Atjaunināt sīkdatņu piekrišanu

E-grāmata: Microwave Tomography: Global Optimization, Parallelization and Performance Evaluation

5.00/5 (2 ratings by Goodreads)
, , ,
  • Formāts: PDF+DRM
  • Izdošanas datums: 08-Jul-2014
  • Izdevniecība: Springer-Verlag New York Inc.
  • Valoda: eng
  • ISBN-13: 9781493907526
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 106,47 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Microwave Tomography: Global Optimization, Parallelization and Performance EvaluationPalielināt
  • Formāts: PDF+DRM
  • Izdošanas datums: 08-Jul-2014
  • Izdevniecība: Springer-Verlag New York Inc.
  • Valoda: eng
  • ISBN-13: 9781493907526
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This book provides a detailed overview on the use of global optimization and parallel computing in microwave tomography techniques. The book focuses on techniques that are based on global optimization and electromagnetic numerical methods. The authors provide parallelization techniques on homogeneous and heterogeneous computing architectures on high performance and general purpose futuristic computers. The book also discusses the multi-level optimization technique, hybrid genetic algorithm and its application in breast cancer imaging.
1 Introduction to Microwave Imaging
1(20)
1.1 Electromagnetic Imaging
1(1)
1.2 Microwave Imaging Methods
2(4)
1.2.1 Radar Approach
2(2)
1.2.2 Microwave Tomography
4(2)
1.3 Qualitative Linear Inversion
6(1)
1.4 Quantitative Nonlinear Inversion
6(3)
1.4.1 Forward Solver
7(1)
1.4.2 Iterative Approaches Without Using Forward Solver
8(1)
1.4.3 Iterative Approaches Using Forward Solver
9(1)
1.5 Deterministic Approaches Based on Local Optimization
9(1)
1.6 Stochastic Approaches Based on Global Optimization
10(1)
1.7 Hybrid Approaches
11(1)
1.8 Summary
11(2)
1.9 Conclusion
13(8)
References
14(7)
2 Sequential Forward Solver
21(18)
2.1 Maxwell's Equations
21(3)
2.1.1 Ill-Posedness of the Inverse Problem
22(1)
2.1.2 Nonlinearity of the Inverse Scattering Problem
23(1)
2.1.3 Inverse Scattering Problem from Theoretical Point of View
24(1)
2.2 Iterative Technique
24(1)
2.3 Time Domain Algorithm
25(1)
2.3.1 Time Domain Forward Scattering Problem
26(1)
2.4 Debye Model
26(1)
2.5 Fundamentals of FDTD Method (Yee Algorithm)
27(5)
2.6 Frequency-Dependent FDTD
32(7)
References
36(3)
3 Global Optimization: Differential Evolution, Genetic Algorithms, Particle Swarm, and Hybrid Methods
39(24)
3.1 Global Optimization Methods
39(1)
3.2 Differential Evolution
40(4)
3.2.1 Hybrid Differential Evolution
44(1)
3.2.2 Summary
44(1)
3.3 Genetic Algorithms
44(2)
3.3.1 Hybrid Genetic Algorithms
44(2)
3.3.2 Summary
46(1)
3.4 Particle Swarm Optimization
46(17)
3.4.1 Hybrid Particle Swarm Optimization
51(2)
3.4.2 Example of Microwave Tomography Using PSO and DE
53(4)
3.4.3 Summary
57(1)
References
58(5)
4 Sequential Optimization: Genetic Algorithm
63(24)
4.1 Genetic Algorithm (GA)
63(7)
4.1.1 Advantage of GA
63(1)
4.1.2 GA Parameters for the Proposed MWT
64(1)
4.1.3 Selection, Crossover, and Mutation
64(1)
4.1.4 Population and Generation Sizes and Rates
65(1)
4.1.5 Real-Coded GA
66(1)
4.1.6 Binary-Coded GA
67(2)
4.1.7 BGA with Knowledge About the Number of Scatterers
69(1)
4.2 Fitness Function
70(2)
4.2.1 Multi-view/Multi-illumination
71(1)
