Название: Fuzzy Systems Modeling in Environmental and Health Risk Assessment
Автор: Boris Faybishenko, Rehan Sadiq
Издательство: Wiley
Год: 2023
Страниц: 332
Язык: английский
Формат: pdf (true)
Размер: 15.8 MB

Fuzzy Systems Modeling in Environmental and Health Risk Assessment Demonstrates the successful application of fuzzy systems modeling to real-world environmental and health problems.

In Fuzzy Systems Modeling in Environmental and Health Risk Assessment, a team of distinguished researchers delivers an up-to-date collection of the most successful and innovative attempts to apply fuzzy logic to problems involving environmental risk assessment, healthcare decision-making, the management of water distribution networks, and the optimization of water treatment and waste management systems. By explaining both the theoretical and practical aspects of using fuzzy systems modeling methods to solve complex problems, analyze risks and optimize system performance, this handy guide maintains a strongly application-oriented perspective throughout, offering readers a practical treatment of a cutting-edge subject.

Since the pioneering work of Lotfi Zadeh, fuzzy logic (FL) analysis has been applied successfully in many scientific and real-life engineering situations, such as electrical, mechanical, civil, chemical, aerospace, agricultural, biomedical, computer, environmental, geological, industrial, as well as by mathematicians, computer software developers and researchers, natural scientists (biology, chemistry, earth science, and physics), medical researchers, social scientists (economics, management, political science, and psychology), public policy analysts, business analysts, and jurists. The methods of FL have proven to be extremely useful when dealing with environmental data, because environmental management and risk assessment activities are often based on limited, imprecise, or uncertain observations and numerical simulations. Environmental data are usually characterized by both highly aleatoric and epistemic uncertainties, which are intrinsically present in environmental problems. Aleatory uncertainty indicates that the system (or media) variables or parameters can be characterized by their probability distributions. Aleatory uncertainty is a naturally occurring phenomenon, and is not because of a lack of information. Therefore, aleatory uncertainty is irreducible. Examples of aleatory uncertainty are such measured variables as river discharge, precipitation, and traffic data, which can be described by probability distributions if sufficient information is available. If there is no sufficient information, these variables can be described using fuzzy numbers. Epistemic uncertainty indicates the lack of, or limited, knowledge about the real system or its models.

Dynamic neural networks are suggested in the replacement of static DNNs to facilitate dynamic learning for solving highly nonlinear problems. Thus, Deep Learning methods along with FL techniques provide better interpretability of the network, while solving complex real-world problems using fuzzy if–then inference rules. The introduction of fuzzy layers to the deep learning architecture can help exploit the powerful aggregation properties expressed through fuzzy methodologies, and can be used to represent fuzzified intermediate, or hidden, layers.

Readers will also find:

Comprehensive explorations of the practical applications of fuzzy systems modeling in environmental science
Practical advice on environmental quality assessments and human health risk analyses
In-depth case studies involving air and water pollution, solid waste, indoor swimming pool and landfill risk assessments, wastewater treatment, and more

Perfect for environmental engineers and scientists, Fuzzy Systems Modeling in Environmental and Health Risk Assessment will also benefit policy makers, computer scientists, mathematicians, and researchers and practitioners interested in applying soft computing theories to environmental problems.