Knowledge is Power in Four Dimensions: Models to Forecast Future Paradigm

Knowledge is Power in Four Dimensions: Models to Forecast Future Paradigms, Forecasting Energy for Tomorrow’s World with Mathematical Modeling and Python Programming Driven Artificial Intelligence delivers knowledge on key infrastructure topics in both AI technology and energy. Sections lay the groundwork for tomorrow’s computing functionality, starting with how to build a Business Resilience System (BRS), data warehousing, data management, and fuzzy logic. Subsequent chapters dive into the impact of energy on economic development and the environment and mathematical modeling, including energy forecasting and engineering statistics. Energy examples are included for application and learning opportunities.

A final section deliver the most advanced content on artificial intelligence with the integration of machine learning and deep learning as a tool to forecast and make energy predictions. The reference covers many introductory programming tools, such as Python, Scikit, TensorFlow and Kera.

Cover image
Title page
Table of Contents
Copyright
Dedication
About the authors
Preface
Acknowledgment
Part I. The general infrastructure
Chapter 1. Knowledge is power
1.1. Introduction
1.2. History of knowledge
1.3. Definition of knowledge
1.4. Types of knowledge
1.5. What value there is in knowing
1.6. Limitation of knowing
1.7. Measurability of knowledge
1.8. Creation of knowledge
1.9. Knowledge resources and power
1.10. Knowledge and information as goods
1.11. Reasons why knowledge is power
1.12. Knowledge is power? Those days are long gone
1.13. There is more to “the knowledge is power”
1.14. Facilitates decision—making capabilities
1.15. Stimulates cultural change and innovation
1.16. Bottom line
1.17. Summary and conclusion
Chapter 2. A general approach to business resilience system (BRS)
2.1. Introduction
2.2. Resilience and stability
2.3. Reactive to proactive safety through resilience
2.4. Reactive to proactive safety through resilience
2.5. Risk atom key concept
2.6. Business resilience system features
2.7. Summary of the business resilience system
2.8. Business resilience system project plan
2.9. Summary and conclusion
Chapter 3. Data warehousing, data mining, data modeling, and data analytics
3.1. Introduction
3.2. Data warehousing concept
3.3. Data mart concept
3.4. Data mining concept
3.5. Data modeling concept
3.6. Data analytics concept
3.7. Big data and master data management concepts
3.8. Architecture and benefits of MDM and big data
3.9. Summary and conclusion
Chapter 4. Structured and unstructured data processing
4.1. Introduction
4.2. Master data management versus big data
4.3. Big data history and current considerations
4.4. Real time data processing and data mining
4.5. Improving big data analytics with machine learning-as-a-service
4.6. The mathematics of data: graph analytics-as-a-service
4.7. Cloud database
4.8. Summary and conclusions
Chapter 5. Mathematical modeling driven predication
5.1. Introduction
5.2. Mathematics for data-driven modeling—the science of crystal balls
5.3. Mathematics of probability
5.4. Statistical analysis
5.5. Bayesian methods and concepts
5.6. Markov chain Monte Carlo methods and concepts
5.7. Predictive modeling and analysis
5.8. Descriptive, prescriptive-analytics-driven predictive analytic
5.9. Predictive versus prescriptive analytics
5.10. Big data analytics: descriptive versus predictive versus prescriptive
5.11. Diagnostic analytics
5.12. Analytical techniques
5.13. Summary and conclusion
Chapter 6. Fuzzy logics: a new method of predictions
6.1. Introduction
6.2. What is fuzzy logic and how it works
6.3. Fuzzy logic and fuzzy sets
6.4. The fuzzy logic method
6.5. The world's first fuzzy logic controller
6.6. The rationale for fuzzy logic
6.7. Information processing driven by fuzzy logic
6.8. Fuzzy logic system type-1 and type-2
6.9. Adaptive neuro-fuzzy interface system
6.10. Back Propagation Neural Network
6.11. Bayesian network
6.12. Fuzzy logic algorithms and neural networking
6.13. Summary and conclusion
Chapter 7. Neural network concept
7.1. Introduction
7.2. Artificial neural network (ANN)
7.3. Back-propagation neural networks
7.4. Biological background
7.5. Biological neural networks
7.6. Learning in a neural network
7.7. Fuzzy logic and neural networks
7.8. Summary and conclusion
Chapter 8. Population—human growth driving ecology
8.1. Introduction
8.2. Population—human growth
8.3. What is population
8.4. The status of population in the world
8.5. Trends—forecasting
8.6. Growth rates
8.7. How many people can planet earth support?
8.8. Criteria to be used in our model
