Advances in Data Science and Analytics: Concepts and Paradigms

Cover
Title Page
Copyright Page
Contents
Preface
Chapter 1 Implementation Tools for Generating Statistical Consequence Using Data Visualization Techniques
	1.1 Introduction
	1.2 Literature Review
	1.3 Tools in Data Visualization
	1.4 Methodology
		1.4.1 Plotting the Data
		1.4.2 Plotting the Model on Data
		1.4.3 Quantifying Linear Relationships
		1.4.4 Covariance vs. Correlation
	1.5 Conclusion
	References
Chapter 2 Decision Making and Predictive Analysis for Real Time Data
	2.1 Introduction
	2.2 Data Analytics
		2.2.1 Descriptive Analytics
		2.2.2 Diagnostic Analytics
		2.2.3 Predictive Analytics
		2.2.4 Prescriptive Analytics
	2.3 Predictive Modeling
	2.4 Categories of Predictive Models
	2.5 Process of Predictive Modeling
		2.5.1 Requirement Gathering
		2.5.2 Data Gathering
		2.5.3 Data Analysis and Massaging
		2.5.4 Machine Learning Statistics
		2.5.5 Predictive Modeling
		2.5.6 Prediction and Decision Making
	2.6 Predictive Analytics Opportunities
		2.6.1 Detecting Fraud
		2.6.2 Reduction of Risk
		2.6.3 Marketing Campaign Optimization
		2.6.4 Operation Improvement
		2.6.5 Clinical Decision Support System
	2.7 Classification of Predictive Analytics Models
		2.7.1 Predictive Models
		2.7.2 Descriptive Models
		2.7.3 Decision Models
	2.8 Predictive Analytics Techniques
		2.8.1 Predictive Analytics Software
		2.8.2 The Importance of Good Data
		2.8.3 Predictive Analytics vs. Business Intelligence
		2.8.4 Pricing Information
	2.9 Data Analysis Tools
		2.9.1 Excel
		2.9.2 Tableau
		2.9.3 Power BI
		2.9.4 Fine Report
		2.9.5 R & Python
	2.10 Advantages & Disadvantages of Predictive Modeling
		2.10.1 Advantages
		2.10.2 Disadvantages
			2.10.2.1 Data Labeling
			2.10.2.2 Obtaining Massive Training Datasets
			2.10.2.3 The Explainability Problem
			2.10.2.4 Generalizability of Learning
			2.10.2.5 Bias in Algorithms and Data
	2.11 Predictive Analytics Biggest Impact
		2.11.1 Predicting Demand
		2.11.2 Transformation Using Technology and Process
		2.11.3 Improved Pricing
		2.11.4 Predictive Maintenance
	2.12 Application of Predictive Analytics
		2.12.1 Financial and Banking Services
		2.12.2 Retail
		2.12.3 Health and Insurance
		2.12.4 Oil and Gas Utilities
		2.12.5 Public Sector
	2.13 Future Scope of Predictive Modeling
		2.13.1 Technological Advancements
		2.13.2 Changes in Work
		2.13.3 Risk Mitigation
	2.14 Conclusion
	References
Chapter 3 Optimizing Water Quality with Data Analytics and Machine Learning
	3.1 Introduction
	3.2 Related Work
	3.3 Data Sources and Collection
	3.4 Water Demand Forecasting
		3.4.1 Network Flow and Zone Demand Estimation
		3.4.2 Demand Forecasting
			3.4.2.1 Feature Importance
			3.4.2.2 Forecast Horizon
		3.4.3 Performance Characterization
	3.5 Re-Chlorination Optimization
		3.5.1 Data
		3.5.2 Water Age Estimation
			3.5.2.1 Travel Time Estimation
			3.5.2.2 Residential Time Estimation
		3.5.3 Ammonia Prediction
		3.5.4 Optimization Model Definition
		3.5.5 Improvements in Customer Water Quality
		3.5.6 Plant Dosing Optimization
	3.6 Conclusion
	Acknowledgements
	References
Chapter 4 Lip Reading Framework using Deep Learning and Machine Learning
	4.1 Introduction
		4.1.1 Overview
		4.1.2 Motivation
		4.1.3 Lip Reading System Outcomes and Deliverables
	4.2 The Emergence and Definition of the Lip-Reading System
		4.2.1 Background of Domain
		4.2.2 Identified Problems
		4.2.3 Tools and Technologies Used
		4.2.4 Implementation Aspects
			4.2.4.1 Data Preparation
	4.3 Design and Components of Lip-Reading System
