Computational Modeling and Simulation of Intellect: Current State and Future Perspectives

Computational Modeling and Simulation of Intellect: Current State and Future Perspectives

Boris Igelnik (BMI Research Inc., USA)
Indexed In: SCOPUS
Release Date: May, 2011|Copyright: © 2011 |Pages: 686
ISBN13: 9781609605513|ISBN10: 1609605519|EISBN13: 9781609605520|DOI: 10.4018/978-1-60960-551-3

Description

With recent progress in information generation, users are experiencing increasing difficulties in processing the available amounts of high-dimensional data, extracting information from it, and eventually finding a meaning in the structured data.

Computational Modeling and Simulation of Intellect: Current State and Future Perspectives confronts the problem of meaning by fusing together methods specific to different fields and exploring the computational efficiency and scalability of these methods. Researchers, instructors, designers of information and management systems, users of these systems, and graduate students will acquire the fundamental knowledge needed to be at the forefront of the research and to use it in the applications. The topic is of great importance for information and management science and technology, both currently and in future.

Topics Covered

The many academic areas covered in this publication include, but are not limited to:

  • Adaptive dynamic programming
  • Biogeography-based optimization
  • Computational efficiency
  • Fusion of interdisciplinary methods
  • Image Analysis
  • Machine Learning Algorithms
  • Problem of meaning
  • Scalability of methods
  • Simulation of a transmission
  • Visual navigation

Reviews and Testimonials

This interesting and ambitious book will assist researchers, users, developers, and designers of the information and management systems. It will also offer a comprehensive overview of computational and artificial intelligence issues to graduate students and other learners, who want a gentle, but rigorous introduction to the computational modeling and simulation of intellect.

– Dr. Jacek M. Zurada, University of Louisville, USA

The current volume edited by Dr. Boris Igelnik provides a superb perspective on this vast new field. The papers collected deal with both fundamental, theoretical problems as well as with specific, practical problems including the vital areas of medicine and environmental protection. Some of them provide very valuable state-of-the-art surveys of important subfields. The reader can get a deeper understanding of some already traditional approaches and learn about new ones. Dr. Igelnik has been very active in the field for many years and has participated in its development with many important contributions. Thanks to his excellent work and vision the volume will be a valuable reference and source of information on the fields concerned for researchers, graduate and postgraduate students as well as practitioners.

– Slawomir Zadrozny, Warszawa, Poland

A number of diverse methods and approaches from different fields are juxtaposed in hopes of some fusion or cross-fertilization in the pursuit of the modeling and simulation of intellect. Among those fields are computer science and engineering, electrical engineering, business, telecommunication, physiology, and statistics. In addition to explaining concepts, the studies cover applying artificial and computational methods to image and signal processing, robotics, control, medicine and environmental monitoring and protection, and learning.

– Book News, Reference - Research Book News - August 2011

Table of Contents and List of Contributors

Search this Book:
Reset

Preface

The methods of computational modeling and simulation of intellect have been developing in various fields, such as digital signal processing (Haykin, 2002, 2007; Swanson, 2002; Richaczek & Hershkowitz, 200; Mars, Chen, Nambiar, 1996; Katz, 1996), image processing (Batchelor & Whelen, 1997; Pratt, 2007; Lillesand & Kiefer, 1999; Jain, 1989), robotics (Bekey, 2005; Bekey et al, 2008; Haykonen, 2003, 2007; Mataric, 2007), control (Hunt et al, 1995; Simon, 2008), systems biology (Alon, 2007; Boogerd, 2007; Priami, 2009; Wilkinson, 2009), molecular computing (Adamatzky, 2001, Sienco et al, 2003), cognitive neuroscience and cognitive modeling (Anderson, 2007; Feng, 2004; O’Reilly & Munakata, 2000; Davis, 2005; Polk & Seifert, 2002; Thelen & Smith, 1998; McLeod, Planket, Rolls, 1998; Perlovsky & Kozma, 2007), cognitive informatics (Wang, 2009), computational neuroscience (Trappenberg, 2002; Lutton, 2002), general artificial intelligence (Goertzel & Pannacin, 2007), knowledge engineering (Cloete & Zurada), knowledge based neurocomputing (Kolman & Margaliot, 2009), multi-agent systems (Gorodetsky et al, 2007; Khosla, Dillon, 1997), semiotics (Gudvin & Queros, 2007), neural-symbolic learning systems (Garses, Broada, Gabbay, 2002), social networks (Bruggerman, 2008), bioinformatics (Zhang, Rajapakse, 2009), data mining (Taniar, 2004), computational intelligence (Reisch, Timme, 2001; Schwefel, Wegener, Weinert, 2003, Zurada, Marks, Robinson, 1994), neural networks (Haykin, 1994; Kasabov, 1996; Perlovsky, 2001), et cetera. There were published several interesting books on what we call below “concepts,” for example, Freeman (2000), Kitamura (2001), Minsky (1986), and Gardenfors (2000). The topic is of great importance for information and management science and technology, both currently and in the future. This book presents a number of diverse methods and approaches to the problem of modeling and simulation of intellect, currently existing in the different areas and their perspectives, and targets a possible fusion of these and coming methods, as well as computational efficiency and scalability of these methods. 

