Muutke küpsiste eelistusi

E-raamat: Big Data and Differential Privacy - Analysis Strategies for Railway Track Engineering: Analysis Strategies for Railway Track Engineering [Wiley Online]

Teised raamatud teemal:
  • Wiley Online
  • Hind: 142,74 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
Big Data and Differential Privacy - Analysis Strategies for Railway Track Engineering: Analysis Strategies for Railway Track EngineeringSuurem pilt
Teised raamatud teemal:
Wiley Online e-raamatudRohkem infot Wiley Online kohta
Raamatu kodulehekülg: https://onlinelibrary.wiley.com/doi/book/10.1002/9781119229070

A comprehensive introduction to the theory and practice of contemporary data science analysis for railway track engineering

Featuring a practical introduction to state-of-the-art data analysis for railway track engineering, Big Data and Differential Privacy: Analysis Strategies for Railway Track Engineering addresses common issues with the implementation of big data applications while exploring the limitations, advantages, and disadvantages of more conventional methods. In addition, the book provides a unifying approach to analyzing large volumes of data in railway track engineering using an array of proven methods and software technologies.

Dr. Attoh-Okine considers some of today’s most notable applications and implementations and highlights when a particular method or algorithm is most appropriate. Throughout, the book presents numerous real-world examples to illustrate the latest railway engineering big data applications of predictive analytics, such as the Union Pacific Railroad’s use of big data to reduce train derailments, increase the velocity of shipments, and reduce emissions.

In addition to providing an overview of the latest software tools used to analyze the large amount of data obtained by railways, Big Data and Differential Privacy: Analysis Strategies for Railway Track Engineering:

• Features a unified framework for handling large volumes of data in railway track engineering using predictive analytics, machine learning, and data mining

• Explores issues of big data and differential privacy and discusses the various advantages and disadvantages of more conventional data analysis techniques

• Implements big data applications while addressing common issues in railway track maintenance

• Explores the advantages and pitfalls of data analysis software such as R and Spark, as well as the Apache™ Hadoop® data collection database and its popular implementation MapReduce

Big Data and Differential Privacy is a valuable resource for researchers and professionals in transportation science, railway track engineering, design engineering, operations research, and railway planning and management. The book is also appropriate for graduate courses on data analysis and data mining, transportation science, operations research, and infrastructure management.

NII ATTOH-OKINE, PhD, PE is Professor in the Department of Civil and Environmental Engineering at the University of Delaware. The author of over 70 journal articles, his main areas of research include big data and data science; computational intelligence; graphical models and belief functions; civil infrastructure systems; image and signal processing; resilience engineering; and railway track analysis. Dr. Attoh-Okine has edited five books in the areas of computational intelligence, infrastructure systems and has served as an Associate Editor of various ASCE and IEEE journals.

Preface xi
Acknowledgments xiii
1 Introduction
1(48)
1.1 General
1(1)
1.2 Track Components
2(2)
1.3 Characteristics of Railway Track Data
4(2)
1.4 Railway Track Engineering Problems
6(5)
1.5 Wheel--Rail Interface Data
11(4)
1.5.1 Switches and Crossings
14(1)
1.6 Geometry Data
15(5)
1.7 Track Geometry Degradation Models
20(5)
1.7.1 Deterministic Models
21(1)
1.7.1.1 Linear Models
21(1)
1.7.1.2 Nonlinear Models
22(1)
1.7.2 Stochastic Models
22(3)
1.7.3 Discussion
25(1)
1.8 Rail Defect Data
25(8)
1.9 Inspection and Detection Systems
33(4)
1.10 Rail Grinding
37(3)
1.11 Traditional Data Analysis Techniques
40(1)
1.11.1 Emerging Data Analysis
41(1)
1.12 Remarks
41(8)
References
42(7)
2 Data Analysis -- Basic Overview
49(10)
2.1 Introduction
49(1)
2.2 Exploratory Data Analysis (EDA)
49(4)
2.3 Symbolic Data Analysis
53(1)
2.3.1 Building Symbolic Data
54(1)
2.3.2 Advantages of Symbolic Data
54(1)
2.4 Imputation
54(2)
2.5 Bayesian Methods and Big Data Analysis
56(1)
2.6 Remarks
57(2)
References
57(2)
3 Machine Learning: A Basic Overview
59(54)
3.1 Introduction
59(1)
3.2 Supervised Learning
60(1)
3.3 Unsupervised Learning
61(1)
3.4 Semi-Supervised Learning
61(1)
3.5 Reinforcement Learning
61(2)
3.6 Data Integration
63(1)
3.7 Data Science Ontology
63(6)
3.7.1 Kernels
64(1)
3.7.1.1 General
64(1)
3.7.1.2 Learning Process
64(1)
3.7.2 Basic Operations with Kernels
65(1)
3.7.3 Different Kernel Types
65(1)
3.7.4 Intuitive Example
65(1)
3.7.5 Kernel Methods
66(1)
3.7.5.1 Support Vector Machines
66(3)
3.8 Imbalanced Classification
69(1)
3.9 Model Validation
70(1)
3.9.1 Receiver Operating Characteristic (ROC) Curves
70(1)
3.9.1.1 ROC Curves
71(1)
3.10 Ensemble Methods
71(3)
3.10.1 General
71(1)
3.10.2 Bagging
72(2)
3.10.3 Boosting
74(1)
3.11 Big P and Small N (P >> N)
74(5)
3.11.1 Bias and Variances
75(1)
3.11.2 Multivariate Adaptive Regression Splines (MARS)
75(4)
3.12 Deep Learning
79(16)
3.12.1 General
79(2)
3.12.2 Deep Belief Networks
81(1)
3.12.2.1 Restricted Boltzmann Machines (RBM)
81(1)
3.12.2.2 Deep Belief Nets (DBN)
82(1)
3.12.3 Convolutional Neural Networks (CNN)
83(1)
3.12.4 Granular Computing (Rough Set Theory)
83(6)
3.12.5 Clustering
89(1)
3.12.5.1 Measures of Similarity or Dissimilarity
89(1)
3.12.5.2 Hierarchical Methods
90(1)
3.12.5.3 Non-Hierarchical Clustering
91(1)
3.12.5.4 k-Means Algorithm
92(1)
3.12.5.5 Expectation--Maximization (EM) Algorithms
93(2)
3.13 Data Stream Processing
95(10)
3.13.1 Methods and Analysis
95(1)
3.13.2 LogLog Counting
96(1)
3.13.3 Count--Min Sketch
97(7)
3.13.3.1 Online Support Regression
104(1)
3.14 Remarks
105(8)
References
105(8)
4 Basic Foundations of Big Data
113(20)
4.1 Introduction
113(3)
4.2 Query
116(7)
4.3 Taxonomy of Big Data Analytics in Railway Track Engineering
123(1)
4.4 Data Engineering
124(6)
4.5 Remarks
130(3)
References
130(3)
5 Hilbert--Huang Transform, Profile, Signal, and Image Analysis
133(24)
5.1 Hilbert--Huang Transform
133(17)
5.1.1 Traditional Empirical Mode Decomposition
134(4)
5.1.1.1 Side Effect (Boundary Effect)
138(1)
5.1.1.2 Example
139(1)
5.1.1.3 Stopping Criterion
139(4)
5.1.2 Ensemble Empirical Mode Decomposition (EEMD)
143(1)
5.1.2.1 Post-Processing EEMD
144(1)
5.1.3 Complex Empirical Mode Decomposition (CEMD)
