
  • model-based search
  • reactive search

Prof Graham Kendall, University of Nottingham
"Hyper-heuristics: Past, Present and Future"

Prof Erwin Pesch, University of Siegen
"Metaheuristics: New Perspectives and Real Applications"

Nowadays there is a large and growing international community working on the application of Computational Intelligence techniques in Computer Vision. During the last years, many special sessions on this topic have been organized in the most important conferences related to Computational Intelligence. One of the main motivations for this growing interest is the fact, pointed out by many authors, that the techniques offered by Computational Intelligence are very well suited for addressing novel, hot and very interesting topics in the area of Computer Vision.

The Workshop "Computational Intelligence in Computer Vision", to be held as part of IEEE WCCI 2010, is the result of the joint effort of a group of researchers in this area, with the following objectives:

• To contribute to the integration of the growing community of researchers on Computational Intelligence for Computer Vision, in particular by encouraging participation in this Workshop.
• To discuss on the evolution of this area of research, the present state and future prospects.
• To talk about the possibilities of transfer of this kind of technology, and the possible contributions we may expect in the areas of business and the benefit of society.
• To facilitate contact between researchers wishing to collaborate, and between researchers and companies for technology transfer, encouraging the participation of both communities in the Workshop.
• To present some of the latest research findings in the area of Computer Vision based on Computational Intelligence, integrating and coordinating the initiatives of different researchers.

Jim Keller, University of Missouri-Columbia, USA.
"A Current View of Computer Vision Research and Challenges for the Fuzzy Set Community"

Ricardo Baeza-Yates, Yahoo! Research, Spain.
"Multimedia Retrieval at Yahoo!"

Nuria Oliver, Telefónica Research, Spain.
"Research Challenges and Opportunities in Multimedia: a Human Centric Perspective"

«Computational Intelligence in Computer Vision: Challenges, Opportunities, and Impact».
Speakers: Jim Keller, Eduard Montseny, Javier Montero, Humberto Bustince, Pedro Melo-Pinto, Mengjie Zhang, Jesús Chamorro-Martínez.

In addition, there are 9 Special Sessions of the Conference that have been organized associated to this Workshop, devoted to specific topics in the area of Computational Intelligence and Computer Vision. The Schedule of these sessions will be made public by the organization of IEEE WCCI as part of the final program of the Conference.

Session overview: This workshop will address two central topics related to research funding in data infrastructure and computational approaches for modeling. The first part will address research priorities and funding opportunities from the National Institutes of Health (NIH) and the National Science Foundation (NSF) for both U.S. and foreign institutions. The second part will focus on developing grant-writing skills, geared toward NIH and NSF proposals, and will include discussion of issues relevant to researchers from non-U.S. institutions.

Part One: Cyberinfrastructure, Modeling, and Analysis: Research Opportunities at NIH and NSF

Technological advances have led to striking changes in the nature and quantity of data available in many fields, including population health and the behavioral and social sciences. The international economic crisis and the burgeoning costs of healthcare, make data access and harmonization for scientific discovery a global priority. Improvements in the breadth, depth, and quality of both health-related and other types of data open new opportunities for research, but also bring new challenges. Specifically:

1. Data volume is increasing exponentially as electronic health records, health information exchanges, and ubiquitous digital devices become more widespread. When coupled with the growth of cyberinfrastructure, geographic information system (GIS) networks, and cloud computing, this situation has created a “needle in a haystack” problem: Where in the overwhelming sea of data do we look for answers?
2. Simultaneously, new and more complex forms of data are coming on the scene, presenting their own challenges for analysis. For example, images are becoming more commonplace (e.g., pictures of food eaten are supplementing food diaries); GIS data provides location-based information and can be used to link behaviors with the locations in which they occur, creating a “package” of data (place and behavior); social network data from sources as diverse as social media/web 2.0 and clinical health systems, provide further context for individual behavior (i.e., social data and the behavior of interest are not stand-alone concepts); and continuous data (e.g., streaming media) from real-time data capture technologies may display underlying patterns for analysis, further complicating traditional approaches for analysis. How do we create/apply appropriate analytic tools to these types of data?
3. What steps are required to harmonize health-related data and increase accessibility? Electronic data spanning all scientific disciplines (e.g., demographic, behavioral, social, genetic/proteomic, biological, clinical, economic, geographic, physical sciences) are at our fingertips. Digital devices are increasingly imbedded in everyday lives worldwide. This creates an opportunity for data mining and modeling in a research context. But such opportunities have their own issues for health-related problems, including accessibility and privacy/confidentiality. Furthermore, the data may not be ideally suited to the primary research objective. How do we maximize use of existing data effectively for health and non-health-related research and discovery?
4. How can we use the power of methods such as computational intelligence to make sense of diverse bodies of existing health-related knowledge? That is, how do we synthesize what we already know, from cells to society, so that we get a better understanding of the big picture, including exposing important knowledge gaps?
5. How can we harness the power of computational modeling and simulation to: identify research priorities and policy levers, devise better interventions, and provide accurate forecasts about the future?