The main themes of the publication are: the problem of meaning, fusion of methods specific to different fields, computational efficiency, and scalability of the methods. Researchers, instructors, designers of information and management systems, users of these systems, and graduate students will acquire the fundamental knowledge needed to be at the forefront of the research and to use it in the applications. 

With progress in science and technology, humans experience increasing difficulties in processing huge amounts of high-dimensional data, extracting information from it, and eventually finding a meaning in the structured data. While computers definitely play a positive role in obtaining large databases, their current ability to make sense of the data is at best questionable.  On the other hand, humans and their forerunners had millions years of experience (multiplied by billions of individuals) in information and technology exchange, and have developed an astonishingly efficient capability of extracting meaning from data. Facing tremendous difficulties in using computers for solving this task, the designers of information and management systems have started thinking: how do we do it? The complete answer to this question is still unknown, but attempts to make it using diverse computational methods and approaches have been emerging in many areas of science and technology. Therefore, it is useful to summarize this variety of methods and approaches in a discipline, which might be called “computational modeling and simulation of intellect.” It is equally important and useful to describe a future development of these and coming methods and to target their fusion, computational efficiency, and scalability. 

I came to the idea of this book while reviewing some of existing approaches to this discipline, which were actually based on a combination of the genetic, environmental, and social foundations in the different proportions. It is impossible to expect that there exists a unique approach best suited for the solution of the problem of modeling and simulation of intellect, just due to its giant complexity. Therefore, it is essential to fuse the knowledge contained in different approaches. The proportion of different foundations in an approach is also of great importance. I prefer to shift attention more to environmental and social foundations than to their genetic base, and I have the long-term goal to implement the learning of intellect by a dynamic combination of the exchange data and knowledge first among humans, next among humans and computers, and next among the computers. This process of learning is supposed to evolve in time with the increasing role of interactions among computers. In my opinion, in the current, early period of development of the discipline, making a preference for social and environmental bases of intellect may save time in obtaining some practical results, while the methods of molecular and systems biology will be moving to a deeper understanding of the genetic foundations of the intellect. As was mentioned above, no general approach or idea (including my own) can be a panacea in the attempts to find a method for computational modeling and simulation of intellect. 

ORGANIZATION OF THE BOOK

The book is divided into four main sections: Application of AI and CI Methods to Image and Signal Processing, Robotics, and Control (Chapters 1-7), Application of AI and CI Methods to Medicine and Environment Monitoring and Protection (Chapters 8-10), Concepts (Chapters 11-18), and Application of AI and CI Methods to Learning (Chapters 19-22).

A brief description of each of the chapters follows below.

