AUT - Books

KEDRI

Home  >  Research  >  Research Institutes  >  KEDRI  >  Books

• Enquire
• Apply now
• Email this page
• Print

• Gene Selection Based On Consistency Modelling, Algorithms And Applications - Genetic Algorithm Application In Bioinformatics Data Analysis
• Evolving Connectionist Systems: The Knowledge Engineering Approach
  
• Computational Neurogenetic Modeling
• Future Directions for Intelligent Systems and Information Sciences
• Neuro-Fuzzy Techniques for Intelligent Information Systems
• Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines
• Brain-Like Computing and Intelligent Information Systems
• Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering

Gene Selection Based On Consistency Modelling, Algorithms And Applications - Genetic Algorithm Application In Bioinformatics Data Analysis

Gene Selection Based On Consistency Modelling, Algorithms And Applications - Genetic Algorithm Application In Bioinformatics Data Analysis

Yingjie Hu
ISBN:3639008839
ISBN-13:9783639008838,978-3639008838
Binding: Paperback
Publishing Date: 04-2008
Publisher: Vdm Verlag
Number of Pages: 112
Language: English

About this book
Consistency modeling for gene selection is a new topic emerging from recent cancer bioinformatics research. The result of classification or clustering on a training set was often found very different from the same operations on a testing set. Here, the issue is addressed as a consistency problem. In practice, the inconsistency of microarray datasets prevents many typical gene selection methods working properly for cancer diagnosis and prognosis. In an attempt to deal with this problem, a new concept of performance-based consistency is proposed in this thesis. The proposed consistency concept has been investigated on eight benchmark microarray and proteomic datasets. The experimental results show that the different microarray datasets have different consistency characteristics, and that better consistency can lead to an unbiased and reproducible outcome with good disease prediction accuracy.

Evolving Connectionist Systems: The Knowledge Engineering Approach

Evolving Connectionist Systems: The Knowledge Engineering Approach
(Second, Extended Edition)

Kasabov, Nikola
Originally published in the Series: Perspectives in Neural Computing
2nd ed., 2007, XXII, 458 p., 185 illus., Softcover
ISBN: 978-1-84628-345-1

About this book
This second edition of Evolving Connectionist Systems presents generic computational methods and techniques for evolvable, adaptive, knowledge-based models and systems. This edition includes new methods, such as: adaptive model and data integration, adaptive model and feature optimisation, neuro-fuzzy personalised modelling, computational neuro-genetic modelling, quantum inspired information processing, along with new applications in: bioinformatics, brain data modelling, adaptive robots, adaptive decision support systems, adaptive multimodal signal processing. The models and techniques presented are connectionist-based, integrating neural networks, fuzzy rule-based systems, evolutionary computation, and statistical techniques, featuring adaptive learning and knowledge discovery. Divided into two parts, the book opens with evolving processes in nature; looks at methods and techniques for adaptive, evolving, knowledge-based learning; then covers bioinformatics and brain data modelling and knowledge discovery; finishing with various applications for intelligent systems. The book is aimed at all those interested in developing adaptive models and systems to solve challenging real world problems in information sciences and engineering.

Table of contents
Part 1 Evolving Connectionist Methods – Modelling and Knowledge Discovery from Dynamic, Evolving Information Processes – Feature selection, Model Creation and Model Validation – Evolving Connectionist Methods for Unsupervised Learning – Evolving Connectionist Methods for Supervised Learning – Evolving State-Based and Spiking Neural Networks – Evolving Neuro-Fuzzy Inference Methods – Population/Generation-Based Methods: Evolutionary Computation - Evolving Integrated Multi-Model Systems – Part II Evolving Intelligent Systems – Adaptive Modelling and Knowledge Discovery in Bioinformatics – Adaptive Modelling and Knowledge Discovery from Brain Data – Modelling the Emergence of Acoustic Segments in Spoken Languages – Adaptive Speech Recognition – Adaptive Image Processing – Adaptive Multi-Modal Signal Processing – Evolving Robotics and Socio-Economic Systems - Quantum Inspired Evolving Intelligent Systems.