8.9. Population structure
8.10. Religions
8.11. The relationship between population and other critical factors
8.12. The impact of climate change on human life
8.13. Population and economic growth and development
8.14. Population and governance
8.15. Population and immigration
8.16. Refugees
8.17. Urbanization
8.18. Summary and conclusion
Chapter 9. Economic factors
9.1. Introduction
9.2. What is economics?
9.3. Key players
9.4. Business cycle
9.5. Economics factors
9.6. Other economic issues
9.7. Summary and conclusion
Chapter 10. Risk management, risk assessment, and risk analysis
10.1. Introduction
10.2. Predictive risk intelligence
10.3. Cognitive computing applications for risk management
10.4. Harnessing product safety and recall analytics
10.5. Managing algorithmic risks
10.6. The future risk, new game, new rules
10.7. Global risk management
10.8. Risk sensing: the evolving state of the art
10.9. Summary and conclusion
Chapter 11. Today's fast-paced technology
11.1. Introduction
11.2. Climate change
11.3. Human behavior
11.4. Technology definition
11.5. The impact of modern technology on human behavior
11.6. The impact of technology on climate change
11.7. Is there any hope
11.8. Summary and conclusion
Part II. The impact of energy on tomorrow’s world
Chapter 12. Understanding of energy
12.1. Introduction
12.2. What is energy?
12.3. Moving from one source of energy to another
12.4. World energy 2017
12.5. United States trends
12.6. Global demand growth
12.7. Use of energy by different sectors in the United States
12.8. Energy use in commercial buildings
12.9. Nature of demand for the energy in the future
12.10. Summary and conclusion
Chapter 13. Economic impact of energy
13.1. Introduction
13.2. Historical relationship between energy and GDP
13.3. Factors influence the demand for energy
13.4. Energy and climate change
13.5. The potential future impacts change in climate on the US energy sector
13.6. Summary and conclusion
Chapter 14. Renewable energy
14.1. Introduction
14.2. Different types of energy
14.3. Definition of the renewable energy
14.4. Factors affecting the future renewable energy
14.5. Types of renewable energy
14.6. Summary and conclusion
Chapter 15. Nonrenewable energy
15.1. Introduction
15.2. Types of nonrenewable energy
15.3. Coal
15.4. Natural gas energy
15.5. World of cautious
Chapter 16. Nuclear energy as nonrenewable energy source
16.1. Introduction
16.2. Nuclear fission process in a nutshell
16.3. Nuclear fusion process in nutshell
16.4. Why we need nuclear power plants
16.5. Is nuclear energy renewable source of energy
16.6. Argument for nuclear as renewable energy
16.7. Argument against nuclear as renewable energy
16.8. Safety
16.9. Conclusion
Chapter 17. Energy storage technologies and their role in renewable integration
17.1. Introduction
17.2. The electric grid
17.3. Power generation
17.4. Transmission and distribution
17.5. Load management
17.6. Types of storage technology
17.7. A battery-inspired strategy for carbon fixation
17.8. Saliva-powered battery
17.9. Summary
Part III. The mathematical approach and modeling
Chapter 18. Predictive analytics
18.1. Introduction
18.2. Predictive analytics history and current advances
18.3. How does predictive analytics work?
18.4. Why is predictive analytics important?
18.5. Predictive analytics benefits and what are they?
18.6. Difference between predictive analytics and traditional analytics
18.7. Predictive analytics starts driving an organization
18.8. Predictive analytics examples and who's using it?
18.9. Predictive modeling and how it works?
18.10. Directed acyclic graph (DAG)
18.11. Notation
18.12. Probability
18.13. Distributions
18.14. Parameter learning
18.15. Online learning
18.16. Evidence
18.17. Instantiation
18.18. Joint probability of a Bayesian network
18.19. Distributive law
18.20. Bayes theorem utilization
18.21. Are Bayesian networks Bayesian?
18.22. Inference
18.23. Queries
18.24. Analysis
18.25. Dynamic Bayesian networks
18.26. Decision graphs
18.27. Decision automation approach
18.28. Bayesian statistics-driven data science
18.29. The difference between Bayesian statistics and machine learning
18.30. What do you need to get started using predictive analytics?
18.31. Predictive analytics—common use cases plus case study
18.32. Rise of prediction in marketing
18.33. Benefits of predictive scoring for marketers
18.34. The four common challenges of predictive analytics
18.35. Summary
Chapter 19. Engineering statistics
19.1. Introduction
19.2. Statistical thinking driving decision-making
19.3. Statics driving future forecast
19.4. Definition of a linear trend
19.5. Expected temperature changes: signal and noise
