Soft Computing Approaches In Chemistry

The contributions to this book cover a wide range of applications of Soft Computing to the chemical domain. The early roots of Soft Computing can be traced back to Lotfi Zadeh's work on soft data analysis [1] published in 1981. 'Soft Computing' itself became fully established about 10 years later, when the Berkeley Initiative in Soft Computing (SISC), an industrial liaison program, was put in place at the University of California - Berkeley. Soft Computing applications are characterized by their ability to: • approximate many different kinds of real-world systems; • tolerate imprecision, partial truth, and uncertainty; and • learn from their environment. Such characteristics commonly lead to a better ability to match reality than other approaches can provide, generating solutions of low cost, high robustness, and tractability. Zadeh has argued that soft computing provides a solid foundation for the conception, design, and application of intelligent systems employing its methodologies symbiotically rather than in isolation. There exists an implicit commitment to take advantage of the fusion of the various methodologies, since such a fusion can lead to combinations that may provide performance well beyond that offered by any single technique.

This book can be regarded as 'Soft computing for physicists and chemists self-taught'. It prepares the readers with a solid background of soft computing and how to adapt soft computing techniques to problem solving in physical and chemical research. Soft computing methods have been little explored by researchers in physical and chemical sciences primarily because of the absence of books that bridge the gap between the traditional computing paradigm pursued by researchers in science and the new soft computing paradigm that has emerged in computer science. This book is the interface between these primary sources and researchers in physics and chemistry.

"This publication presents a series of practical applications of different Soft Computing techniques to real-world problems, showing the enormous potential of these techniques in solving problems"--Provided by publisher.

An in-depth look at soft computing methods and their applications in the human sciences, such as the social and the behavioral sciences. Soft computing methods - including fuzzy systems, neural networks, evolutionary computing and probabilistic reasoning - are state-of-the-art methods in theory formation and model construction. The powerful application areas of these methods in the human sciences are demonstrated, including the replacement of statistical models by simpler numerical or linguistic soft computing models and the use of computer simulations with approximate and linguistic constituents. "Dr. Niskanen's work opens new vistas in application of soft computing, fuzzy logic and fuzzy set theory to the human sciences. This book is likely to be viewed in retrospect as a landmark in its field" (Lotfi A. Zadeh, Berkeley)

The book provides a platform for dealing with the flaws and failings of the soft computing paradigm through different manifestations. The different chapters highlight the necessity of the hybrid soft computing methodology in general with emphasis on several application perspectives in particular. Typical examples include (a) Study of Economic Load Dispatch by Various Hybrid Optimization Techniques, (b) An Application of Color Magnetic Resonance Brain Image Segmentation by Para Optimus LG Activation Function, (c) Hybrid Rough-PSO Approach in Remote Sensing Imagery Analysis, (d) A Study and Analysis of Hybrid Intelligent Techniques for Breast Cancer Detection using Breast Thermograms, and (e) Hybridization of 2D-3D Images for Human Face Recognition. The elaborate findings of the chapters enhance the exhibition of the hybrid soft computing paradigm in the field of intelligent computing.

This volume provides a collection of sixteen articles containing review and new material. In a unified way, they describe the recent development of theories and methodologies in pattern recognition, image processing and vision using fuzzy logic, artificial neural networks, genetic algorithms, rough sets and wavelets with significant real life applications. The book details the theory of granular computing and the role of a rough-neuro approach as a way of computing with words and designing intelligent recognition systems. It also demonstrates applications of the soft computing paradigm to case based reasoning, data mining and bio-informatics with a scope for future research. The contributors from around the world present a balanced mixture of current theory, algorithms and applications, making the book an extremely useful resource for students and researchers alike. Contents: Pattern Recognition: Multiple Classifier Systems; Building Decision Trees from the Fourier Spectrum of a Tree Ensemble; Clustering Large Data Sets; Multi-objective Variable String Genetic Classifier: Application to Remote Sensing Imagery; Image Processing and Vision: Dissimilarity Measures Between Fuzzy Sets or Fuzzy Structures; Early Vision: Concepts and Algorithms; Self-organizing Neural Network for Multi-level Image Segmentation; Geometric Transformation by Moment Method with Wavelet Matrix; New Computationally Efficient Algorithms for Video Coding; Soft Computing for Computational Media Aesthetics: Analyzing Video Content for Meaning; Granular Computing and Case Based Reasoning: Towards Granular Multi-agent Systems; Granular Computing and Pattern Recognition; Case Base Maintenance: A Soft Computing Perspective; Real Life Applications: Autoassociative Neural Network Models for Pattern Recognition Tasks in Speech and Image; Protein Structure Prediction Using Soft Computing; Pattern Classification for Biological Data Mining. Readership: Upper level undergraduates, graduates, researchers, academics and industrialists.