This book provides theoretical and practical knowledge about a methodology for evolutionary algorithm-based search strategy with the integration of several machine learning and deep learning techniques. These include convolutional neural networks, Gröbner bases, relevance vector machines, transfer learning, bagging and boosting methods, clustering techniques (affinity propagation), and belief networks, among others. The development of such tools contributes to better optimizing methodologies. Beginning with the essentials of evolutionary algorithms and covering interdisciplinary research topics, the contents of this book are valuable for different classes of readers: novice, intermediate, and also expert readers from related fields. Following the chapters on introduction and basic methods, Chapter 3 details a new research direction, i.e., neuro-evolution, an evolutionary method for the generation of deep neural networks, and also describes how evolutionary methods are extended in combination with machine learning techniques. Chapter 4 includes novel methods such as particle swarm optimization based on affinity propagation (PSOAP), and transfer learning for differential evolution (TRADE), another machine learning approach for extending differential evolution. The last chapter is dedicated to the state of the art in gene regulatory network (GRN) research as one of the most interesting and active research fields. The author describes an evolving reaction network, which expands the neuro-evolution methodology to produce a type of genetic network suitable for biochemical systems and has succeeded in designing genetic circuits in synthetic biology. The author also presents real-world GRN application to several artificial intelligent tasks, proposing a framework of motion generation by GRNs (MONGERN), which evolves GRNs to operate a real humanoid robot.
Author: Khosrow-Pour, D.B.A., Mehdi
Publisher: IGI Global
Release Date: 2017-06-20
In recent years, our world has experienced a profound shift and progression in available computing and knowledge sharing innovations. These emerging advancements have developed at a rapid pace, disseminating into and affecting numerous aspects of contemporary society. This has created a pivotal need for an innovative compendium encompassing the latest trends, concepts, and issues surrounding this relevant discipline area. During the past 15 years, the Encyclopedia of Information Science and Technology has become recognized as one of the landmark sources of the latest knowledge and discoveries in this discipline. The Encyclopedia of Information Science and Technology, Fourth Edition is a 10-volume set which includes 705 original and previously unpublished research articles covering a full range of perspectives, applications, and techniques contributed by thousands of experts and researchers from around the globe. This authoritative encyclopedia is an all-encompassing, well-established reference source that is ideally designed to disseminate the most forward-thinking and diverse research findings. With critical perspectives on the impact of information science management and new technologies in modern settings, including but not limited to computer science, education, healthcare, government, engineering, business, and natural and physical sciences, it is a pivotal and relevant source of knowledge that will benefit every professional within the field of information science and technology and is an invaluable addition to every academic and corporate library.
Author: Björn H. Junker
Publisher: John Wiley & Sons
Release Date: 2011-09-20
An introduction to biological networks and methods for theiranalysis Analysis of Biological Networks is the first book of itskind to provide readers with a comprehensive introduction to thestructural analysis of biological networks at the interface ofbiology and computer science. The book begins with a brief overviewof biological networks and graph theory/graph algorithms and goeson to explore: global network properties, network centralities,network motifs, network clustering, Petri nets, signal transductionand gene regulation networks, protein interaction networks,metabolic networks, phylogenetic networks, ecological networks, andcorrelation networks. Analysis of Biological Networks is a self-containedintroduction to this important research topic, assumes no expertknowledge in computer science or biology, and is accessible toprofessionals and students alike. Each chapter concludes with asummary of main points and with exercises for readers to test theirunderstanding of the material presented. Additionally, an FTP sitewith links to author-provided data for the book is available fordeeper study. This book is suitable as a resource for researchers in computerscience, biology, bioinformatics, advanced biochemistry, and thelife sciences, and also serves as an ideal reference text forgraduate-level courses in bioinformatics and biologicalresearch.