19.6. Deriving trend statistics
19.7. Trend uncertainties
19.8. Confidence intervals and significance testing
19.9. Comparing trends in two datasets
19.10. Multiple atmosphere/ocean general circulation model (AOGCM) simulations
19.11. Practical versus statistical significance
19.12. Climate change and global warming
Chapter 20. Data and data collection driven information
20.1. Introduction
20.2. Data versus information
20.3. Detrend data driving statistics
20.4. Engineering data collection
20.5. Exploratory data analysis
20.6. Exploratory data analysis versus classical and Bayesian data analysis
20.7. Exploratory data analysis versus summary analysis
20.8. Exploratory data analysis primary and secondary goals
20.9. Summary and conclusion
Chapter 21. Statistical forecasting—regression and time series analysis
21.1. Introduction
21.2. Signal versus noise
21.3. Risk of forecasting
21.4. Introduction to ARIMA: a nonseasonal models
Chapter 22. Introduction to forecasting: the simplest models
22.1. Introduction
22.2. Forecasting with the mean model
22.3. More rules of thumb for confidence intervals
22.4. More about t
22.5. Our example continued
22.6. Presentation of results
22.7 Summary
Chapter 23. Notes on linear regression analysis
23.1. Introduction
23.2. Linear regression analysis description
23.3. Linear regression and correlation
23.4. Correlation and regression to mediocrity
23.5. Mathematics of the simple regression model
23.6. Introducing R-squared
23.7. The standard errors of means and forecasts
23.8. Linear regression methods
23.9 The listen learned
Chapter 24. Principles and risks of forecasting
24.1. Introduction
24.2. Forecasting principles and perspectives
24.3. How to move data around
24.4. Get to know your data
24.5. Inflation adjustment (deflation)
24.6. Seasonal adjustment
24.7. Stationarity and differencing
24.8. Autoregressive integrated moving average (ARIMA) models with regressors
24.9. The mathematical structure of ARIMA models
Chapter 25. Artificial intelligence driving predictive and forecasting paradigm
25.1. Introduction
25.2. Prediction versus forecasting
25.3. Artificial intelligence role
25.4. Data analytics role
25.5. Predictive analytics role
25.6. Predictive analytics and machine learning
25.7. Applications of predictive analytics and machine learning
25.8. Conclusion
Part IV. Python programming-driven artificial intelligence
Chapter 26. Python programming–driven artificial intelligence
26.1. Introduction
26.2. History of knowledge
26.3. Definition of knowledge
26.4. Python basics
26.5. Python standard and add-on libraries
26.6. Python for artificial intelligence, machine learning, and deep learning
Chapter 27. Artificial intelligence, machine learning, and deep learning driving big data
27.1. Introduction
27.2. What is machine learning?
27.3. What is deep learning?
27.4. Short description of artificial intelligence, machine learning, and deep learning
27.5. Big data
27.6. Natural language processing (NLP)
27.7. Cognitive science and cognitive linguistics
27.8. Neural networks concepts
27.9. Data science and data science platform
27.10. Conclusion
Chapter 28. Artificial intelligence, machine learning, and deep learning use cases
28.1. Introduction
28.2. Apple stock prediction, using machine learning
28.3. Boston housing market analysis
28.4. Customer segmentation using K-means clustering a machine learning
28.5. Credit card fraud detection
Appendix A: Pendulum problem
Appendix B: Fluorescence microscopy
Appendix C: Factors contributed to the financial crisis 2008–09
Appendix D: factors contributing to the financial crisis of 2008
Appendix E: Forecasting the future by the OECD
Appendix F: The 2025 global landscape
Appendix G: The world in 2050
Appendix H: Risk
Appendix I: Fission nuclear energy research and development roadmap
Appendix J: Thermonuclear fusion reaction driving electrical power generation
Appendix K: The Weibull distribution
Appendix L: The logarithm transformation
Appendix M: Geometric random walk model
Appendix N. Appendix N: Random walk model
Appendix O: Examples of forecasting driven by artificial intelligence and machine learning
Appendix P: Examples of python programming driving artificial intelligence and machine learning
Appendix Q: Artificial intelligence and human intelligence
Appendix R: Deep learning, machine learning limitations and flaws
Appendix S: Machine learning–driven e-commerce
Appendix T: From business intelligence to artificial intelligence
Index

With Artificial Intelligence Integration in Energy and Other Use Cases

Purchase options

Save 50% on book bundles

Institutional subscription on ScienceDirect

Bahman Zohuri

Farahnaz Behgounia