4.2.2 Multifrequency
71(1)
4.3 Dependent Regularization
72(1)
4.4 GA-Based Inverse Solver
73(4)
4.4.1 The GA Inversion Procedure
74(1)
4.4.2 Step I. Define Parameters
75(1)
4.4.3 Step II. Representation Scheme
75(1)
4.4.4 Step III. Initialization
75(1)
4.4.5 Step IV. Calculating the Fitness Function
75(1)
4.4.6 Step V. Saving the Fitness Values and Chromosomes
75(1)
4.4.7 Step VI. Selection, Evolution, and Mutation
76(1)
4.4.8 Step VII. Repeat the Procedure
76(1)
4.4.9 Example of GA Process
76(1)
4.5 Preliminary Validation
77(10)
4.5.1 I. Reconstruction Algorithm Using BGA
77(1)
4.5.2 Single Scatterer
78(2)
4.5.3 Multiple Scatterers
80(1)
4.5.4 Dispersive Separated Scatterers
80(2)
4.5.5 Dispersive Multiple Adjacent Scatterers
82(2)
References
84(3)
5 Inclusion of A Priori Information Using Neural Networks
87(56)
5.1 Hybrid GA Global Optimization and Neural Network Training
87(2)
5.2 Regularization Through Neural Network Classification
89(2)
5.3 Mathematical Formulation
91(3)
5.3.1 Numerical Phantom
92(2)
5.4 The NNRGA Method
94(7)
5.4.1 Variable Reduction
95(1)
5.4.2 Genetic Algorithm
95(1)
5.4.3 Neural Network Classifier
96(4)
5.4.4 Parameter Selection
100(1)
5.5 Numerical Results
101(3)
5.6 Reconstruction Results
104(18)
5.6.1 Reconstruction Results for the Samples Including Tumors
113(4)
5.6.2 Specificity and Sensitivity
117(5)
5.7 Conclusion
122(21)
References
139(4)
6 Parallel Forward Solver
143(10)
6.1 Parallel FDTD (PFDTD)
143(4)
6.2 Graphics Processing Unit Computing
147(1)
6.3 GPU Parallelization of FDTD Forward Solver
147(6)
6.3.1 FDTD GPU Acceleration Results
150(2)
References
152(1)
7 Parallel Optimization Methods
153(26)
7.1 Survey of Parallel and Distributed Evolutionary Algorithms
153(4)
7.1.1 Parallel Genetic Algorithms
154(1)
7.1.2 Parallel Differential Evolution
155(1)
7.1.3 Parallel Particle Swarm Optimization
155(2)
7.2 Asynchronous Global Optimization
157(4)
7.2.1 Asynchronous Genetic Algorithms
158(1)
7.2.2 Asynchronous Particle Swarm Optimization
159(1)
7.2.3 Asynchronous Differential Evolution
160(1)
7.3 Implementation of PGA for Microwave Imaging
161(3)
7.3.1 Integrating PGA and PFDTD Algorithms
162(1)
7.3.2 Example of Image Reconstructing Using the PFDTD/PGA
163(1)
7.4 Parallel Particle Swarm Performance Analysis
164(2)
7.5 Microwave Tomography Imaging for Breast Cancer Detection Using Parallel FDTD/GA
166(4)
7.5.1 Numerical Breast Phantom
166(2)
7.5.2 Penetration Depth
168(2)
7.6 Reconstructed Images
170(9)
7.6.1 Optimization Procedure
173(2)
References
175(4)
8 Benchmarking Parallel Evolutionary Algorithms
179(20)
8.1 Simulating Asynchronous Optimization
179(6)
8.2 Simulation Results
185(7)
8.2.1 Optimization and Test Function Parameters
185(1)
8.2.2 Simulating Homogeneous Environments
185(7)
8.2.3 Simulating Heterogeneous Environments
192(1)
8.3 Summary
192(7)
References
198(1)
Index 199
Sima Noghanian is an associate professor and chair of the Antenna and Applied Electromagnetics department of the University of North Dakota. 

Travis Desell is an assistant professor at the University of North Dakota.

Abas Sabouni is a research associate at Concordia University.

Ali Ashtari is the lead researcher at Invenia Technical Computing.
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97814939075262e.html
Keywords: