Atjaunināt sīkdatņu piekrišanu

Mechanistic Data Science for STEM Education and Applications 2021 ed. [Hardback]

, ,
  • Formāts: Hardback, 276 pages, height x width: 235x155 mm, weight: 659 g, 181 Illustrations, color; 23 Illustrations, black and white; XV, 276 p. 204 illus., 181 illus. in color., 1 Hardback
  • Izdošanas datums: 22-Dec-2021
  • Izdevniecība: Springer Nature Switzerland AG
  • ISBN-10: 3030878317
  • ISBN-13: 9783030878313
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 78,14 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Standarta cena: 91,94 €
  • Ietaupiet 15%
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Mechanistic Data Science for STEM Education and Applications 2021 ed.Palielināt
  • Formāts: Hardback, 276 pages, height x width: 235x155 mm, weight: 659 g, 181 Illustrations, color; 23 Illustrations, black and white; XV, 276 p. 204 illus., 181 illus. in color., 1 Hardback
  • Izdošanas datums: 22-Dec-2021
  • Izdevniecība: Springer Nature Switzerland AG
  • ISBN-10: 3030878317
  • ISBN-13: 9783030878313
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9783030878313.html
Keywords:

This book introduces Mechanistic Data Science (MDS) as a structured methodology for combining data science tools with mathematical scientific principles (i.e., “mechanistic” principles) to solve intractable problems.  Traditional data science methodologies require copious quantities of data to show a reliable pattern, but the amount of required data can be greatly reduced by considering the mathematical science principles. MDS is presented here in six easy-to-follow modules: 1) Multimodal data generation and collection, 2) extraction of mechanistic features, 3) knowledge-driven dimension reduction, 4) reduced order surrogate models, 5) deep learning for regression and classification, and 6) system and design. These data science and mechanistic analysis steps are presented in an intuitive manner that emphasizes practical concepts for solving engineering problems as well as real-life problems. This book is written in a spectral style and is ideal as an entry level textbook for engineering and data science undergraduate and graduate students, practicing scientists and engineers, as well as STEM (Science, Technology, Engineering, Mathematics) high school students and teachers.

1 Introduction to Mechanistic Data Science
1(32)
1.1 A Brief History of Science: From Reason to Empiricism to Mechanistic Principles and Data Science
3(1)
1.2 Galileo's Study of Falling Objects
4(1)
1.3 Newton's Laws of Motion
4(2)
1.4 Science, Technology, Engineering and Mathematics (STEM)
6(1)
1.5 Data Science Revolution
7(1)
1.6 Data Science for Fatigue Fracture Analysis
8(2)
1.7 Data Science for Materials Design: "What's in the Cake Mix"
10(2)
1.8 From Everyday Applications to Materials Design
12(3)
1.8.1 Example: Tire Tread Material Design Using the MDS Framework
13(1)
1.8.2 Gold and Gold Alloys for Wedding Cakes and Wedding Rings
14(1)
1.9 Twenty-First Century Data Science
15(1)
1.9.1 AlphaGo
15(1)
1.9.2 3D Printing: From Gold Jewelry to Customized Implants
15(1)
1.10 Outline of Mechanistic Data Science Methodology
16(3)
1.11 Examples Describing the Three Types of MDS Problems
19(14)
1.11.1 Determining Price of a Diamond Based on Features (Pure Data Science: Type 1)
19(3)
1.11.2 Sports Analytics
22(3)
1.11.3 Predicting Patient-Specific Scoliosis Curvature (Mixed Data Science and Surrogate: Type 2)
25(3)
