548 BOOK REVIEWS

the next part are organized as follows: first, a and the controllability theory in Chapter 7.
general review of notions relevant for nonlinear Without any doubt this book will become a
dynamical or control systems is given, and then classic in the field and, due to its completeness, it
the special case of simple mechanical control will very likely be considered as the ‘bible’ in this
systems is treated. These reviews are, on their specific methodology for the study of mechanical
own, a self-contained review of aspects of systems using Riemannian Geometry.
geometric control theory. This second part also Related nice volumes are the book of Bloch [1]
contains the interesting concept of kinematic and the book of Nijmijer and van der Schaft [2],
reduction, which gives a precise formulation just to name a few [3, 4]. I dare to say that the
of when, roughly speaking, a mechanical work is a real masterpiece, and the only critique
control system can be characterized by studying which I may express is the fact that its extreme
appropriate driftless first-order systems, called preciseness of exposition may prevent a broader
kinematic reductions. public to appreciate the beauty of the methodol-
The third part of the book is devoted to a ogies presented in this volume.
collection of control design problems, including
potential shaping for fully actuated and under- REFERENCES
actuated systems, tracking using oscillatory
controls, and motion planning using kinematic 1. Bloch AM. Nonholonomic Mechanics and Control.
Springer: New York, NY, 2003.
reductions. As explained by the authors, this part 2. Nijmeijer H, van der Schaft A. Nonlinear Dynamical
is to be understood as a collection of approaches, Control Systems. Springer: New York, NY, 1990.
rather than the comprehensive fully developed 3. Abraham R, Marsden JE. Foundations of Mechanics.
treatment in the modelling and analysis parts. Addison-Wesley: New York, NY, 1994.
Chapter 10 and 11 contain a nice review of 4. Arnold VI. Mathematical Methods of Classical
Mechanics. Springer: New York, NY, 1989.
potential shaping methods; here this is limited to
potential energy shaping. Chapter 12 contains
control laws based on the averaging techniques STEFANO STRAMIGIOLI
previously introduced. Finally, Chapter 13 con- Control Engineering Laboratory,
tains motion planning algorithms for mechanical IMPACT Institute,
control systems that admit controllable kinematic University of Twente,
reductions. P.O. Box 217, NL-7500 AE Enschede,
On numerous counts, this text is a unique The Netherlands
textbook-style reference for subjects rarely E-mail: [email protected]
exposed in the literature. Examples include the
treatment of detailed distributions in Chapter 3, (DOI: 10.1002/rnc.1064)
aspects of the physical modelling in Chapter 4,

soft computing and intelligent systems about them’. In terms of hierarchy, the intelli-
design: theory, tools and applications, gence occupies next to genius ‘person with very
F. O. Karry and C. De Silva, Pearson, Addison- high intelligent quotient’ as shown in Figure 1. At
Wesley, New York, NY, 2004 the bottom of the ladder is the data which when
formatted becomes information to be useful for
any analysis. If one acquires a lot of information,
1. INTRODUCTION he/she becomes a knowledgeable person. If knowl-
edge is used with respect to facts and reason, it
Intelligence is defined, according to Webster’s becomes intelligence. A highly intelligent person
Dictionary, as ‘the capacity to apprehend facts becomes a genius. The conventional artificial
and propositions and their relations and to reason intelligence (AI) refers to mimicking human

Copyright # 2006 John Wiley & Sons, Ltd. Int. J. Robust Nonlinear Control 2006; 16:547–551
 BOOK REVIEWS 549

intelligent behaviour by expressing in language or GENIUS

symbolic forms [1–3]. The earlier products of AI

are expert systems or knowledge-based systems.
With spectacular advances in computer hardware INTELLIGENCE