	4.4 Lip Reading System Architecture
	4.5 Testing
	4.6 Problems Encountered During Implementation
		4.6.1 Assumptions and Constraints
	4.7 Conclusion
	4.8 Future Work
	References
Chapter 5 New Perspective to Management, Economic Growth and Debt Nexus Analysis: Evidence from Indian Economy
	5.1 Introduction
	5.2 Literature Review
		5.2.1 External Debt and Economic Growth
		5.2.2 Trade Openness, FDI, and Economic Growth
		5.2.3 FDI and Economic Growth
	5.3 Data
		5.3.1 Analytical Framework and Data Description
		5.3.2 Theoretical Background and Specifications
			5.3.2.1 Model Specification
	5.4 Methodology and Findings
		5.4.1 Unit Root Testing
		5.4.2 Cointegration
		5.4.3 Vector Error Correction Model
		5.4.4 Long-Run Relationship Estimation
		5.4.5 Causality Test
	5.5 Conclusion and Policy Implications
	Declarations
	Availability of Data and Materials
	Competing Interests
	Funding
	Authors’ Contributions
	Acknowledgments
	References
Chapter 6 Data-Driven Delay Analysis with Applications to Railway Networks
	6.1 Introduction
	6.2 Related Works
	6.3 Background Knowledge
		6.3.1 Background and Problem Formulation
			6.3.1.1 Train Delay
			6.3.1.2 Delay Propagation
		6.3.2 Preliminaries
			6.3.2.1 Bayesian Inference
			6.3.2.2 Markov Property
	6.4 Delay Propagation Model
		6.4.1 Conditional Bayesian Delay Propagation
			6.4.1.1 Delay Self-Propagation
			6.4.1.2 Incremental Run-Time Delay
			6.4.1.3 Incremental Dwell Time Delay
			6.4.1.4 Accumulative Departure Delay
		6.4.2 Cross-Line Propagation, Backward Propagation and Train Connection Propagation
	6.5 Primary Delay Tracing Back
		6.5.1 Delay Candidates Selection
		6.5.2 Relation Construction
			6.5.2.1 Preceding and Following Trains
			6.5.2.2 Preceding and Connecting Trains
	6.6 Evaluation on Dwell Time Improvement Strategy
	6.7 Experiments
		6.7.1 Experiment Setting
		6.7.2 Temporal Prediction of Delay Propagation
		6.7.3 Spatial Prediction of Delay Propagation
		6.7.4 Case Study of Primary Delay Tracing Down
		6.7.5 Evaluation of Dwell Time Improvement Strategy
	6.8 Conclusion
	References
Chapter 7 Proposing a Framework to Analyze Breast Cancer in Mammogram Images Using Global Thresholding, Gray Level Co-Occurrence Matrix, and Convolutional Neural Network (CNN)
	7.1 Introduction & Purpose of Study
		7.1.1 Segmentation
			7.1.1.1 Types of Segmentation
		7.1.2 Compression
	7.2 Literature Review & Motivation
	7.3 Proposed Work
		7.3.1 Algorithm
		7.3.2 Explanation
		7.3.3 Flowchart
	7.4 Observation Tables and Figures
	7.5 Conclusion
	7.6 Future Work
	References
Chapter 8 IoT Technologies for Smart Healthcare
	8.1 Introduction
	8.2 Literature Review
		8.2.1 IoT-Based Smart Health
		8.2.2 Advantages of Applying IoT in Health
	8.3 Findings
		8.3.1 Significant Features and Applications of IoT in Health
			8.3.1.1 Simultaneous Monitoring and Reporting
			8.3.1.2 End-to-End Connectivity and Affordability
			8.3.1.3 Data Analysis
			8.3.1.4 Tracking, Alerts, and Remote Medical Care
			8.3.1.5 Research
			8.3.1.6 Patient-Generated Health Data (PGHD)
			8.3.1.7 Management of Chronic Diseases and Preventative Care
			8.3.1.8 Home-Based and Short-Term Care
	8.4 Case Study: CyberMed as an IoT-Based Smart Health Model
	8.5 Discussions
		8.5.1 Limitations of Adopting IoT in Health
			8.5.1.1 Data Security and Privacy
			8.5.1.2 Connectivity
			8.5.1.3 Compatibility and Data Integration
			8.5.1.4 Implementation Cost
			8.5.1.5 Complexity and Risk of Errors
	8.6 Future Insights
	8.7 Conclusions
	References
Chapter 9 Enhancement of Scalability of SVM Classifiers for Big Data
	9.1 Introduction