1.11.4 Identifying Important Dimensions and Damping in a Mass-Spring System (Type 3 Problem)
28(3)
References
31(2)
2 Multimodal Data Generation and Collection
33(16)
2.1 Data as the Central Piece for Science
34(3)
2.2 Data Formats and Sources
37(3)
2.3 Data Science Datasets
40(1)
2.4 Example: Diamond Data for Feature-Based Pricing
41(2)
2.5 Example: Data Collection from Indentation Testing
43(4)
2.6 Summary of Multimodal Data Generation and Collection
47(2)
References
47(2)
3 Optimization and Regression
49(40)
3.1 Least Squares Optimization
49(23)
3.1.1 Optimization
50(2)
3.1.2 Linear Regression
52(2)
3.1.3 Method of Least Squares Optimization for Linear Regression
54(1)
3.1.4 Coefficient of Determination (r2) to Describe Goodness of Fit
54(1)
3.1.5 Multidimensional Derivatives: Computing Gradients to Find Slope or Rate of Change
55(3)
3.1.6 Gradient Descent (Advanced Topic: Necessary for Data Science)
58(2)
3.1.7 Example: "Moneyball": Data Science for Optimizing a Baseball Team Roster
60(9)
3.1.8 Example: Indentation for Material Hardness and Strength
69(1)
3.1.9 Example: Vickers Hardness for Metallic Glasses and Ceramics
70(2)
3.2 Nonlinear Regression
72(6)
3.2.1 Piecewise Linear Regression
72(2)
3.2.2 Moving Average
74(1)
3.2.3 Moving Least Squares (MLS) Regression
75(1)
3.2.4 Example: Bacteria Growth
76(2)
3.3 Regularization and Cross-Validation (Advanced Topic)
78(8)
3.3.1 Review of the Lp-Norm
80(1)
3.3.2 L1-Norm Regularized Regression
81(1)
3.3.3 L2-Norm Regularized Regression
82(1)
3.3.4 K-Fold Cross-Validation
83(3)
3.4 Equations for Moving Least Squares (MLS) Approximation (Advanced Topic)
86(3)
References
87(2)
4 Extraction of Mechanistic Features
89(42)
4.1 Introduction
89(1)
4.2 What Is a "Feature"
90(1)
4.3 Normalization of Feature Data
90(2)
4.3.1 Example: Home Buying
91(1)
4.4 Feature Engineering
92(4)
4.4.1 Example: Determining a New Store Location Using Coordinate Transformation Techniques
92(4)
4.5 Projection of Images (3D to 2D) and Image Processing
96(1)
4.6 Review of 3D Vector Geometry
97(1)
4.7 Problem Definition and Solution
98(1)
4.8 Equation of Line in 3D and the Least Square Method
99(4)
4.8.1 Numerical Example
101(2)
4.9 Applications: Medical Imaging
103(2)
4.9.1 X-ray (Radiography)
103(1)
4.9.2 Computed Tomography (CT)
104(1)
4.9.3 Magnetic Resonance Imaging (MRI)
105(1)
4.9.4 Image Segmentation
105(1)
4.10 Extracting Geometry Features Using 2D X-ray Images
105(8)
4.10.1 Coordinate Systems
107(1)
4.10.2 Input Data
108(1)
4.10.3 Vertebra Regions [ Advanced Topic]
108(1)
4.10.4 Calculating the Angle Between Two Vectors
109(1)
4.10.5 Feature Definitions: Global Angles
110(3)
4.11 Signals and Signal Processing Using Fourier Transform and Short Term Fourier Transforms
113(1)
4.12 Fourier Transform (FT)
114(9)
4.12.1 Example: Analysis of Separate and Combined Signals
116(3)
4.12.2 Example: Analysis of Sound Waves from a Piano
119(4)
4.13 Short Time Fourier Transform (STFT)
123(8)
References
128(3)
5 Knowledge-Driven Dimension Reduction and Reduced Order Surrogate Models
131(40)
5.1 Introduction
132(1)
5.2 Dimension Reduction by Clustering
132(14)
5.2.1 Clustering in Real Life: Jogging
132(1)
5.2.2 Clustering for Diamond Price: From Jenks Natural Breaks to K-Means Clustering
133(5)
5.2.3 K-Means Clustering for High-Dimensional Data
138(1)
5.2.4 Determining the Number of Clusters
139(2)
5.2.5 Limitations of K-Means Clustering
141(1)
5.2.6 Self-Organizing Map (SOM) [ Advanced Topic]
141(5)
5.3 Reduced Order Surrogate Models
146(21)