Opportunities to address these significant challenges will be the subject of the workshop. Representatives from two federally-funded U.S. research institutions, the National Institutes of Health (NIH) and the National Science Foundation (NSF), will present on specific aspects of these challenges. They will also present a variety of research opportunities pertinent to these challenges. Special attention will be paid to funding opportunity announcements open to investigators at foreign institutions.

The format for the 90-minute session will be as follows: 10 minute overview and introduction by the Session Chair, Dr. Gary Fogel (Natural Selection, Inc.) followed by four 15 minute talks by NIH and NSF staff, and a 20 question/discussion period.

Specifically, following the Session Chair’s opening remarks, Dr. Fahmida Chowdhury (NSF) will present on a variety of cross-directorate and cross-disciplinary initiatives including computational modeling and cyberinfrastructure at NSF and available funding opportunities. Next, Dr. Abdul Shaikh (NIH) will present the PopSciGrid framework for conceptualizing grid-enabled data harmonization and advanced computation in population health. He will also describe current research priorities and funding opportunities in population health, cyberinfrastructure, and behavioral informatics available at the National Cancer Institute. He will describe a number of international initiatives funded by NCI including cancer modeling (CISNET), cancer prevention and control, and the Small Business Innovation Research (SBIR) mechanism. Dr. Stephane Philogene (NIH) will describe behavioral and social science data infrastructure needs of the NIH and local communities to facilitate and enhance population health research. Program initiatives and funding opportunity announcements underway in this area, including the BIGData collaboration, will also be discussed. Dr. Patricia Mabry (NIH) will describe program interests and funding opportunities in mathematical modeling and simulation available at NIH and will illustrate with work by NIH-funded investigators.

Part Two: Grant-writing Workshop: How U.S. and Foreign Institutions Can Compete for NIH and NSF Funding

In this second half of the session, audience members will learn how to compete for the funding opportunities they heard about in Part One. Considerations for investigators from non-U.S. institutions will be included. Part Two of the session will include a 40 minute presentation by an NIH program staff member and a 40 minute presentation by an NSF program staff member and 40 minutes for questions and discussion. This long Q&A period is by design, it is anticipated that many audience members will have questions about the grant application process. In Part Two, following an overview of each agency’s mission and organization, participants will learn about a wide variety of topics related to the grants process. Topics to be covered include: where to find out about funding announcements, what types of announcements exist and how they differ from one another, how to determine if foreign institutions are eligible for a particular announcement, how grant applications will be reviewed, who to contact prior to submitting a proposal, how to plan a grant submission timeline, how to develop collaborations, how to seek out a mentor for the grant writing process, how to register in the electronic application systems, the format of each agency’s grant application and what to include in each section, and what kinds of major funding mechanisms are used by each agency. Resources for further information on the topics presented will also be identified.

Dr. Gary Fogel, Fahmida Chowdhury

Additional Workshop Panelists (in order of presentation): Abdul Shaikh, Stephane Philogene, Patricia L. Mabry

1. to provide an opportunity for biomedical and computer scientists to present and discuss accomplishments, as well as speculative futuristic ideas, related to the computational intelligence foundation of the knowledge based medicine,
2. to organize an international community interested in on-going exploration of appropriate applications of computational intelligence in knowledge based medicine,
3. to develop an international community of practice dedicated to developing and sharing data, computer programs, knowledge and other resources related to computing in support of knowledge based medicine.

Topics:

• disease prevention, early detection, diagnoses and prognosis
• lifetime treatment planning and follow-up
• biomedical numeric, categorical, text, image & signal data mining
• knowledge extraction from electronic patient records
• low-cost screening devices
• cost reduction in any aspect of medicine
• continuous patient monitoring and alarm systems
• detecting untoward effects such as adverse drug reactions, drug-drug interactions, etc.
• patient-management workflow optimization
• disease modeling & treatment selection
• survival prediction & other time-to-event modeling
• medical biometric technology & personal multimedia data processing
• building and using biomedical ontologies
• designing clinical research trials
• drug dose targeting & drug evaluation
• medical devices, patient monitoring & preventive treatment strategies
• subject recruitment for clinical research protocols
• translational research & comparative effectiveness
• genomics, proteomics, transcriptomics, metabolomics in relation to clinical practice
• pharmacology, pharmacokinetics, pharmacodynamics & pharmacogenomics

The three organizers and leaders of the CI applications in medicine