Muutke küpsiste eelistusi

Soft Computing in Water Resources Engineering: Artifical Neural Networks, Fuzzy Logic and Genetic Algorithms [Kõva köide]

3.00/5 (2 hinnangut Goodreads-ist)
  • Formaat: Hardback, 288 pages, kõrgus x laius: 230x155 mm, Illustrations
  • Ilmumisaeg: 07-Dec-2011
  • Kirjastus: WIT Press
  • ISBN-10: 1845646363
  • ISBN-13: 9781845646363
Teised raamatud teemal:
Soft Computing in Water Resources Engineering: Artifical Neural Networks, Fuzzy Logic and Genetic AlgorithmsSuurem pilt
  • Formaat: Hardback, 288 pages, kõrgus x laius: 230x155 mm, Illustrations
  • Ilmumisaeg: 07-Dec-2011
  • Kirjastus: WIT Press
  • ISBN-10: 1845646363
  • ISBN-13: 9781845646363
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781845646363.html
Märksõnad:
Engineers have attempted to solve water resources engineering problems with the help of empirical, regression-based and numerical models. Empirical models are not universal, nor are regression-based models. The numerical models are, on the other hand, physics-based but require substantial data measurement and parameter estimation. Hence, there is a need to employ models that are robust, user-friendly, and practical and that do not have the shortcomings of the existing methods. Artificial intelligence methods meet this need. Soft Computing in Water Resources Engineering introduces the basics of artificial neural networks (ANN), fuzzy logic (FL) and genetic algorithms (GA). It gives details on the feed forward back propagation algorithm and also introduces neuro-fuzzy modelling to readers. Artificial intelligence method applications covered in the book include predicting and forecasting floods, predicting suspended sediment, predicting event-based flow hydrographs and sedimentographs, locating seepage path in an earth-fill dam body, and the predicting dispersion coefficient in natural channels.The author also provides an analysis comparing the artificial intelligence models and contemporary non-artificial intelligence methods (empirical, numerical, regression, etc. ). The ANN, FL, and GA are fairly new methods in water resources engineering. The first publications appeared in the early 1990s and quite a few studies followed in the early 2000s. Although these methods are currently widely known in journal publications, they are still very new for many scientific readers and they are totally new for students, especially undergraduates. Numerical methods were first taught at the graduate level but are now taught at the undergraduate level. There are already a few graduate courses developed on AI methods in engineering and included in the graduate curriculum of some universities. It is expected that these courses, too, will soon be taught at the undergraduate levels.
Preface xv
Part I Artificial Neural Networks
Chapter 1 Introduction to Artificial Neural Networks
3(10)
1.1 General View
3(1)
1.2 Biological Neuron
4(1)
1.3 Artificial Neuron
5(1)
1.4 Artificial Neural Network
6(2)
1.4.1 History
6(1)
1.4.2 General Properties of ANN
7(1)
1.5 ANN Types
8(1)
1.5.1 Architecture
8(1)
1.5.2 Neuro-dynamics
9(1)
1.6 ANN versus Other Models
9(4)
Chapter 2 Artificial Neuron
13(12)
2.1 Components of Artificial Neuron
13(2)
2.2 Methods for Computing Net Information
15(1)
2.2.1 Summation (P) method
16(1)
2.2.2 Maximum (max) method
16(1)
2.2.3 Minimum (min) method
16(1)
2.2.4 Product (Q) method
16(1)
2.3 Activation Functions
16(9)
2.3.1 Linear function
17(1)
2.3.2 Step function
17(2)
2.3.3 Rampage function
19(1)
2.3.4 Gaussian function
20(1)
2.3.5 Sigmoid function
20(2)
2.3.6 Hyperbolic tangent function
22(3)
Chapter 3 Network Training
25(30)
3.1 Pre-Training Procedures
25(4)
3.1.1 Data Standardization
25(3)
3.1.1.1 Standardization methods when using sigmoid function
26(2)
3.1.1.2 Standardization methods when using hyperbolic tangent function
28(1)
3.1.2 Network Initialization
28(1)
3.2 Network Training
29(18)
3.2.1 Back-propagation algorithm
30(12)
3.2.1.1 Updating weights in output-inner layers
33(1)
3.2.1.2 Updating weights in inner-input layers
34(1)
3.2.1.3 Worked examples
35(7)
3.2.2 Radial basis function
42(2)
3.2.3 Conjugate gradient algorithm
44(1)
3.2.4 Cascade correlation algorithm
45(1)
3.2.5 Generalized regression algorithm
46(1)
3.3 Learning Rules
47(1)
3.4 Learning Parameter
48(4)
Appendix
52(1)
Exercise Problem
53(2)
Chapter 4 Model Testing
55(6)
4.1 De-standardization of Model Output
55(1)
4.2 Evaluating Model Performance
55(4)
4.3 Over-training and Cross-training
59(2)
Chapter 5 Model Application in Water Resources Engineering
61(48)
5.1 Prediction
61(27)
5.1.1 Total suspended sediment
61(6)
5.1.2 Seepage
67(7)
5.1.3 Dispersion coefficient
74(3)
5.1.4 Sheet sediment
77(2)
5.1.5 Runoff at plot scale
79(2)
5.1.6 Runoff at watershed scale
81(2)
5.1.7 Flood hydrograph at basin scale