and software, and biological modelling, the mod-

ern AI, also called machine intelligence, compu-
KNOW LE DGE
tational intelligence, or soft computing (SC),
comprises additionally methodologies based on
neural networks (NNs), fuzzy logic (FL),
evolutionary computation, probabilistic reason- I N F O R M AT I O N
ing (PR), simulated annealing (SA), chaotic sys-
tems and so on. The SC, unlike the traditional
hard computing aiming for precision and certain-
ty, focuses on accommodating pervasive impreci- D A T A
sion and uncertainty of the real world. The NNs
provide learning, identification and adaptation [4];
the FL deals with imprecision, approximate rea-
soning, and rule-based systems [5]. Evolutionary
computing (EC), also called evolutionary
algorithms, is based on biological evolutionary Figure 1. Hierarchy of Data to Genius
processes of Darwian theory [6] that ‘allow (# D. S. Naidu, 2005).
populations of organisms to adapt to their sur-
rounding environment, genetic inheritance and fields such as electrical power systems and drives
survival of the fittest’ [7]. The EC [8] comprises of [20] and telecommunications [21].
evolutionary programming (EP), genetic algo-
rithms (GAs), genetic programming (GP), and
classifier systems (CS). The GAs and SA aim at 2. THE BOOK
systemized random search and derivative-free op-
timization [9,10]. The GP is used in the automatic The present book by Karry and De Silva [22] joins
production of computer programs [11]. The CS, the category of books that deal with NN, FL, and
consisting of message and rule systems, credit as- their combinations such as [23–26], whereas there
signment system and GA, are based on machine are other books that deal with NN, FL, GA, SA
learning which deals with building computer pro- and their combinations [7, 13, 15, 27–30].
grams that change depending upon the environ- The book focuses on subjects of FL, NNs, EC,
ment or experience [12]. Often, GP and CS are intelligent machines, and intelligent control. The
considered as special cases of GA and not as spe- book is composed of four parts, each consisting of
cial cases of EC [13]. The EP is an approach to AI chapters.
making use of finite states automata [14]. The PR
provides decision analysis and management of * Part I: Fuzzy Logic and Fuzzy Control
uncertainty. These various methodologies are syn- * Chapter 1: Introduction to Intelligent
ergetic and complementary rather than competi- Systems and Soft Computing
tive and hence are frequently used in combination * Chapter 2: Fundamentals of Fuzzy Logic
leading to some kind of hybrid systems. One such Systems
very useful and promising integrating technology * Chapter 3: Fuzzy Logic Control
emanates from ‘neuro-fuzzy’ or ‘fuzzy-neuro’ * Part II: Connections in Modeling and
systems, although other forms such as fuzzy- Neural Networks
genetic, neuro-genetic, or neurofuzzy-genetic are * Chapter 4: Fundamentals of Neural
continuously evolving [15]. Networks
There are specific books that deal with SC and * Chapter 5: Major Classes of Neural
its applications in general [16–19] and to specific Networks

Copyright # 2006 John Wiley & Sons, Ltd. Int. J. Robust Nonlinear Control 2006; 16:547–551
550 BOOK REVIEWS

* Chapter 6: Dynamic Neural Networks 4. Another useful feature of this book is the
and their Applications to Control and case studies and application spectrum dis-
Chaos Prediction cussed exclusively in separate chapters.
* Chapter 7: Neuro-Fuzzy Systems 5. Another regular feature that is incorporated
* Part III: Evolutionary and Soft Computing now-a-days in most of the books is the
* Chapter 8: Evolutionary Computing integration of some kind of simulation
* Part IV: Applications and Case Studies software and this book used the academia-
* Chapter 9: Soft Computing for Soft
standard MATLAB1 :
Machine Design 6. The book provides an extensive bibliogra-
* Chapter 10: Tools of Soft Computing in
phy at the end of each chapter for further
Real-World Applications study.
7. Finally, this reviewer, having used the book
by Jang et al. [28], is tempted to consider
A brief summary of these four parts of the book
using the present book [22] accompanied by
follows. Part I focusing on FL and FL
a Solutions Manual, for graduate course on
control starts with an introduction to intelligent
Intelligent Control Systems, at Idaho State
systems and SC and focuses on fundamentals
University.
of FL and its operations, fuzzification, defuzzi-
fication, fuzzy control architectures and robust- The book can be used without much background
ness and stability related to fuzzy dynamical material for senior and/or graduate students in-
systems. The field of NNs is the focus of Part II terested in knowing fundamental aspects of the
discussing basics of NNs, classes of NN (such fields of NNs, and FL within the broader disci-
as radial basis function networks, Kohonen’s pline of intelligent control systems. On the whole,
networks, Hopfield network), recurrent NNs, the present book is a welcome addition to the
applications to identification and control, and developing field of SC.
chaos. Also focused in this part is the important
topic of neuro-fuzzy architectures. Under Part III,
the authors discuss the topics under EC such as REFERENCES
GAs, fusion of GAs with NNs and with FL. The 1. De Silva CW (ed.). Intelligent Machines: Myths and
important topics of applications and case studies Realities. CRC Press: Boca Raton, FL, 2000.
is covered under the final Part IV. Some of the 2. Bradley DA, Seward D, Dawson D, Burge S.
interesting applications include controller tuning, Mechatronics and the Design of Intelligent Machines
and Systems. Stanley Thornes (Publishers) Ltd.:
supervisory control of a fish processing machine,
Cheltenham, U.K., 2000.
direct-current (DC) motor control, CDMA 3. Meystel AM, Albus JS (eds). Intelligent Systems:
cellular system, and asynchronous transfer Architecture, Design, and Control. Wiley Series on
mode (ATM). Intelligent Systems, vol. 1. Wiley: New York, NY,
Here are some comments by this reviewer. 2002.
4. Ham FM, Kostanic I. Principles of Neurocomputing
for Science and Engineering. McGraw-Hall Inc.:
New York, NY, 2001.
1. The field of SC is rapidly changing and 5. Chen G, Pham TT. Introduction to Fuzzy Sets, Fuzzy
this book captures recent developments Logic, and Fuzzy Control Systems. CRC Press: Boca
integrating theory, tools or techniques and Raton, FL, 2001.
applications. 6. Darwin C. The Origins of Species. John Murray:
2. Another distinguishing feature of this book London, U.K., 1859.
7. Tettamanzi A, Tomassini M. Soft Computing:
is the style of presentation, it is simple, con- Integrating Evolutionary, Neural, and Fuzzy Sys-
cise and easy to read and understand, and tems. Springer: Berlin, Germany, 2001.
the book is written ‘for the benefit of the 8. Back T. Evolutionary Algorithms in Theory and
student’. Practice. Oxford University Press: Oxford, U.K.,
1996.
3. There is lot of thought that went into pre- 9. Holland JH. Adaptation in Natural and Artificial
paring the examples, end-of-chapter prob- Systems. The University of Michigan Press: Ann
lems and references, exercises, and projects. Arbor, MI, 1975.