Author: Ion Mandoiu
Publisher: John Wiley & Sons
Release Date: 2008-02-15
Presents algorithmic techniques for solving problems in bioinformatics, including applications that shed new light on molecular biology This book introduces algorithmic techniques in bioinformatics, emphasizing their application to solving novel problems in post-genomic molecular biology. Beginning with a thought-provoking discussion on the role of algorithms in twenty-first-century bioinformatics education, Bioinformatics Algorithms covers: General algorithmic techniques, including dynamic programming, graph-theoretical methods, hidden Markov models, the fast Fourier transform, seeding, and approximation algorithms Algorithms and tools for genome and sequence analysis, including formal and approximate models for gene clusters, advanced algorithms for non-overlapping local alignments and genome tilings, multiplex PCR primer set selection, and sequence/network motif finding Microarray design and analysis, including algorithms for microarray physical design, missing value imputation, and meta-analysis of gene expression data Algorithmic issues arising in the analysis of genetic variation across human population, including computational inference of haplotypes from genotype data and disease association search in case/control epidemiologic studies Algorithmic approaches in structural and systems biology, including topological and structural classification in biochemistry, and prediction of protein-protein and domain-domain interactions Each chapter begins with a self-contained introduction to a computational problem; continues with a brief review of the existing literature on the subject and an in-depth description of recent algorithmic and methodological developments; and concludes with a brief experimental study and a discussion of open research challenges. This clear and approachable presentation makes the book appropriate for researchers, practitioners, and graduate students alike.
High-throughput sequencing and functional genomics technologies have given us a draft human genome sequence and have enabled large-scale genotyping and gene expression profiling of human populations. Databases containing large numbers of sequences, polymorphisms, and gene expression profiles of normal and diseased tissues in different clinical states are rapidly being generated for human and model organisms. Bioinformatics is thus rapidly growing in importance in the annotation of genomic sequences, in the understanding of the interplay between genes and proteins, in the analysis of the genetic variability of species, and so on. This proceedings contains an up-to-date exchange of knowledge, ideas, and solutions to conceptual and practical issues of bioinformatics, by researchers, professionals, and industrial practitioners at the 4th Asia-Pacific Bioinformatics Conference held in Taipei in February 2006.
Author: Leandro N. De Castro
Publisher: IGI Global
Release Date: 2005
Recent Developments in Biologically Inspired Computing is necessary reading for undergraduate and graduate students, and researchers interested in knowing the most recent advances in problem solving techniques inspired by nature. This book covers the most relevant areas in computational intelligence, including evolutionary algorithms, artificial neural networks, artificial immune systems and swarm systems. It also brings together novel and philosophical trends in the exciting fields of artificial life and robotics. This book has the advantage of covering a large number of computational approaches, presenting the state-of-the-art before entering into the details of specific extensions and new developments. Pseudocodes, flow charts and examples of applications are provided so as to help newcomers and mature researchers to get the point of the new approaches presented.
Author: Matthias Dehmer
Publisher: John Wiley & Sons
Release Date: 2012-06-26
Explore the multidisciplinary nature of complex networksthrough machine learning techniques Statistical and Machine Learning Approaches for NetworkAnalysis provides an accessible framework for structurallyanalyzing graphs by bringing together known and novel approaches ongraph classes and graph measures for classification. By providingdifferent approaches based on experimental data, the book uniquelysets itself apart from the current literature by exploring theapplication of machine learning techniques to various types ofcomplex networks. Comprised of chapters written by internationally renownedresearchers in the field of interdisciplinary network theory, thebook presents current and classical methods to analyze networksstatistically. Methods from machine learning, data mining, andinformation theory are strongly emphasized throughout. Real datasets are used to showcase the discussed methods and topics, whichinclude: A survey of computational approaches to reconstruct andpartition biological networks An introduction to complex networks—measures, statisticalproperties, and models Modeling for evolving biological networks The structure of an evolving random bipartite graph Density-based enumeration in structured data Hyponym extraction employing a weighted graph kernel Statistical and Machine Learning Approaches for NetworkAnalysis is an excellent supplemental text for graduate-level,cross-disciplinary courses in applied discrete mathematics,bioinformatics, pattern recognition, and computer science. The bookis also a valuable reference for researchers and practitioners inthe fields of applied discrete mathematics, machine learning, datamining, and biostatistics.