Chapter 1 analyzes the images of colon in inflammatory bowel diseases (IBD) for localization and parameterization of the glandular ducts in order to extract the knowledge of IBD that is contained in it, especially to associate different stages of IBD with the location, shapes, geometry, and parameters of the ducts.
Chapter 2 focuses on the presentation of Igelnik and Parikh’s Kolmogorov Spline Network (KSN) for image processing and details two applications: image compression and progressive transmission. In ?compression, a combination of the KSN and wavelet decomposition into the JPEG 2000 encoder is presented. In ?progressive transmission, a modification of the generation of the KSN is proposed. The results of the simulation of a transmission over packet-loss channels are demonstrated.
Chapter 3 presents the intelligent information description techniques and the mostly used classification methods in an image retrieval and recognition system. A multicriteria classification method applied for sickle cells disease image databases is given. The recognition performance system is illustrated and discussed.
Chapter 4 describes a number of machine learning algorithms for autonomous navigation in a vegetative environment.  Specifically it focuses on the task of generalization and classification of a great number of high-dimensional feature vectors. For this purpose, such machine learning algorithms as k-nearest neighbor algorithm, multilayer perception, and support vector machine are considered.
Chapter 5 considers an application of the principles of Adaptive Dynamic Programming (ADP) to the control of a quadrotor helicopter platform flying in an uncontrolled environment and subject to various disturbances and model uncertainties. The ADP is based on reinforcement learning. The chapter is perfectly organized, combining the rigor of mathematics with deep understanding of practical issues.  
Chapter 6 describes an application of a neural modeling fields (NMF) paradigm to solution of two important problems: target tracking and situation recognition. It is shown that both problems can be solved within the NMF framework using the same basic algorithm. 
Chapter 7 presents a newly developed biogeography-based optimization (BBO) algorithm for tuning PID control system for real-world mobile robots. The BBO algorithm can be also used for the purpose of solving general global optimization problems. 
Chapter 8 employs the nascent Classification and Ranking Belief Simplex (CaRBS) technique that enables analysis in the spirit of uncertain reasoning.  The operational rudiments of the CaRBS technique are based on the Dempster-Shafer theory of evidence, affording the presence of ignorance in any analysis to be undertaken. An investigation of Total Hip Arthraplasty (THA), concerned with hip replacements, forms the applied problem around which the uncertain reasoning based analysis using CaRBS is exposited.  
Chapter 9 introduces a novel Levenberg-Marquardt like second-order algorithm for tuning the Parzen window s in a Radial Basis Function (Gaussian) kernel. The Kernel Partial Least Squares (K-PLS) model is applied to several benchmark data sets in order to estimate the effectiveness of the second-order sigma tuning procedure for an RBF kernel. The variable subset selection method based on these sigma values is then compared with different feature selection procedures such as random forests and sensitivity analysis. The sigma-tuned RBF kernel model outperforms K-PLS and SVM models with a single sigma value. K-PLS models also compare favorably with Least Squares Support Vector Machines (LS-SVM), epsilon-insensitive Support Vector Regression, and traditional PLS. The sigma tuning and variable selection procedure introduced in this chapter is applied to industrial magnetocardiogram data for the detection of ischemic heart disease from measurement of the magnetic field around the heart.
Chapter 10 gives a fundamental insight and overview of the process mechanism of different biological waste–gas (biofilters, biotrickling filters, continuous stirred tank bioreactors and monolith bioreactors) and wastewater treatment systems (activated sludge process, trickling filter and sequencing batch reactors). The basic theory of artificial neural networks has been explained. A generalized neural network modeling procedure for waste treatment applications has been outlined, and the role of back propagation algorithm network parameters has been discussed. Anew, the application of neural networks for solving specific environmental problems is presented in the form of a literature review.
Chapter 11 describes the motivated learning (ML) method that advances model building and learning techniques for intelligent systems. The chapter addresses: 1) critical limitations of the reinforcement learning (RL) in coordinating a machine’s interaction with an unknown dynamic environment by maximizing the external reward, and 2), the ML method that overcomes deficiencies of the RL by dynamically establishing the internal reward. ML is favorably compared with RL in an example, using a rapidly changing environment in which the agent needs to structure its motivations as well as to choose and implement the goal in order to succeed.
Chapter 12 addresses the role of the hippocampus in the physiological and cognitive mechanisms of topological space representation in humans and animals. The authors have shown that by using only the times of spikes from hippocampus place cells, it is possible to construct a topological space. The authors argue as well that the hippocampus is specialized for computing a topological representation of the environment. The chapter discusses a possibility of a constructive neural representation of a topological space.
Chapter 13 suggests a cognitive model of human conceptualisation on the basis of a cognitive theory of information processing and a Peircean theory of signs. Two examples are demonstrated related to a conceptualisation by an individual and to an elicitation by a team of participants. The results of experiments, conducted in these examples, to some degree justify the use of the cognitive model in various fields of human-computer interfacings such as computer aided problems solving and elicitation problems.