Color figures from this book
Click here to download

Computational Neurogenetic Modeling

By Lubica Benuskova and Nikola Kasabov, Auckland University of Technology, Auckland, New Zealand

Computational Neurogenetic Modeling
Series: Topics in Biomedical Engineering. International Book Series
Benuskova, Lubica, Kasabov, Nikola
2007, XII, 292 p., 27 illus., 27 in colour, Hardcover
ISBN: 978-0-387-48353-5

We have a limited number of exemplars to be purchased directly from the authors at a reduced price by 45% including shipment. Please contact lubica.benuskova@aut.ac.nz

About this book
Computational Neurogenetic Modeling is a student text, introducing the scope and problems of a new scientific discipline - Computational Neurogenetic Modeling (CNGM). CNGM is concerned with the study and development of dynamic neuronal models for modeling brain functions with respect to genes and dynamic interactions between genes. These include neural network models and their integration with gene network models. This new area brings together knowledge from various scientific disciplines, such as computer and information science, neuroscience and cognitive science, genetics and molecular biology, as well as engineering.

Written for
Researchers in academia and industry, advanced undergraduates, graduate students in Biomedical Engineering: Bioinformatics applications across the disciplines of Computer and Information Sciences, Neuroscience and Cognitive Science, Genetics and Molecular Biology, Bioengineering and Engineering.

Table of contents
Introduction

Part I. Neuro-Information Processing: Organisation and Functions of the Brain -Neuro-Information Processing in the Brain -Measuring Activities of the Brain.

Part II. Artifical Neural Networks (ANN) and Connectionist Systems: Artifical Neural Networks (ANN) -Neurocomputing Models of Brain Functions.

Part III. Gene Information Processing: Genes and Cellular Processes - Computational Models of Gene Information Processing.

Part IV. Neuro-Genetic Information Processing: Neuro-Genetic Processes in the Brain.- Computational Neuro-Genetic Modeling (CNGM).- CNGM of Brain Functions and Diseases.- Conclusion and Future Directions.- References.- Appendices.- Glossary.- Index.

Color figures from this book
Click here to download

Future Directions for Intelligent Systems and Information Sciences

By Nikola Kasabov, Auckland University of Technology, Auckland, New Zealand

Future Directions for Intelligent Systems and Information Sciences
The Future of Speech and Image Technologies, Brain Computers, WWW, and Bioinformatics
Series: Studies in Fuzziness and Soft Computing , Vol. 45
Kasabov, Nikola (Ed.)
2000, VIII, 424 p. 116 illus., Hardcover
ISBN: 978-3-7908-1276-3

About this book
The book introduces and discusses the future trends in computer science and artificial intelligence. These trends include image and speech technologies; virtual reality and multimedia systems; evolving systems and artificial life; artificial and natural neural networks; brain-computers; the Web, the intelligent agents on it, and the distributed processing systems; mobile robots in a real and in a virtual environment; bioinformatics, and the marriage of genetic engineering and information science. The book comprises chapters written by well-known specialists in this field and can be used by scientists and graduate students from different areas, as well as by a wider audience of people interested in the present and future development of intelligent systems, in all areas of information sciences.

Written for
Researchers

Table of contents
Part I: Adaptive, evolving, learning systems: N. Kasbov: ECOS - Evolving Connectionist Systems - a new/old paradigm for on-line learning and knowledge engineering.- S.-B. Cho: Artificial life technology for adaptive information processing.- R.J. Duro, J. Santos, J.A. Becerra: Evolving ANN controllers for smart mobile robots.- G. Coghill: A simulation environment for the manipulation of naturally variable objects.- Y. Maeda: Behavior-decision fuzzy algorithm for autonomous mobile robot.- J. Taylor, N. Kasabov: Modelling the emergence of speech and language through evolving connectionist systems.

