skip to content
Artificial neural networks in biological and environmental analysis Preview this item
ClosePreview this item

Artificial neural networks in biological and environmental analysis

Author: Grady Hanrahan
Publisher: Boca Raton, FL : CRC Press, ©2011.
Series: Analytical chemistry series (CRC Press)
Edition/Format:   Print book : EnglishView all editions and formats
Summary:
"Drawing on the experience and knowledge of a practicing professional, this book provides a comprehensive introduction and practical guide to the development, optimization, and application of artificial neural networks (ANNs) in modern environmental and biological analysis. Based on our knowledge of the functioning human brain, ANNs serve as a modern paradigm for computing. Presenting basic principles of ANNs
You are not connected to the University of Cape Town Libraries network. Access to online content and services may require you to authenticate with your library. Off-campus access
Getting this item's online copy... Getting this item's online copy...

Find a copy in the library

Getting this item's location and availability... Getting this item's location and availability...

WorldCat

Find it in libraries globally
Worldwide libraries own this item

Details

Material Type: Internet resource
Document Type: Book, Internet Resource
All Authors / Contributors: Grady Hanrahan
ISBN: 9781439812587 1439812586
OCLC Number: 667210573
Description: xxii, 188 pages : illustrations (some color) ; 25 cm.
Contents: Machine generated contents note: ch. 1 Introduction --
1.1. Artificial Intelligence: Competing Approaches or Hybrid Intelligent Systems? --
1.2. Neural Networks: An Introduction and Brief History --
1.2.1. The Biological Model --
1.2.2. The Artificial Neuron Model --
1.3. Neural Network Application Areas --
1.4. Concluding Remarks --
References --
ch. 2 Network Architectures --
2.1. Neural Network Connectivity and Layer Arrangement --
2.2. Feedforward Neural Networks --
2.2.1. The Perceptron Revisited --
2.2.2. Radial Basis Function Neural Networks --
2.3. Recurrent Neural Networks --
2.3.1. The Hopfield Network --
2.3.2. Kohonen's Self-Organizing Map --
2.4. Concluding Remarks --
References --
ch. 3 Model Design and Selection Considerations --
3.1. In Search of the Appropriate Model --
3.2. Data Acquisition. 3.3. Data Preprocessing and Transformation Processes --
3.3.1. Handling Missing Values and Outliers --
3.3.2. Linear Scaling --
3.3.3. Autoscaling --
3.3.4. Logarithmic Scaling --
3.3.5. Principal Component Analysis --
3.3.6. Wavelet Transform Preprocessing --
3.4. Feature Selection --
3.5. Data Subset Selection --
3.5.1. Data Partitioning --
3.5.2. Dealing with Limited Data --
3.6. Neural Network Training --
3.6.1. Learning Rules --
3.6.2. Supervised Learning --
3.6.2.1. The Perceptron Learning Rule --
3.6.2.2. Gradient Descent and Back-Propagation --
3.6.2.3. The Delta Learning Rule --
3.6.2.4. Back-Propagation Learning Algorithm --
3.6.3. Unsupervised Learning and Self-Organization --
3.6.4. The Self Organizing Map --
3.6.5. Bayesian Learning Considerations --
3.7. Model Selection --
3.8. Model Validation and Sensitivity Analysis --
3.9. Concluding Remarks --
References. Ch. 4 Intelligent Neural Network Systems and Evolutionary Learning --
4.1. Hybrid Neural Systems --
4.2. An Introduction to Genetic Algorithms --
4.2.1. Initiation and Encoding --
4.2.1.1. Binary Encoding --
4.2.2. Fitness and Objective Function Evaluation --
4.2.3. Selection --
4.2.4. Crossover --
4.2.5. Mutation --
4.3. An Introduction to Fuzzy Concepts and Fuzzy Inference Systems --
4.3.1. Fuzzy Sets --
4.3.2. Fuzzy Inference and Function Approximation --
4.3.3. Fuzzy Indices and Evaluation of Environmental Conditions --
4.4. The Neural-Fuzzy Approach --
4.4.1. Genetic Algorithms in Designing Fuzzy Rule-Based Systems --
4.5. Hybrid Neural Network-Genetic Algorithm Approach --
4.6. Concluding Remarks --
References --
ch. 5 Applications in Biological and Biomedical Analysis --
5.1. Introduction --
5.2. Applications --
5.2.1. Enzymatic Activity --
5.2.2. Quantitative Structure-Activity Relationship (QSAR). 5.2.3. Psychological and Physical Treatment of Maladies --
5.2.4. Prediction of Peptide Separation --
5.3. Concluding Remarks --
References --
ch. 6 Applications in Environmental Analysis --
6.1. Introduction --
6.2. Applications --
6.2.1. Aquatic Modeling and Watershed Processes --
6.2.2. Endocrine Disruptors --
6.2.3. Ecotoxicity and Sediment Quality --
6.2.4. Modeling Pollution Emission Processes --
6.2.5. Partition Coefficient Prediction --
6.2.6. Neural Networks and the Evolution of Environmental Change / Kudlak --
6.2.6.1. Studies in the Lithosphere --
6.2.6.2. Studies in the Atmosphere --
6.2.6.3. Studies in the Hydrosphere --
6.2.6.4. Studies in the Biosphere --
6.2.6.5. Environmental Risk Assessment --
6.3. Concluding Remarks --
References.
Series Title: Analytical chemistry series (CRC Press)
Responsibility: Grady Hanrahan.

Abstract:

"Drawing on the experience and knowledge of a practicing professional, this book provides a comprehensive introduction and practical guide to the development, optimization, and application of artificial neural networks (ANNs) in modern environmental and biological analysis. Based on our knowledge of the functioning human brain, ANNs serve as a modern paradigm for computing. Presenting basic principles of ANNs together with simulated biological and environmental data sets and real applications in the field, this volume helps scientists comprehend the power of the ANN model to explain physical concepts and demonstrate complex natural processes"--Provided by publisher.

"The cornerstones of research into prospective tools of artificial intelligence originate from knowledge of the functioning brain. Like most transforming scientific endeavors, this field-- once viewed with speculation and doubt--has had profound impacts in helping investigators elucidate complex biological, chemical, and environmental processes. Such efforts have been catalyzed by the upsurge in computational power and availability, with the co-evolution of software, algorithms, and methodologies contributing significantly to this momentum. Whether or not the computational power of such techniques is sufficient for the design and construction of truly intelligent neural systems is of continued debate. In writing Artificial Neural Networks in Biological and Environmental Analysis, my aim was to provide in-depth and timely perspectives on the fundamental, technological, and applied aspects of computational neural networks. By presenting basic principles of neural networks together with real applications in the field, I seek to stimulate communication and partnership among scientists in the fields as diverse as biology, chemistry, mathematics, medicine, and environmental science. This interdisciplinary discourse is essential not only for the success of independent and collaborative research and teaching programs, but also for the continued acquiescence of the use of neural network tools in scientific inquiry"--Provided by publisher.

Retrieving notes about this item Retrieving notes about this item

Reviews

Editorial reviews

Publisher Synopsis

"...overall it is a concise and readable account of neural networks applied to biological and environmental systems. It combines fundamental, technical and applied aspects and encourages an Read more...

 
User-contributed reviews

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.