Artificial neural networks in biological and environmental analysis / Grady Hanrahan.

"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 knowled...

Full description

Saved in:
Bibliographic Details
Online Access: Full Text (via ProQuest)
Main Author: Hanrahan, Grady
Format: eBook
Language:English
Published: Boca Raton, FL : CRC Press, ©2011.
Series:Analytical chemistry series (CRC Press)
Subjects:
Table of 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.