Part II: Intelligent human computer interaction and scientific visualisation: H.J. van den Herik, E.O. Postma: Discovering the visual signature of painters.- A. Nijholt, J. Hulstijn: Multimodal interactions with agents in virtual worlds.- M. Paulin, R. Berquist: Virtual BioBots.

Part III: New connectionist computational paradigms: Brainlike computing and quantum neural networks: J.G. Taylor: Future directions for neural networks and intelligent systems from the brain imaging research.- A.A. Ezhov, D. Ventura: Quantum neural networks.- N.G. Stocks, R. Mannella: Suprathreshold stochastic resonance in a neuronal network model: a possible strategy for sensory coding.

Part IV: Bioinformatics: C. Brown, M. Schreiber, B. Chapman, G. Jacobs: Information science and bioinformatics.- V.B. Bajic, I.V. Bajic: Neural network system for promoter recognition.

Part V: Knowledge representation, knowledge processing, knowledge discovery, and some applications: W. Pedrycz: Granular computing: An introduction.- J. Kacpzryk: A new paradigm shift from computation on numbers to computation on words on an example of linguistic database summarization.- N. Kasabov, L. Erzegovezi, M. Fedrizzi, A. Beber, D. Deng: Hybrid intelligent decision support systems and applications for risk analysis and discovery of evolving economic clusters in Europe.- Y.Y. Yun: Intelligent resource management through the constrained resource planning model.- A. Ramer, M. do Carmo Nicoletti, S.Y. Sung: Evaluative studies of fuzzy knowledge discovery through NF systems.

Neuro-Fuzzy Techniques for Intelligent Information Systems (Studies in Fuzziness and Soft Computing, Vol. 30)

By Nikola Kasabov (editor), Robert Kozma (editor)

Hardcover: 449 pages
Publisher: Springer-Verlag Telos (June 1999)
Language: English
ISBN-10: 3790811874
ISBN-13: 978-3790811872
Product Dimensions: 9.5 x 6.8 x 1 inches
Amazon.com page

This volume comprises selected chapters that cover contemporary issues of the development and the application of neuro-fuzzy techniques. Developing and using neural networks, fuzzy logic systems, genetic algorithms and statistical methods as separate techniques, or in their combination, have been research topics in several areas such as mathematics, engineering, computer science, physics, economics and finance. Here the latest results in the fields are presented from both theoretical and practical point of view. The volume has four main parts. Part one presents generic techniques and theoretical issues while part two, three and four deal with practically oriented models, systems and implementations.

Part 1. Generic Neuro-Fuzzy and Hybrid Techniques

Analysis and Modeling of Complex Systems Using the Self-Organizing Map
(Olli Simula, Juha Vesanto, Esa Alhoiemi and Jaakko Hollmen)
Fuzzy Methods for Learning from Data (Vladimir Cherkassky)
Uneven Allocation of Membership Functions for Fuzzy Modeling of Multi-Iput System (Kanta Tachibaa and Takeshi Furuhashi)
Fuzzy Equivalence Relations and Fuzzy Partitions (Berd Reusch)
Identifying Fuzzy Rule-Based Models Utilizing Neural Networks, Fuzzy Logic and Genetic Algorithms (Andreas Bastian)
Neuro-Genetic Information Processing for Optimisation and Adaptation in Intelligent Systems (Michael Watts and Nikola Kasabov) Evolving Connectionist and Fuzzy-Connectioist Systems: Theory and Applications for Adaptive, O-line Itelligent systems (Nikola Kasanbov)

Part 2. Neuro-Fuzzy Systems for Pattern Recognition, Image, Speech- and Laguage Processing

Connectionist Approaches for Feature Analysis (Nikhil R. Pal)
Patter Classification ad Feature Selectio by Ellipsoidal Fuzzy Rules (Shigeo Abe)
Printed Chinese Optical Character recognition by Neural Network (Youshio Wu and Mingsheg Zhao)
Image Processing by Chaotic Neural Network (Harold Szu)
Fuzzy Membership Functions (Charles Hsu)
Fuzzy Learing Machine with Application to the Detection of Landmarks for Orthodontic Treatment (Eiji Uchino and Takeshi Yamakawa)
Speech Data Analysis and Recognition Using Fuzzy Neural Networks and Self-Organizing Maps (N. Kasabov, R. Kozma, R. Kilgour, M. Laws, M. Watts, A. Gary and J. Taylor)
Connectionist Methods for Stylometric Analysis: A Hybrid Approach (Diana Kassabova and Philip Sallis) 

Part 3. Neuro-Fuzzy Systems for Informatio Retrieval and Socio-Economic Applications

Soft Information Retrieval: Applications of Fuzzy Theory and Neural Networks (Fabio Crestani and Gabriella Pasi)
Modeling Consensus in Group Decision Making: a Fuzzy Dynamical Approach (Mario Fedrizzi, Michele Fedrizzi and R.A. Marques Pereria)
Building Fuzzy Expert Systems (Michael Negnevitsky)
A Neural Network for Fuzzy Dynamic Programming ad Its Use in Socio-Economic Regional Development Planning (Jausz Kapcprzyk, Roseli A. Francelin and Ferrando A.C. Gomide)
Investment Maps for Emerging Markets (Guido J. Deboeck)
Adaptive Fuzzy-Impedance Controller for Cosntrained Robot Motion (Petar B. Petrovic)

Part 4. Specialised Hardware for Neuro-Fuzzy Intelligent System

Specialisd Hardware for Computaional Intelligence (George Coghill)
Evoluable Hardware - the coming Hardware Design Method? (Jim Torresen)

Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines

By Kasabov, N., Auckland University of Technology, Auckland, New Zealand

Hardcover - 400 pages
Springer Verlag, March 1998
ISBN: 9813083581
Dimensions (in inches): 1.35 x 9.60 x 6.54
Amazon.com page
Springer Online Catalogue

Many methods and models have been proposed for solving difficult problems such as prediction, planning and knowledge discovery in application areas such as bioinformatics, speech and image analysis. Most, however, are designed to deal with static processes which will not change over time. Some processes - such as speech, biological information and brain signals - are not static, however, and in these cases different models need to be used which can trace, and adapt to, the changes in the processes in an incremental, on-line mode, and often in real time. This book presents generic computational models and techniques that can be used for the development of evolving, adaptive modelling systems. The models and techniques used are connectionist-based (as the evolving brain is a highly suitable paradigm) and, where possible, existing connectionist models have been used and extended. The first part of the book covers methods and techniques, and the second focuses on applications in bioinformatics, brain study, speech, image, and multimodal systems. It also includes an extensive bibliography and an extended glossary. Evolving Connectionist Systems is aimed at anyone who is interested in developing adaptive models and systems to solve challenging real world problems in computing science or engineering. It will also be of interest to researchers and students in life sciences who are interested in finding out how information science and intelligent information processing methods can be applied to their domains.

Colour figures from the book
Chapter 8, Chapter 9, Chapter 10, Chapter 11, Chapter 12, Chapter 13

Chapter Presentations
Chapter 1, Chapter 2, Chapter 3, Chapter 4, Chapter 5, Chapter 6, Chapter 7, Chapter 8, Chapter 9, Chapter 10, Chapter 11, Chapter 12, Chapter 13

Purchase from Amazon

• Amazon.com
• Amazon.co.uk
• Amazon.co.jp

ECOS Toolbox for Matlab
The Matlab toolbox includes three major modules:

• DENFIS
• ECM
• ESOM

ECOS modules are now part of the project "NeuCom". For more information, please visit the NeuCom homepage.

Selected papers on ECOS

2003 - Kasabov, N., Data Mining and Knowledge Discovery Using Adaptive Neural Networks, Tutorial, IJCNN'03, Portland, USA

2003 - Kasabov, N., Goh, L., NeuCom - Environment for teaching and research in Bioinformatics, ISBM'2003, Brisbane, Australia

2002-Kasabov, N., and Song, Q., DENFIS: Dynamic Evolving Neural-Fuzzy Inference System and its Application for Time Series Prediction, IEEE Transactions on Fuzzy Systems, vol. 10, no.2, April, (2002) 144-154.