5.3.1 A First Look at Principal Component Analysis (PCA)
146(3)
5.3.2 Understanding PCA by Singular Value Decomposition (SVD) [ Advanced Topic]
149(6)
5.3.3 Further Understanding of Principal Component Analysis [ Advanced Topic]
155(5)
5.3.4 Proper Generalized Decomposition (PGD) [ Advanced Topic]
160(7)
5.4 Eigenvalues and Eigenvectors [ Advanced Topic]
167(1)
5.5 Mathematical Relation Between SVD and PCA [ Advanced Topic]
168(3)
References
169(2)
6 Deep Learning for Regression and Classification
171(44)
6.1 Introduction
171(4)
6.1.1 Artificial Neural Networks
174(1)
6.1.2 A Brief History of Deep Learning and Neural Networks
174(1)
6.2 Feed Forward Neural Network (FFNN)
175(14)
6.2.1 A First Look at FFNN
175(8)
6.2.2 General Notations for FFNN [ Advanced Topic]
183(2)
6.2.3 Apply FFNN to Diamond Price Regression
185(4)
6.3 Convolutional Neural Network (CNN)
189(16)
6.3.1 A First Look at CNN
189(4)
6.3.2 Building Blocks in CNN
193(7)
6.3.3 General Notations for CNN [ Advanced Topic]
200(1)
6.3.4 COVID-19 Detection from X-Ray Images of Patients [ Advanced Topic]
201(4)
6.4 Musical Instrument Sound Conversion Using Mechanistic Data Science
205(6)
6.4.1 Problem Statement and Solutions
205(3)
6.4.2 Mechanistic Data Science Model for Changing Instrumental Music [ Advanced Topic]
208(3)
6.5 Conclusion
211(4)
References
213(2)
7 System and Design
215(52)
7.1 Introduction
215(1)
7.2 Piano to Guitar Musical Note Conversion (Type 3 General)
216(22)
7.2.1 Mechanistic Data Science with a Spring Mass Damper System
216(12)
7.2.2 Principal Component Analysis for Musical Note Conversion (Type 1 Advanced)
228(1)
7.2.3 Data Preprocessing (Normalization and Scaling)
228(2)
7.2.4 Compute the Eigenvalues and Eigenvectors for the Covariance Matrix of Bp and Bg
230(1)
7.2.5 Build a Reduced-Order Model
230(1)
7.2.6 Inverse Transform Magnitudes for all PCs to a Sound
231(1)
7.2.7 Cumulative Energy for Each PC
231(1)
7.2.8 Python Code for Step 1 and Step 2
232(1)
7.2.9 Training a Fully-Connected FFNN
233(1)
7.2.10 Code Explanation for Step 3
234(1)
7.2.11 Generate a Single Guitar
235(1)
7.2.12 Python Code for Step 4
236(1)
7.2.13 Generate a Melody
237(1)
7.2.14 Code Explanation for Step 5
237(1)
7.2.15 Application for Forensic Engineering
237(1)
7.3 Feature-Based Diamond Pricing (Type 1 General)
238(1)
7.4 Additive Manufacturing (Type 1 Advanced)
238(5)
7.5 Spine Growth Prediction (Type 2 Advanced)
243(4)
7.6 Design of Polymer Matrix Composite Materials (Type 3 Advanced)
247(5)
7.7 Indentation Analysis for Materials Property Prediction (Type 2 Advanced)
252(5)
7.8 Early Warning of Rainfall Induced Landslides (Type 3 Advanced)
257(5)
7.9 Potential Projects Using MDS
262(5)
7.9.1 Next Generation Tire Materials Design
262(2)
7.9.2 Antimicrobial Surface Design
264(1)
7.9.3 Fault Detection Using Wavelet-CNN
265(1)
References
265(2)
Index 267
Dr. Wing Kam Liu is Walter P. Murphy Professor of Mechanical Engineering & Civil and Environmental Engineering and (by courtesy) Materials Science and Engineering, and Director of Global Center on Advanced Material Systems and Simulation (CAMSIM) at Northwestern University in Evanston, Illinois;  Dr. Zhengtao Gan is Research Assistant Professor in the Department of Mechanical Engineering at Northwestern University in Evanston, Illinois; and Dr. Mark Fleming, is the Chief Technical Officer of Fusion Engineering, and an Adjunct Professor in the Department of Mechanical Engineering at Northwestern University in Evanston, Illinois.