	9.2 Support Vector Machine
		9.2.1 Challenges
	9.3 Parallel and Distributed Mechanism
		9.3.1 Shared-Memory Parallelism
	9.4 Distributed Big Data Architecture
		9.4.1 Hadoop MapReduce
		9.4.2 Spark
		9.4.3 AKKA
	9.5 Distributed High Performance Computing
		9.5.1 GASNet
		9.5.2 Charm++
	9.6 GPU Based Parallelism
		9.6.1 CUDA
		9.6.2 OpenCL
	9.7 Parallel and Distributed SVM Algorithms
		9.7.1 LS-SVM
		9.7.2 Cascade SVM
		9.7.3 DC SVM
		9.7.4 Parallel Distributed Multiclass SVM Algorithms
	9.8 Conclusion and Future Research Directions
	References
Chapter 10 Electrical Network-Related Incident Prediction Based on Weather Factors
	10.1 Introduction
	10.2 Related Work
	10.3 Methodology
		10.3.1 Binary Classification of Incident and Normality
		10.3.2 Incident Categorization Using Natural Language Processing
		10.3.3 Classification of Multiple Types of Incidents
	10.4 Experiments
		10.4.1 Data Sets
		10.4.2 Evaluation Metrics
		10.4.3 Binary Classification
		10.4.4 Incident Categorization
		10.4.5 Multi-Class Classification
	10.5 Conclusion and Future Work
	Acknowledgements
	References
Chapter 11 Green IoT: Environment-Friendly Approach to IoT
	11.1 Introduction
	11.2 G-IoT (Green Internet of Things)
	11.3 Layered Architecture of G-IoT
		11.3.1 Data Center/Cloud
		11.3.2 Data Analytics and Control Applications It
		11.3.3 Data Aggregation and Storage
		11.3.4 Edge Computing
		11.3.5 Communication and Processing Unit
	11.4 Techniques for Implementation of G-IoT
	11.5 Power Saving Methods Based on Components
	11.6 Applications of G-IoT
	11.7 Challenges and Future Scope
	11.8 Case Study
	11.9 Conclusion
	References
Chapter 12 Big-Data Analytics: A New Paradigm Shift in Micro Finance Industry
	12.1 Introduction
	12.2 Reality of Area and Transcendent Difficulties
		12.2.1 Probable Overlending
		12.2.2 Information Imbalance
		12.2.3 Retreating Not-for-Profit Sector
		12.2.4 Neighbourhood Pressure
	12.3 Data Analytics in Microfinance
		12.3.1 Types of Data Analytics Used in Microfinance
		12.3.2 Use of Big Data in Microfinance Industry
		12.3.3 Risk and Data Based Credit Decisions
		12.3.4 Product Development and Selection
		12.3.5 Product or Service Positioning
		12.3.6 M-Commerce and E-Payments
		12.3.7 Making Reliable Credit Decisions
		12.3.8 Big Data-Driven Model Promises Psychometric Evaluations
		12.3.9 Product Build-Up, Service Positioning, and Offering
	12.4 Opportunities and Risks in Using Data Analytics
	12.5 Risk in Utilizing Big Data
	12.6 Conclusion
	References
Chapter 13 Big Data Storage and Analysis
	13.1 Introduction
		13.1.1 6 V’s of Big Data
		13.1.2 Types of Data
		13.1.3 Issues in Handling Big Data
	13.2 Hadoop as a Solution to Challenges of Big Data
		13.2.1 The Hadoop Ecosystem
		13.2.2 Rack Awareness Policy in HDFS
	13.3 In-Memory Storage and NoSQL
		13.3.1 Key-Value Data Stores
		13.3.2 Document Stores
		13.3.3 Wide Column Stores
		13.3.4 Graph Stores
		13.3.5 Multi-Modal Databases
	13.4 Advantages of NoSQL Database
	13.5 Conclusion
	References
Chapter 14 A Framework for Analysing Social Media and Digital Data by Applying Machine Learning Techniques for Pandemic Management
	14.1 Introduction
	14.2 Literature Review
	14.3 Understanding Pandemic Analogous to a Disaster
	14.4 Application of Machine Learning Techniques at Various Phases of Pandemic Management
		14.4.1 Mitigation Phase
		14.4.2 Preparedness Phase
		14.4.3 Response Phase
		14.4.4 Recovery Phase
	14.5 Generalized Framework to Apply Machine Learning Techniques for Pandemic Management
	14.6 Conclusion
	References
About the Editors
Index
EULA