2001 - Kasabov, N., Evolving Fuzzy Neural Networks for Supervised/Unsupervised On-Line, Knowledge-Based Learning, IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, Vol 31, No. 6 Issue (December 2001, pp.902-918)

2001 - Kasabov, N., Artificial Neural Networks for Intelligent Information Processing, Transactions of Chemical Engineering, London, June 2001, 27:28

2001 - Kasabov, N. On-line learning, reasoning, rule extraction and aggregation in locally optimised evolving fuzzy neural networks, Neurocomputing, 41 (2001) 25-41

1999 - Kasabov, N . Evolving connectionist and fuzzy connectionist systems – theory and applications for adaptive, on-line intelligent systems, In: Neuro-Fuzzy Techniques for Intelligent Information Processing, N. Kasabov and R. Kozma (eds.), Heidelberg Physica Verlag.

1999 - Kasabov, N. . Evolving connectionist and fuzzy connectionist systems for on-line adaptive decision making and control, In: Advances in Soft Computing - Engineering Design and Manufacturing, R. Roy, T. Furuhashi and P.K. Chawdhry (Eds.) Springer-Verlag.

1999 - Kasabov, N. . Evolving connectionist systems for fast identification, classification and decision making, Australian Journal of Intelligent Information Processing Systems.

1998 - Kasabov, N. . The ECOS framework and the 'eco' training method for evolving connectionist systems, Journal of Advanced Computational Intelligence, vol.2, No.6, 1-8.

ECOS Power Point Presentation

2000 - Nikola Kasabov. Evolving Connectionist Systems: Methods, Techniques, Applications, IJCNN'2000 Tutorial.

Brain-Like Computing and Intelligent Information Systems

By Shun-Ichi Amari (editor), Nikola K. Kasabov (editor)

Hardcover - 400 pages
Springer Verlag, March 1998
ISBN: 9813083581
Dimensions (in inches): 1.35 x 9.60 x 6.54
Amazon.com page

This book introduces and defines a new area in computer science ant artificial intelligence called brain-like computing. Brain-like computing combines traditional computational techniques with computational and cognitive ideas, principles and models inspired by the human brain for building intelligent information systems, to be used in our everyday life. Image and speech processing, blind signal separation, creative planning and design, decision making, adaptive control, knowledge acquisition and database mining, are only a few areas where brain-like computing is applied. The more is known about the functionality of the brain the more intelligent the information systems will become. Modelling mind and consciousness are topics also presented in the book along with other new theoretical models and applications in the area of artificial intelligence.

The book comprises chapters written by well-known specialists in the field and can be used by scientists and graduate students from different areas, as well as by a wider audience of people interested in the present and future development of computer science and artificial intelligence.

Table of Contents
Part I Computer Vision and Image Processing

Part II Speech Recognition and Language Processing

Chapter 4. A Computational Model of the Auditory Pathway to the Superior Colliculus (Raymond J.W. Wang and Marwan Jabri)
Chapter 5. A Framework for Intelligent "Conscious" Machines Utilising Fuzzy Neural Networks and Spatio-Temporal Maps and a Case Study of Multilingual Speech Recognition (Nikola Kasabov)

Part III Dynamic Systems: Statistical and Chaos Modelling. Blind Source Separation

Chapter 6. Noise-Mediated Cooperative Behavior in Integrate-Fire Models of Neuron Dynamics (Adi R. Bulsara)
Chapter 7. Blind Source Separation -- Mathematical Foundations (Shun-ichi Amari)
Chapter 8. Neural Independent Component Analysis -- Approaches and Applications (Erkki Oja, Juha Karhunen, Aapo Hyvarinen, Ricardo Vigario and Jarmo Hurri)
Chapter 9. General Regression Techniques Based on Spherical Kernel Functions for Intelligent Processin (Anthony Zankich and Yianny Attikiouzel)
Chapter 10. Chaos and Fractal Analysis of Irregular Time Series Embedded in a Connectionist Structure (Robert Kozma and Nikola Kasabov)