Copyright # 2006 John Wiley & Sons, Ltd. Int. J. Robust Nonlinear Control 2006; 16:547–551
 BOOK REVIEWS 551

10. Gen M, Cheng R. Genetic Algorithms and Engineer- Intelligence. Prentice-Hall: Englewood Cliffs, NJ,
ing Design. Wiley: New York, NY, 1997. 1992.
11. Langdon WB, Poli R. Foundations of Genetic 24. Cai Z-X. Intelligent Control: Principles, Techniques
Programming. Springer: Berlin, Germany, 2002. and Applications. World Scientific: Singapore, 1997.
12. Goldberg DE. Genetic Algorithms in Search, 25. Hines JW. MATLAB Supplement to Fuzzy and
Optimization and Machine Learning. Addison- Neural Approaches in Engineering. Wiley: New
Wesley: Reading, MA, 1989. York, NY, 1997 (Companion to Fuzzy and Neural
13. King RE. Computational Intelligence in Control En- Approaches to Engineering by L. H. Tsoukalas and
gineering. Marcel Dekker Inc.: New York, NY, 1999. R. E. Uhrig).
14. Fogel LJ, Owens AJ, Walsh MJ. Artificial 26. Lewis FL, Campos J, Selmic R. Neuro-Fuzzy
Intelligence Through Simulated Evolution. Wiley: Control of Industrial Systems with Actuator Non-
New York, NY, 1966. linearities. Society of Industrial and Applied
15. Tsoukalas LH, Uhrig RE. Fuzzy and Neural Ap- Mathematics (SIAM): Philadelphia, PA, 2002.
proaches in Engineering. Wiley: New York, NY, 1997. 27. Lin C-T, Lee CS. Neural Fuzzy Systems:
16. Sinha NK, Gupta MM (eds). Soft Computing A Neuro-Fuzzy Synergism to Intelligent Systems.
and Intelligent Systems: Theory and Applications. Prentice-Hall Inc.: Upper Saddle River, NJ,
Academic Press: San Diego, CA, 2000. 1996.
17. Leondes CT (ed.). Fuzzy Theory Systems: 28. Jang J-SR, Sun C-T, Mizutani E. Neuro-Fuzzy and
Techniques and Applications, vols. 1–4. Academic Soft Computing: A Computational Approach to
Press: San Diego, CA, 1999 (Four Volume Set). Learning and Machine Intelligence. Prentice-Hall
18. Ruano AE (ed.). Intelligent Control Systems Using PTR: Upper Saddle River, NJ, 1997.
Computational Intelligent Techniques. The Institu- 29. Zilouchian A, Jamshidi M (eds). Intelligent Control
tion of Electrical Engineers: Stevenage, Herts, U.K., Systems Using Soft Computing Methodologies. CRC
2005. Press: Boca Raton, FL, 2001.
19. Konoar A. Computational Intelligence: Principles, 30. Nguyen HT, Prasad NR, Walker CL, Walker EA. A
Techniques and Applications. Springer: Berlin, First Course in Fuzzy and Neural Control. Chapman
Germany, 2005. & Hall/CRC: Boca Raton, FL, 2003.
20. Cirstea MN, Dinu A, Khor JG, McMormick M.
Neural and Fuzzy Logic Control of Drives and Power
Systems. Elsevier Science: Oxford, U.K., 2002. D. SUBBARAM NAIDU
21. Stavroulakis P (ed.). Neuro-Fuzzy and Fuzzy-Neural Measurement and Control Engineering
Applications in Telecommunications. Springer: Research Center,
Berlin, Germany, 2004. Idaho State University,
22. Karry FO, De Silva C. Soft Computing and Intelli-
gent Systems Design: Theory, Tools and Applications. Pocatello, ID 83209-8060, U.S.A.
Pearson, Addison-Wesley: New York, NY, 2004. E-mail: [email protected]
23. Kosko B. Neural Networks and Fuzzy Systems:
A Dynamical Systems Approach to Machine (DOI: 10.1002/rnc.1072)

Copyright # 2006 John Wiley & Sons, Ltd. Int. J. Robust Nonlinear Control 2006; 16:547–551