Chapter 14 focuses on the application of the discovery of association rules in approaches vague spatial databases.  The background of data mining and uncertainty representations using rough set and fuzzy set techniques is provided.  The extensions of association rule extraction for uncertain data as represented by rough and fuzzy sets are described.  Finally, an example of rule extraction for both types of uncertainty representations is given.
Chapter 15 describes a method of feature selection and ranking based on human expert knowledge and training and testing of a neural network. Being computationally efficient, the method is less sensitive to round-off errors and noise in the data than the traditional methods of feature selection and ranking grounded on the sensitivity analysis. The method may lead to a significant reduction of a search space in the tasks of modeling, optimization, and data fusion. The structure of ranking procedure refutes the common belief that neural networks are black box models.
Chapter 16 discusses the spiking neural network architectures for visual, auditory, and integrated audiovisual pattern recognition and classification. A spiking neural network, suggested by the authors, uses time to first spike as a code for saliency of input features. The system is trained and evaluated on the person authentication task. The authors conclude that the time-to-first-spike coding scheme may not be suitable for this difficult task, nor for auditory processing. Other coding schemes and extensions of this spiking neural network are discussed as the topics of the future research.
Chapter 17 suggests to model the intellect from a coordination of actions point of view, a balanced perspective that recognizes both social and individual aspects. A research program for modeling the intellect, based on the concept of “activity” (introduced in the Russian Activity Theory) and the activity models, is proposed. Provisional arguments for the relevance of the activity modalities are discussed in three different realms associated with the intellect: the social, conceptual, and neural ones. The chapter is concluded with some preliminary research questions, pertinent for the research program.
Chapter 18 describes use of chemical reaction-diffusion media as the information processing means fundamentally different from contemporary digital computers. Distributed character and complex nonlinear dynamics of chemical reactions inherent in the medium are the basis for large-scale parallelism and complex logical operations performed by the medium as primitives. It was found during the last decades that chemical reaction-diffusion media can be effectively used for solving artificial intelligence problems, such as image processing, finding the shortest paths in a labyrinth and some other important problems that are at the same time problems of high computational complexity. Spatially non uniform control of the medium by physical stimuli and fabrication of multi level reaction-diffusion systems seem to be the promising way enabling low cost and effective information processing devices that meet the commercial needs. Biological roots and specific neural net architecture of reaction diffusion media seem to enable simulating some phenomena inherent in the cerebral cortex, such as optical illusions.
Chapter 19 presents a Modified Learning Vector Quantization (MLVQ) algorithm. Experiments on the MLVQ algorithm are performed and contrasted against LVQ, GLVQ and FCM. Results show that MLVQ determines the number of clusters and converges to the centroids. Results also show that MLVQ is insensitive to the sequence of the training data, able to identify centroids of overlapping clusters and able to ignore outliers without identifying them as separate clusters. Results, using MLVQ algorithm and Gaussian membership functions with Pseudo Outer-Product Fuzzy Neural Network using Compositional Rule of Inference and Singleton fuzzifier (POPFNN-CRI(S)) on pattern classification and time series prediction, are also provided in order to demonstrate the effectiveness of the fuzzy membership functions derived using MLVQ.
Chapter 20 includes a discussion of the most well-known and efficient outlier detection techniques with numerical demonstrations in linear regression. The chapter will help the readers interested in exploring and investigating an effective mathematical model. This chapter is self-contained, maintaining its general accessibility.
Chapter 21 surveys the problem of classification tasks in unbalanced datasets. The effect of the imbalance of the distribution of target classes in databases is analyzed with respect to the performance of standard classifiers such as decision trees and support vector machines. The main approaches to improve the generally not satisfactory results obtained by such methods are described. Finally, two typical applications coming from real world frameworks are introduced, and the use of the techniques employed for the related classification tasks is shown in practice.
Chapter 22 demonstrates the behavior of the 1-n-1 complex-valued neural network that has learned a transformation on the Steiner circles. The relationship between the values of the complex-valued weights after training and a linear transformation related to the Steiner circles is clarified via computer simulations. Furthermore, the relationship between the weight values of the 1-n-1 complex-valued neural network learned 2D affine transformations and the learning patterns used is elucidated. These research results make it possible to solve complicated problems more simply and efficiently with 1-n-1 complex-valued neural networks. In particular, an application of the 1-n-1 type complex-valued neural network to an associative memory is presented.


REFERENCES

Adamatzky, A. (2001). Computing in nonlinear media and automata collectives. Bristol, UK: Institute of Physics Publishing.

Alon, U. (2007). An introduction to systems biology: Design principles of biological circuits. London, UK: Chapman & Hall/CRC.

Anderson, J. R. (2007). How can the human mind occur in the physical universe? New York, NY: Oxford University Press.

B. Goertzel & C. Pennacin (Eds.). (2007). Artificial general intelligence. Berlin/ Heidelberg, Germany: Springer-Ferlag.

B. Reusch, & K. H. Timme (Eds). (2001). Computational intelligence in theory and practice. Heidelberg, Germany: Phisica-Verlag.

Batchelor, B. G., & Whelan, P. F. (1997). Intelligent vision systems for industry. New York, NY: Springer.

Bekey, G. A. (2005). Autonomous robots: From biological inspiration to implementation and control. Cambridge, MA: The MIT Press.

Bekey, G. A., et al. (2008). Robotics: State of the art and future challenges. Hackensack, NJ: World Scientific Publishing.

Bruggerman, J. (2008). Social networks: An introduction. London, UK & New York, NY: Routledge, Taylor & Francis Group.

D. N. Davis (Ed.). (2005). Visions of mind: Architectures for cognition and affect. Hershey, PA: Information Science Publishing.

D. Taniar (Ed). (2004). Research and trends in data mining technologies and applications. Hershey, PA: Idea Group Publishing.

F. C. Boogerd, et al (Eds.). (2007). Systems biology: Philosophical foundations. Amsterdam, The Netherlands: Elsevier.

Freeman, W. J. (2000). How brains make up their minds. New York, NY: Columbia University Press.

Garcez, A. S. A., Broada, K. B., & Gabbay, D. M. (2002). Neural-symbolic learning systems: Foundations and applications.  London, UK: Springer. 

Gardenforc, P. (2000). Conceptual spaces: The geometry of thought. Cambridge, MA: The MIT Press.

Haikonen, P. O. (2003). The cognitive approach to conscious machines. Charlottersville, VA: Imprint Academic.

Haikonen, P. O. (2007). Robot brains. Hoboken, NJ: John Wiley & Sons, Inc.

Haykin, S. (1994). Neural networks: A comprehensive foundation. New York, NY: Macmillan College Publishing.

Haykin, S. (2002). Adaptive filter theory, 4th ed. Upper Saddle River, NJ: Prentice Hall.

I. Cloete & J. M. Zurada (Eds.). Knowledge-based engineering. Cambridge, MA: The MIT Press.

J. Feng (Ed.). (2004). Computational neuroscience: A comprehensive approach. Boca Raton, FL: Chapman & Hall/CRC.

J. M. Zurada, R. J. Marks II, & C. J. Robinson (Eds.). (1994). Computational intelligence: Imitating life. New York, NY: IEEE Press.

Jain, A. K. (1989). Fundamentals of digital image processing. Englewood Cliffs, NJ: Prentice-Hall.

K. J. Hunt, G. R. Irwin, & K. Warwick (Eds). (1995). Neural network engineering in dynamic control systems. New York, NY: Springer.

Kasabov, N. K. (1996). Foundations of neural networks, fuzzy systems, and knowledge engineering. Cambridge, MA: MIT Press.

Khosla, R., & Dillon, T. (1997). Engineering intelligent hybrid multi-agent systems. Norwell, MA: Kluwer Academic Publishers.

Kolman, E., & Margaliot, M. (2009). Knowledge-based neurocomputing: A fuzzy logic approach. Berlin/ Heidelberg, Germany: Springer-Ferlag.

L. I. Perlovsky& R. Kozma (Eds.). (2007). Neurodynamics of cognition and consciousness. Heidelberg, Germany: Springer. 

Lillesand, T. M., & Kiefer, R. (1999). Remote sensing and image interpretation. New York, NY: Wiley.

Lytton, W. W. (2002). From computer to brain: Foundations of computational neuroscience. New York, NY: Springer-Verlag.

Mars, P., Chen, J. R., & Nambiar, R. (1996). Learning algorithms: Theory and applications in signal processing, control and communications. Boca Raton, FL: CRC Press.

Mataric, M. J. (2007). The robotics primer. Cambridge, MA: The MIT Press.

McLeod, P., Planket, P. K., & Rolls, E. T. (1998). Introduction to connectionist modeling of cognitive processes. Oxford, UK: Oxford University Press.

Minsky, M. (1986). Society of minds. New York, NY: Simon and Schuster.

O’Reilly, R. C., & Munakata, Y. (2000). Computational explorations in cognitive neuroscience. Cambridge, MA: The MIT Press.

Perlovsky, L. I. (2001). Neural networks and intellect: Using model-based concepts. Oxford, UK: Oxford University Press.

Perlovsky, L. (2007). Symbols: Integrated cognition and language. In R. Gudvin & J. Queiroz (Eds.), Semiotics and intelligent systems development. Hershey, PA: Idea Group Publishing.

Polk, T. A., & Seifert, C. M. (2002). Cognitive modeling. Cambridge, MA: The MIT Press.

Pratt, W. K. (2007). Digital image processing, 4th ed. Hoboken, NJ: John Wiley & Sons, Inc.

Priami, C. (2009). Algorithmic systems biology. Communications of the ACM, 52(5), 80-88.

R. A. Katz (Ed.). (1996). Chaotic, fractal, and nonlinear signal processing. Woodbury, NY: AIP Press.

R. Gudvin & J. Queiroz (Eds.). (2007). Semiotics and intelligent systems development. Hershey, PA: Idea Group Publishing.  

Rihaczek, A. W., & Hershkowitz, S. J. (2000). Theory and practice of radar target identification. Norwood, MA: Artech House.

S. Haykin, et al. (Eds.). (2007). New directions in statistical processing: From systems to brain. Cambridge, MA: The MIT Press.

Schwefel, H.-P., Wegener, I., & Weinert, K. (2003). Advances in computational intelligence: Theory and practice. Berlin, Germany: Springer.

Simon, D. (2006). Optimal state estimation: Kalman, HY, and nonlinear approaches. Hoboken, NJ: Wiley & Sons.

Swanson, D. C. (2002). Signal processing for intelligent sensing systems. New York, NY: Marcel Dekker.

T. Kitamura (Ed.). (2001). What should be computed to understand and model brain function? From robotics, soft computing, biology and neuroscience to cognitive philosophy. Singapore: World Scientific.

T. Sienco, A. Adamatzky, N. Rambidi, & M. Conrad (Eds.). (2003). Molecular computing. Cambridge, MA: The MIT Press.

Thelen, E., & Smith, L. B. (1998). A dynamic systems approach to the development of cognition and action. Cambridge, MA: MIT Press.

Trappenberg, T. P. (2002). Fundamentals of computational neuroscience. Oxford, UK: Oxford University Press.

V. Gorodetsky, et al. (Eds.). (2007). Autonomous intelligent systems: Agents and data mining. Berlin/ Heidelberg, Germany: Springer-Ferlag.

Wilkinson, D. J. (2006). Stochastic modelling in systems biology. Boca Raton, FL: Chapman & Hall/CRC.

Y.-Q. Zang, & J. C. Rajapakse. (Eds). (2009). Machine learning in bioinformatics. Hoboken, NJ: J. Wiley & Sons, Inc.

Y. Wang (Ed.). (2009). Novel approaches in cognitive informatics and natural intelligence. Hershey, PA: IGI Global.

Author(s)/Editor(s) Biography

Boris Igelnik received M.S. degree in electrical engineering from the Moscow Electrical Engineering Institute of Communication, M. S. degree in mathematics from the Moscow State University, and Ph.D. degree in Electrical Engineering from the Institute for Problems of Information Transmission, Academy of Sciences USSR, Moscow, Russia and the Moscow Electrical Engineering Institute of Communication. He is Chief Scientist at the BMI Research, Inc., Richmond Heights (Cleveland), OH, USA and Adjunct Associate Professor at Case Western Reserve University, Cleveland, OH, USA. His current research interests are in the areas of computational and artificial intelligence, digital signal processing, adaptive control, and computational models of intellect. Boris Igelnik is a Senior Member of IEEE.

Indices

Editorial Board

  • Andrew Adamatzky, University of West England, UK
  • Boris Igelnik, BMI Research, Inc. and Case Western Reserve University, USA
  • Sheng Chen, University of Southampton, UK
  • Witold Kinzner, University of Manitoba, Canada
  • Frank Lewis, University of Texas at Arlington, USA
  • Tohru Nitta, National Institute of Advanced Industrial Science and Technology, Japan
  • Leonid Perlovsky, US Air Force Research Laboratory, USA
  • Dan Simon, Cleveland State University, USA
  • Janusz Starzyk, University of Ohio at Athens, USA