Part IV Learning Systems and Evolutionary Computation

Chapter 11. Bayesian Ying-Yang System and Theory as a Unified Statistical Learning Approach (I): Unsupervised and Semi-Unsupervised Learning (Lei Xu)
Chapter 12. Evolutionary Computation: An Introduction, Some Current Applications, and Future Directions (David B. Fogel)
Chapter 13. Biologically Inspired New Operations for Genetic Algorithms (Ashish Ghosh and Sankar K. Pal) 

Part V Adaptive Learning for Navigation, Control and Decision Making

Chapter 14. From Vision to Action via Distributed Computation (Michael A. Arbib)
Chapter 15. A Brain-like Design to Learn Optimal Decision Strategies in Complex Environments (Paul J. Werbos) 

Part VI Knowledge Recovery and Information Retrieval

Chapter 16. Structural Learning and Rule Discovery from Data (Masumi Ishikawa)
Chapter 17. Measuring the Significance and Contributions of Inputs in Backpropagation Neural Networks for Rules Extraction and Data Mining (Tamas D. Gedeon)
Chapter 18. Applying Connectionist Models to Information Retrieval (Sally Jo Cunningham, Geoffrey Holmes, Jamie Littin, Russell Beale and Ian H. Witten)

Part VII Consciousness in Living and Artificial Systems

Chapter 19. Neural Networks for Consciousness (John G. Taylor)
Chapter 20. Platonic Model of Mind as an Approximation to Neurodynamics (Wlodzislaw Duch)
Chapter 21. Towards Visual Awareness in a Neural System (Igor Aleksander, Chris Browne, Barry Dunmall and Tim Wright)

Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering

By Nikola K. Kasabov 

Hardcover - 550 pages
MIT Press, December 1996
ISBN: 0262112124
Dimensions (in inches): 1.59 x 9.37 x 7.42
Amazon.com page
MIT Press page

Editorial Review by MIT Press

Neural networks and fuzzy systems are different approaches to introducing human-like reasoning into expert systems. This text is the first to combine the study of these two subjects, their basics and their use, along with symbolic AI methods to build comprehensive artificial intelligence systems. In a clear and accessible style, Kasabov describes rule- based and connectionist techniques and then their combinations, with fuzzy logic included, showing the application of the different techniques to a set of simple prototype problems, which makes comparisons possible. A particularly strong feature of the text is that it is filled with applications in engineering, business, and finance. AI problems that cover most of the application-oriented research in the field (pattern recognition, speech and image processing, classification, planning, optimization, prediction, control, decision making, and game simulations) are discussed and illustrated with concrete examples. Intended both as a text for advanced undergraduate and postgraduate students as well as a reference for researchers in the field of knowledge engineering, Foundations of Neural Networks, Fuzzy Systems, and Knowledgen Engineering has chapters structured for various levels of teaching and includes original work by the author along with the classic material. Data sets for the examples in the book as well as an integrated software environment that can be used to solve the problems and do the exercises at the end of each chapter are available free through anonymous ftp.

Table of Contents

Chapter 1. The Faculty of Knowledge Engineering and Problem Solving
Chapter 2. Knowledge Engineering and Symbolic Artificial Intelligence
Chapter 3. From Fuzzy Sets to Fuzzy Systems
Chapter 4. Neural Networks: Theoretical and Computational Models
Chapter 5. Neural Networks for Knowledge Engineering and Problem Solving
Chapter 6. Hybrid Symbolic, Fuzzy, and Connectionist Systems: Toward Comprehensive Artificial Intelligence
Chapter 7. Neural Networks, Fuzzy Systems and Nonlinear Dynamical Systems. Chaos; Toward New Connectionist and Fuzzy Logic Models

Downloads

Software: FuzzyCope I, FuzzyCope2, NeuCom
Dataset: dataset.zip
Others: Flyer, Lecture Notes