In regression the objective is to determine an appropriate function which reflects reality as accurate as possible but also eliminates irregularities from data noise and is therefore easy to interpret. A popular and flexible approach for estimating the true underlying function is the additive model. One possible approach for fitting additive models is the expansion in B-splines which allows direct calculation of the estimators. If the number of B-splines is too large the estimated functions become wiggly and tend to be very close to the observed data. To avoid this problem of overfitting we use a penalization approach characterized by smoothing parameters. In this thesis we propose the use of genetic algorithms for smoothing parameter optimization. Genetic algorithms are rarely applied in the field of statistics and refer to the principle that better adapted individuals win against their competitors under equal conditions. Apart from smoothing parameter optimization the user often faces datasets containing large numbers of relevant and irrelevant explanatory variables. Appropriate variable selection approaches allow to reduce the number of variables to subsets of relevant variables. We propose to consider the problems of variable selection and choice of smoothing parameters simultaneously by using genetic algorithms. Our approach bases on an appropriate combination of the genetic algorithms for smoothing parameter optimization and variable selection.

• Real-world problems can be high-dimensional, complex, and noisy • More data does not imply more information • Different approaches deal with the so-called curse of dimensionality to reduce irrelevant information • A process with multidimensional information is not necessarily easy to interpret nor process • In some real-world applications, the number of elements of a class is clearly lower than the other. The models tend to assume that the importance of the analysis belongs to the majority class and this is not usually the truth • The analysis of complex diseases such as cancer are focused on more-than-one dimensional omic data • The increasing amount of data thanks to the reduction of cost of the high-throughput experiments opens up a new era for integrative data-driven approaches • Entropy-based approaches are of interest to reduce the dimensionality of high-dimensional data

This book introduces readers to genetic algorithms (GAs) with an emphasis on making the concepts, algorithms, and applications discussed as easy to understand as possible. Further, it avoids a great deal of formalisms and thus opens the subject to a broader audience in comparison to manuscripts overloaded by notations and equations. The book is divided into three parts, the first of which provides an introduction to GAs, starting with basic concepts like evolutionary operators and continuing with an overview of strategies for tuning and controlling parameters. In turn, the second part focuses on solution space variants like multimodal, constrained, and multi-objective solution spaces. Lastly, the third part briefly introduces theoretical tools for GAs, the intersections and hybridizations with machine learning, and highlights selected promising applications.

This book constitutes the refereed proceedings of the 9th International Workshop on Structural and Syntctic Pattern Recognition, SSPR 2002 and the 4th International Workshop on Statistical Techniques in Pattern Recognition, SPR 2002 held jointly in Windsor, Ontario, Canada in August 2002. The 45 revised full papers and 35 poster papers presented together with three invited papers were carefully reviewed and selected from 116 submissions. The papers are organized in topical sections on graphs, grammars, and languages; graphs, strings, and grammars; documents and OCR; image shape analysis and application; density estimation and distribution models; multi classifiers and fusion; feature extraction and selection; general methodology; and image shape analysis and application.

Foundations of Genetic Algorithms 1991 (FOGA 1) discusses the theoretical foundations of genetic algorithms (GA) and classifier systems. This book compiles research papers on selection and convergence, coding and representation, problem hardness, deception, classifier system design, variation and recombination, parallelization, and population divergence. Other topics include the non-uniform Walsh-schema transform; spurious correlations and premature convergence in genetic algorithms; and variable default hierarchy separation in a classifier system. The grammar-based genetic algorithm; conditions for implicit parallelism; and analysis of multi-point crossover are also elaborated. This text likewise covers the genetic algorithms for real parameter optimization and isomorphisms of genetic algorithms. This publication is a good reference for students and researchers interested in genetic algorithms.

This proposed text appears to be a good introduction to evolutionary computation for use in applied statistics research. The authors draw from a vast base of knowledge about the current literature in both the design of evolutionary algorithms and statistical techniques. Modern statistical research is on the threshold of solving increasingly complex problems in high dimensions, and the generalization of its methodology to parameters whose estimators do not follow mathematically simple distributions is underway. Many of these challenges involve optimizing functions for which analytic solutions are infeasible. Evolutionary algorithms represent a powerful and easily understood means of approximating the optimum value in a variety of settings. The proposed text seeks to guide readers through the crucial issues of optimization problems in statistical settings and the implementation of tailored methods (including both stand-alone evolutionary algorithms and hybrid crosses of these procedures with standard statistical algorithms like Metropolis-Hastings) in a variety of applications. This book would serve as an excellent reference work for statistical researchers at an advanced graduate level or beyond, particularly those with a strong background in computer science.

Genetic Algorithms: Principles and Perspectives: A Guide to GA Theory is a survey of some important theoretical contributions, many of which have been proposed and developed in the Foundations of Genetic Algorithms series of workshops. However, this theoretical work is still rather fragmented, and the authors believe that it is the right time to provide the field with a systematic presentation of the current state of theory in the form of a set of theoretical perspectives. The authors do this in the interest of providing students and researchers with a balanced foundational survey of some recent research on GAs. The scope of the book includes chapter-length discussions of Basic Principles, Schema Theory, "No Free Lunch", GAs and Markov Processes, Dynamical Systems Model, Statistical Mechanics Approximations, Predicting GA Performance, Landscapes and Test Problems.