83(5)
5.2 Classification
88(1)
5.3 Forecasting
89(6)
5.3.1 Forecasting flood hydrograph at basin scale
89(6)
5.4 Extrapolation
95(1)
5.5 Filling Gap in Time Series Data
96(4)
References
100(9)
Part II Fuzzy Logic Algorithm
Chapter 6 Introduction to Fuzzy Logic Algorithm
109(6)
6.1 General View
109(1)
6.2 Basic Concept in Fuzzy Logic
110(2)
6.3 Fuzzy Systems
112(3)
Chapter 7 Fuzzy Membership Functions, Set Operations, and Fuzzy Relations
115(20)
7.1 Fuzzy Membership Functions
115(3)
7.2 Fuzzy Set Operations
118(10)
7.2.1 Set representation
118(1)
7.2.2 Set operations
119(6)
7.2.2.1 Union of sets
119(1)
7.2.2.2 Intersection of sets
120(2)
7.2.2.3 Complementary sets
122(1)
7.2.2.4 Subsets
122(2)
7.2.2.5 Operation properties of fuzzy sets
124(1)
7.2.3 Operations unique to fuzzy sets
125(15)
7.2.3.1 Concentration
125(1)
7.2.3.2 Dilation
125(1)
7.2.3.3 Normalization
126(1)
7.2.3.4 Intensification
127(1)
7.3 Fuzzy Relations
128(4)
Exercise Questions
132(3)
Chapter 8 Constructing Fuzzy Model
135(16)
8.1 Fuzzification
135(2)
8.2 Fuzzy Rule Base
137(3)
8.3 Fuzzy Inference Engine
140(6)
8.3.1 Inference sub-process
140(5)
8.3.2 Composition sub-process
145(1)
8.4 Defuzzification
146(4)
Exercise Questions
150(1)
Chapter 9 Fuzzy Model Application in Water Resources Engineering
151(34)
9.1 Introduction
151(1)
9.2 TSS Prediction
152(5)
9.2.1 Model development
154(1)
9.2.2 Model calibration and application
155(2)
9.3 Sheet Sediment Prediction
157(7)
9.3.1 Fuzzy model
157(4)
9.3.2 Physics-based model
161(2)
9.3.3 ANN model
163(1)
9.4 Peak Discharge Prediction
164(4)
9.4.1 Experimental data
164(1)
9.4.2 ANN model training and testing
164(1)
9.4.3 FL model calibration and validation
164(2)
9.4.4 KWA model calibration and validation
166(2)
9.5 Runoff Hydrograph Simulation
168(3)
9.5.1 ANN model training and testing
168(2)
9.5.2 FL model calibration and validation
170(1)
9.5.3 KWA model calibration and verification
170(1)
9.6 Hydrograph Simulation at Watershed Scale
171(1)
9.7 Dispersion Prediction
172(7)
9.7.1 Experimental data
173(3)
9.7.2 Regression-based model
176(1)
9.7.3 Fuzzy model
177(2)
References
179(6)
Part III Genetic Algorithms
Chapter 10 Genetic Algorithms (GAS)
185(18)
10.1 Introduction
185(1)
10.2 Basic Units of GA
186(2)
10.3 GA Operations
188(15)
10.3.1 Forming initial gene pool
189(1)
10.3.2 Evaluating fitness of each chromosome
190(2)
10.3.3 Selection
192(1)
10.3.4 Cross-over operation
193(3)
10.3.4.1 Single cut
194(1)
10.3.4.2 Double cut
195(1)
10.3.4.3 Multiple cut
195(1)
10.3.4.4 Uniform crossing
195(1)
10.3.4.5 Using sub-chromosome
195(1)
10.3.4.6 Reversing
196(1)
10.3.5 Mutation
196(7)
Chapter 11 Variant of Genetic Algorithm
203(18)
11.1 Variant of Genetic Algorithms
203(8)
11.1.1 Responsive perturbation algorithm
204(1)
11.1.2 Trait-based heterogeneous populations (TUT)
205(2)
11.1.3 Trait-based heterogeneous populations plus (TbHP+)
207(4)
11.2 Test Functions
211(6)
11.3 Model Testing
217(4)
Chapter 12 Genetic Algorithm Model Applications in Water Resources Engineering
221(42)
12.1 GA Application Problems
221(36)
12.1.1 Longitudinal dispersion coefficient in natural streams
221(10)
12.1.2 Hydrograph simulation
231(9)
12.1.2.1 Watershed and hydrologic data
231(4)
12.1.2.2 GA-RCM model implementation and calibration
235(1)
12.2.2.3 Hydrograph predictions
236(4)
12.1.3 Sensitivity analysis
240(6)
12.1.3.1 Number of events used in calibration
240(2)
12.1.3.2 Using shorter wave travel time events in the calibration
242(1)
12.1.3.3 Using lower peak events in calibration
243(3)
12.1.4 Hydrograph simulation using level data
246(4)
12.1.4.1 Hydrograph predictions
247(3)
12.1.5 Mean and bankfull discharge prediction
250(7)
12.1.5.1 Non-linear regression method
251(1)
12.1.5.2 Artificial neural networks method
251(1)
12.1.5.3 Fuzzy method
252(1)
12.1.5.4 Genetic algorithm
253(4)
Appendix
257(2)
References
259(4)
Index 263
Prof. Dr. Gokmen TAYFUR is an associate professor in the Civil Engineeirng Department at the Izmir Institute of Technology where he teaches graduate course on numerical methods in engineering, artificial intelligence methods in engineering, hydrology and hydraulics, and non-point source pollution. He also teaches undergraduate courses on numerical methods and analysis in engineering, He received his Ph.D. and MS degrees from the University of California in Davis. And his undergraduate degree from Istanbul Technical University. His research interests include Surface and subsurface flows; Rainfall-runoff induced erosion/sediment transport , Solute transport in saturated and unsaturated zone; Solute transport by surface flows; and Application of artificial intelligence methods in water resources engineering and water quality. He has written numerous conference and journal papers and research reports on those topics.