Originating from models of biological neural systems, artificial neural networks (ANN) are the cornerstones of artificial intelligence research. Catalyzed by the upsurge in computational power and availability, and made widely accessible with the co-evolution of software, algorithms, and methodologies, artificial neural networks have had a profound impact in the elucidation of complex biological, chemical, and environmental processes.
Artificial Neural Networks in Biological and Environmental Analysis provides an in-depth and timely perspective on the fundamental, technological, and applied aspects of computational neural networks. Presenting the basic principles of neural networks together with applications in the field, the book stimulates communication and partnership among scientists in 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 interest in the use of neural network tools in scientific inquiry.
The book covers:
- A brief history of computational neural network models in relation to brain function
- Neural network operations, including neuron connectivity and layer arrangement
- Basic building blocks of model design, selection, and application from a statistical perspective
- Neurofuzzy systems, neuro-genetic systems, and neuro-fuzzy-genetic systems
- Function of neural networks in the study of complex natural processes
Scientists deal with very complicated systems, much of the inner workings of which are frequently unknown to researchers. Using only simple, linear mathematical methods, information that is needed to truly understand natural systems may be lost. The development of new algorithms to model such processes is needed, and ANNs can play a major role. Balancing basic principles and diverse applications, this text introduces newcomers to the field and reviews recent developments of interest to active neural network practitioners.
Table of Contents
Glossary of Acronyms
Artificial Intelligence: Competing Approaches or Hybrid Intelligent Systems?
Neural Networks: An Introduction and Brief History
Neural Network Application Areas
Neural Network Connectivity and Layer Arrangement
Feedforward Neural Networks
Recurrent Neural Networks
Model Design and Selection Considerations
Data Preprocessing and Transformation Processes
Data Subset Selection
Neural Network Training
Model Validation and Sensitivity Analysis
Intelligent Neural Network Systems and Evolutionary Learning
An Introduction to Genetic Algorithms
An Introduction to Fuzzy Concepts and Fuzzy
The Neural-Fuzzy Approach
Hybrid Neural Network-Genetic Algorithm Approach
Applications in Biological and Biomedical Analysis
Applications in Environmental Analysis
Appendix I: Review of Basic Matrix Notation and Operations
Appendix II: Cytochrome P450 (CYP450) Isoform Data Set Used in Michielan et al (2009)
Appendix III: A 143-Member VOC Data Set and Corresponding Observed and Predicted Values of Air-to-Blood Partition Coefficients
Grady Hanrahan received his Ph.D. in Environmental Analytical Chemistry from the University of Plymouth, UK. With experience in directing undergraduate and graduate research, he has taught in the fields of Analytical Chemistry and Environmental Science at California State University, Los Angeles and California Lutheran University. He has written or co-written numerous peer-reviewed technical papers and is the author and editor of four books detailing the use of modern chemometric and computational modeling techniques to solve complex biological and environmental problems.
"…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 interdisciplinary approach to extracting information from large and complex datasets."
—Paul Worsfold, University of Plymouth