144(1)
5.1.4 Spectral Analysis
145(1)
5.1.5 Bidimensional Empirical Mode Decomposition (BEMD)
146(1)
5.1.5.1 Example
147(3)
5.2 Axle Box Acceleration
150(1)
5.2.1 General
150(1)
5.3 Analysis
151(2)
5.4 Remarks
153(4)
References
153(4)
6 Tensors -- Big Data in Multidimensional Settings
157(18)
6.1 Introduction
157(1)
6.2 Notations and Definitions
158(3)
6.3 Tensor Decomposition Models
161(3)
6.3.1 Nonnegative Tensor Factorization
162(2)
6.4 Application
164(6)
6.5 Remarks
170(5)
References
171(4)
7 Copula Models
175(17)
7.1 Introduction
175(9)
7.1.1 Archimedean Copulas
179(1)
7.1.1.1 Concordance Measures
180(3)
7.1.2 Multivariate Archimedean Copulas
183(1)
7.2 Pair Copula: Vines
184(2)
7.3 Computational Example
186(6)
7.3.1 Results
187(5)
7.4 Remarks
192(5)
References
193(4)
8 Topological Data Analysis
197(10)
8.1 Introduction
197(1)
8.2 Basic Ideas
197(6)
8.2.1 Topology
197(1)
8.2.2 Homology
198(1)
8.2.2.1 Simplicial Complex
199(1)
8.2.2.2 Cycles, Boundaries, and Homology
200(1)
8.2.3 Persistent Homology
201(1)
8.2.3.1 Filtration
201(1)
8.2.4 Persistence Visualizations
201(1)
8.2.4.1 Persistence Diagrams
201(2)
8.3 A Simple Railway Track Engineering Application
203(1)
8.3.1 Embedding Method
203(1)
8.4 Remarks
204(3)
References
204(3)
9 Bayesian Analysis
207(18)
9.1 Introduction
207(3)
9.1.1 Prior and Posterior Distributions
208(2)
9.2 Markov Chain Monte Carlo (MCMC)
210(1)
9.2.1 Gibbs Sampling
210(1)
9.2.2 Metropolis--Hastings
210(1)
9.3 Approximate Bayesian Computation
210(6)
9.3.1 ABC -- Rejection algorithm
211(5)
9.3.2 ABC Steps
216(1)
9.4 Markov Chain Monte Carlo Application
216(3)
9.5 ABC Application
219(2)
9.6 Remarks
221(4)
References
222(3)
10 Basic Bayesian Nonparametrics
225(10)
10.1 General
225(1)
10.2 Dirichlet Family
226(1)
10.2.1 Moments
226(1)
10.2.1.1 Marginal Distribution
227(1)
10.3 Dirichlet Process
227(4)
10.3.1 Stick-Breaking Construction
228(1)
10.3.2 Chinese Restaurant Process
229(1)
10.3.3 Chinese Restaurant Process (CRP) for Infinite Mixture
229(2)
10.3.4 Nonparametric Clustering and Dirichlet Process
231(1)
10.4 Finite Mixture Modeling
231(1)
10.5 Bayesian Nonparametric Railway Track
232(1)
10.6 Remarks
233(2)
References
233(2)
11 Basic Metaheuristics
235(6)
11.1 Introduction
235(2)
11.1.1 Particle Swarm Optimization
235(2)
11.1.2 PSO Algorithm Parameters
237(1)
11.2 Remarks
237(4)
References
239(2)
12 Differential Privacy
241(8)
12.1 General
241(1)
12.2 Differential Privacy
242(5)
12.2.1 Differential Privacy: Hypothetical Track Application
243(4)
12.3 Remarks
247(2)
References
247(2)
Index 249
Nii Attoh-Okine, PhD, PE is Professor in the Department of Civil and Environmental Engineering at the University of Delaware. The author of over 70 journal articles, his main areas of research include big data and data science; computational intelligence; graphical models and belief functions; civil infrastructure systems; image and signal processing; resilience engineering; and railway track analysis. Dr. Attoh-Okine has edited five books in the areas of computational intelligence, infrastructure systems and has served as an Associate Editor of various ASCE and IEEE journals.
Püsilink: https://www.kriso.ee/db/9781119229070_pe.html
Märksõnad: