Big Data Applications in Industry 4.0

Description

Industry 4.0 is the latest technological innovation in manufacturing with the goal to increase productivity in a flexible and efficient manner. Changing the way in which manufacturers operate, this revolutionary transformation is powered by various technology advances including artificial intelligence (AI), Big Data analytics, Internet-of-Things (IoT) and cloud computing. Big Data analytics has been identified as one of the significant components of Industry 4.0, as it provides valuable insights for smart factory management. Big Data and Industry 4.0 have the potential to reduce resource consumption and optimize processes, thereby playing a key role in achieving sustainable development. Big Data Applications in Industry 4.0 covers the recent advancements that have emerged in the field of Big Data and its applications. The book introduces the concepts and advanced tools and technologies for representing and processing Big Data. It also covers applications of Big Data in such domains as financial services, education, healthcare, biomedical research, logistics, and warehouse management. Researchers, students, scientists, engineers, and statisticians can turn to this book to learn about concepts, technologies, and applications that solve real world problems. The books features: An introduction to data science and the types of data analytics methods accessible today An overview of data integration concepts, methodologies, and solutions A general framework of forecasting principles and applications as well as basic forecasting models including naïve, moving average, and exponential smoothing models A detailed roadmap of the Big Data evolution and its related technological transformation in computing, along with a brief description of related terminologies The application of Industry 4.0 and Big Data in the field of education The features, prospects, and significant role of Big Data in banking industry, as well as various use cases of Big Data in banking, finance services, and insurance. Implementing a Data Lake (DL) in the cloud and the significance of a data lake in for decision-making. Cover Half Title Title Page Copyright Page Dedication Contents Preface Acknowledgments Editors Contributors Chapter 1. Data Science and Its Applications 1.1 Introduction to Data Science 1.1.1 Data Science: A Definition 1.1.2 Data in the Business 1.1.3 Types of Data Analytics 1.1.4 Use Cases in the Business 1.1.5 Data Analytics Process, Implementation and Measurement 1.2 Data Science and Its Application in the Healthcare Industry 1.2.1 Data Types Generated in the Healthcare Sector 1.2.2 Analytics Use Cases in Healthcare 1.2.3 Future and Challenges 1.3 Data Science and Its Application in the Retail and Retail E-Commerce 1.3.1 Data Types Generated in the Retail and Retail E-Commerce Sector 1.3.2 Analytics Use Cases in Retail and Retail E-Commerce 1.3.3 Future and Challenges 1.4 Data Science and Its Application in the Banking, Financial Services and Insurance (BFSI) Sector 1.4.1 Data Types Generated in the BFSI Sector 1.4.2 Analytics Use Cases in BFSI 1.4.3 Future and Challenges 1.5 Statistical Methods and Analytics Techniques Used across Businesses 1.6 Statistical Methods and Analytics Techniques Used in Sales and Marketing 1.6.1 Data Types Generated in Sales and Marketing Function 1.6.2 Statistical Methods and Analytical Techniques 1.6.3 Future and Challenges 1.7 Statistical Methods and Analytics Techniques Used in Supply Chain Management 1.7.1 Data Types Used in the SCM 1.7.2 Analytics Use Cases in SCM 1.7.3 Future and Challenges 1.8 Statistical Methods and Analytics Techniques Used in Human Resource Management 1.8.1 Data Types Generated in Human Resource Management 1.8.2 Analytics Use Cases in Human Resource Management 1.8.3 Future and Challenges References Chapter 2. Industry 4.0: Data and Data Integration 2.1 Introduction 2.2 Data Integration 2.3 Data Integration Solutions 2.3.1 Custom Code 2.3.2 ETL 2.3.2.1 Extract 2.3.2.2 Transform 2.3.2.3 Load 2.3.3 ELT 2.4 Data Integration Methodologies 2.4.1 Bulk Loading 2.4.2 Daily Differentials 2.4.3 Insert Only 2.4.4 Database Replication 2.4.5 Batch Processing 2.4.6 Streaming 2.5 Service Providers 2.6 Brief on Each Software 2.7 Conclusion References Chapter 3. Forecasting Principles and Models: An Overview 3.1 Introduction 3.2 Meaning of Forecasting 3.3 Applications of Forecasting 3.3.1 Business Forecasting 3.3.2 Forecasting in Supply Chain Management 3.3.3 Epidemiological Forecasting 3.3.4 Weather Forecasting 3.4 Limitations of Forecasting 3.5 Types of Forecasting Procedures 3.5.1 Qualitative Approach 3.5.2 Quantitative Approach 3.6 Process of Forecasting 3.6.1 Problem Identification 3.6.2 Collection of Data 3.6.3 Description and Manipulation of Data 3.6.4 Analysis of Data, Model Construction, and Evaluation 3.6.5 Model Implementation, Forecast Evaluation, and Model Performance 3.7 Basic Forecasting Models 3.7.1 Naïve Forecast Model 3.7.2 Forecasting with Averaging Models 3.7.2.1 Simple Averages 3.7.2.2 Moving Averages 3.7.3 Exponential Smoothing Models 3.8 Software Tools for Forecasting 3.9 Conclusions References Chapter 4. Breaking Technology Barriers in Diabetes and Industry 4.0 4.1 Brief Introduction to Diabetes 4.1.1 The Epidemic of Diabetes 4.1.2 Burden of Type 1 Diabetes in India 4.1.3 Burden of Type 2 Diabetes in India 4.1.4 Burden of Type 1, Type 2 Diabetes and Prediabetes in India: So, What? 4.2 "Big Data" Concept 4.2.1 "Big Data": Definition and Concepts 4.2.2 Big Data and Diabetes 4.2.3 Big Data, Predictive Analysis and Diabetes 4.2.4 Case Study in Big Data 4.3 Recent Technological Advances in Diabetes Management 4.3.1 Closed-Loop Insulin Pump Systems 4.3.2 Glucose Monitoring Sensors 4.3.3 Smartwatches for Noninvasive Glucose Monitoring 4.3.4 Deep Machine Learning for Diabetic Retinopathy Screening 4.4 Barriers in Diabetes Technology 4.5 Technical Solutions to Break the Barriers 4.6 Summary References Chapter 5. Role of Big Data Analytics in Industrial Revolution 4.0 5.1 Big Data Analytics 5.1.1 Data: Terminologies 5.1.2 Data Evolution: A Look-Back 5.1.2.1 Transformation: Data to Big Data 5.1.2.2 Data Formats and Sources: Data Growth 5.1.3 Big Data: A Comprehensive View 5.1.3.1 Definition 5.1.3.2 Data Analysis 5.1.3.2.1 Data Analysis 5.1.3.2.2 Data Analytics 5.1.3.3 Big Data vs. Statistics vs. Data Mining 5.1.3.3.1 Data Science 5.2 Big Data Components 5.2.1 Big Data Characteristics 5.2.1.1 Big Data Myths 5.2.2 Big Data Processing: Architecture 5.2.2.1 Traditional vs. Big Data Framework 5.2.3 Big Data-Related Technologies 5.2.4 Big Data: Industry 4.0 Applications 5.3 Big Data & Industry 4.0 5.3.1 Big Data Analytics: Essentials 5.3.2 Data Migration to Cloud 5.3.3 Predictive Analytics 5.3.4 Artificial Intelligence 5.4 Big Data Use Cases 5.4.1 Big Data Use Case: Social Good 5.4.1.1 An Epidemic: Preventive Care Management 5.4.1.2 Natural Resource Management: Oil and Gas 5.4.1.3 Agriculture 5.4.2 Big Data: Industry Use Case 5.4.2.1 Warehouse Management and Supply Chain 5.4.2.2 Automobile Industry 5.4.2.3 Pharmaceuticals 5.4.2.4 Sports Analytics 5.5 Big Data Roles 5.5.1 Data Scientist 5.5.2 Big Data Engineer 5.5.3 Machine Learning Engineer 5.5.4 Data Analyst 5.5.5 Business Analyst 5.5.6 Statisticians References Chapter 6. Big Data Infrastructure and Analytics for Education 4.0 6.1 Introduction 6.2 Industrial Revolutions 6.3 Advantages of Industry 4.0 in Education 6.4 System for Smart Education 6.4.1 Stakeholders 6.4.2 Dashboard 6.4.3 Internet of Things 6.4.4 Cloud Computing 6.4.5 AI in Smart Education 6.4.6 Augmented Reality 6.5 Big Data Infrastructure for Smart Education 6.5.1 Database and Distributed File System 6.5.2 Stream Processing 6.5.3 Batch Processing 6.5.4 Data Visualization 6.5.5 Data Processing Model 6.6 Big Data Analysis for Smart Education 6.6.1 Data Science 6.6.2 Data Analyst 6.6.3 Big Data Analytics 6.6.4 Text Analytics 6.6.5 Text Summarization 6.6.6 Question Answering (QA) 6.6.7 Sentiment Analysis (Opinion Mining) 6.6.8 Audio Analytics 6.6.9 Video Analytics 6.6.10 Social Media Analytics 6.7 Conclusion References Chapter 7. Text Analytics in Big Data Environments 7.1 Introduction 7.1.1 Need for Text Analytics 7.2 Text Analytics: Big Data Environment 7.2.1 Text Data Collection 7.2.1.1 Data Collection Methods 7.2.2 Data Storage 7.2.3 Text Preprocessing 7.2.4 Text Analysis 7.2.4.1 Text Classification 7.2.4.2 Text Clustering 7.2.4.3 Text Summarization 7.2.4.4 Sentimental Analysis 7.2.4.5 Topic Modeling 7.2.5 Result Interpretation 7.2.6 Visualization 7.3 Applications of Text Analytics 7.4 Issues and Research Challenges in Text Analytics 7.5 Tools for Text Analytics 7.6 Conclusion References Chapter 8. Business Data Analytics: Applications and Research Trends 8.1 Big Data Analytics and Business Analytics: An Introduction 8.2 Digital Revolution of Education 4.0 8.2.1 Education 4.0 8.2.2 Requirement of Education 4.0 in Industry 8.2.3 Benefits of Education 4.0 for Business Sector 8.2.4 Influence of Industrial Revolution 4.0 on Higher Education 8.3 Conceptual Framework of Big Data for Industry 4.0 8.3.1 Big Data Application Design 8.3.2 Preprocessing Input Data Streams 8.3.3 Distributed Infrastructure 8.3.4 Distribution of Results 8.4 Business Analytics 8.4.1 Business Analytics vs. Business Intelligence 8.4.1.1 Business Analytics (BA) 8.4.1.2 Business Intelligence (BI) 8.5 Applications of Big Data and Business Analytics 8.6 Challenges of Big Data and Business Analytics 8.6.1 Uncertainty of Data Management 8.6.2 Talent Gap 8.6.3 Synchronising the Data Sources 8.6.4 Issues with Data Integration 8.7 Open Research Directions 8.8 Conclusion References Chapter 9. Role of Big Data Analytics in the Financial Service Sector 9.1 Introduction 9.2 The Effect of Finance 4.0 in a Nutshell 9.2.1 Data Revolution 9.2.2 What Does Finance 4.0 Mean? 9.2.3 The Revolution of Finance Industry 9.2.4 Embrace Industry 4.0 in Finance Industry 9.2.5 Banking and Big Data 9.2.5.1 Easy to Customer Segment Identification 9.2.5.2 Adopt the Customized Familiarity 9.2.5.3 Client Behavioral Approach 9.2.5.4 Profit-Sharing Possibilities 9.2.5.5 Deduction of Deceitful Performance 9.3 Big Data in the Banking Industry 9.3.1 Four V's of Big Data 9.3.2 Arrangement of Big Data 9.3.3 Big Data Analysis in Banking 9.3.4 Leveraging Big Data Analysis 9.3.4.1 Improved Deception Revealing 9.3.4.2 Greater Risk Appraisal 9.3.4.3 Enlarged Customer Continued Possession 9.3.4.4 Service or Product Individuality 9.3.4.5 Efficient Client Criticism 9.3.5 Significant Role of Big Data in Banking and Finance 9.3.6 Prospect of Big Data in Finance Sector 9.3.7 The Banking Industry's Big Data Analytics Potential 9.3.7.1 Preventing Frauds 9.3.7.2 Identifying and Acquiring Customers 9.3.7.3 Retaining Customers 9.3.7.4 Enhancing Customer Experience 9.3.7.5 Optimizing Operations 9.3.7.6 Meeting Regulatory Requirements and Dealing with Setbacks in Real Time 9.3.7.7 Optimizing the Overall Product Portfolio/Improving Product Design 9.3.7.8 Increasing Transparency 9.3.8 Advantages of Big Data in Financial Sectors 9.3.8.1 Identification of Innovative Services 9.3.8.2 Minimize the Deception Movement 9.3.8.3 Enhanced Maneuvers 9.3.8.4 Improved Operations 9.3.8.5 Identifying and Analyzing Potential Issue 9.3.8.6 A Greater Understanding of Market Conditions 9.3.8.7 Better Customer Service 9.3.8.8 Endeavour to Accomplish a High Growth 9.3.8.9 Marketing Plan and Tactics 9.3.8.10 Designed Constructive Approach in Decrease Costs 9.4 Big Data Analytics in Finance Industry 9.4.1 Finance Analysis in Cloud 9.4.2 Finance Team Needs Big Data Experts: How to Find Them 9.4.3 Data Science in Banking and Finance 9.4.4 Big Data Analysis to Improve Finance Industry 9.4.5 Big Data Analysis in Finance: Pros and Cons 9.5 Sector of Finance Data Science 9.5.1 Data Science for the Internet Age 9.5.2 Modernize Data Science in Finance Industry 9.5.3 The Financial Sector Needs Data Science 9.5.4 Machine Learning in Finance Information 9.5.5 Sentiment Analysis in Finance or Service Sector 9.5.6 Predictive Analytics in Service or Finance Sector 9.5.7 Social Media Insights for Finance Industry 9.5.8 Analytics Tools for Finance Data 9.5.9 Finance Sector and Its Upcoming Role of Data Analysis 9.6 Conclusion Acknowledgments References Chapter 10. Role of Big Data Analytics in the Education Domain 10.1 Introduction 10.1.1 Industry 4.0 10.1.1.1 First Industrial Revolution (IR 1.0) 10.1.1.2 Second Industrial Revolution (IR 2.0) 10.1.1.3 Third Industrial Revolution (IR 3.0) 10.1.1.4 Fourth Industrial Revolution (IR 4.0) 10.1.2 Revolution of Education 10.1.3 Education 4.0 10.1.3.1 5 I's of Learning in Education 4.0 10.1.4 Big Data Analytics 10.2 Need for Big Data Analytics in Education 10.2.1 Learning Analytics 10.2.2 Predictive Analytics 10.2.3 Academic Analytics 10.2.4 Text Analytics 10.2.5 Visual Analytics 10.3 Applications of Big Data Analytics in Education 10.3.1 Creating Predictive Model 10.3.2 Personalized Curriculum 10.3.3 Adaptive Learning 10.3.4 Personalized Resources 10.3.5 Data-Driven Decision-Making Culture 10.3.6 Access Data Easier 10.3.7 Virtual Interview 10.3.8 Design a New Course 10.4 Advantages of Big Data in Education 10.5 Challenges in Implementing Big Data in Education 10.6 Education 4.0 in India 10.7 Case Study: Big Data Analytics in E-Learning 10.7.1 E-Learning Platforms 10.8 Conclusion References Chapter 11. Social Media Analytics 11.1 Introduction 11.2 Process of Social Media Analytics 11.2.1 Capture Data 11.2.2 Understand Data 11.2.3 Present Data 11.3 Social Media Analytics 11.3.1 Content Analysis 11.3.1.1 Topic Identification 11.3.1.2 Sentiment Analysis 11.3.1.3 Social Multimedia Analysis 11.3.2 Group and Network Analysis 11.3.2.1 Group Identification 11.3.2.2 Relationship Characterization 11.3.3 Prediction 11.4 Techniques and Algorithms 11.4.1 Techniques 11.4.1.1 NLP 11.4.1.2 News Analytics 11.4.1.3 Opinion Mining 11.4.1.4 Scraping 11.4.1.5 Text Analytics 11.4.2 Machine Learning and Deep Learning Algorithms 11.4.2.1 Artificial Neural Network (ANN) 11.4.2.2 SVM 11.4.2.3 Convolutional Neural Network (CNN) 11.4.2.4 Recurrent Neural Network (RNN) 11.4.2.5 Auto-Encoder (AE) 11.4.2.6 Deep Belief Network (DBN) 11.5 Tools 11.6 Research Challenges 11.7 Case Studies in Social Media Analytics 11.7.1 Barclays 11.7.2 Keen 11.7.3 Samsung 11.7.4 TOMS Shoes 11.7.5 Yale 11.7.6 Cisco 11.7.7 Kmart 11.8 Conclusion References Chapter 12. Robust Statistics: Methods and Applications 12.1 Introduction 12.2 History of Robust Statistics 12.3 Classical Statistics vs. Robust Statistics 12.4 Robust Statistical Measures 12.5 Robust Regression Procedures 12.6 Data Depth Procedures 12.7 Statistical Learning 12.7.1 Principal Component Analysis 12.7.2 Factor Analysis 12.7.3 Discriminant Analysis 12.7.4 Cluster Analysis 12.8 Robust Statistics in R 12.9 Summary References Chapter 13. Big Data in Tribal Healthcare and Biomedical Research 13.1 Introduction 13.1.1 Photographs Were Taken During the NRDMS Project Data Survey 13.1.2 NRDMS Project-Based Website (www.nrdms-bu.edu.in) 13.1.3 Big Data Approaches 13.2 Data Lifecycle 13.2.1 Big Data in Socioeconomic Status 13.3 Big Data in Genomic Research 13.3.1 Hadoop 13.3.2 Apache Spark 13.3.3 NGS Read Alignment 13.3.4 Variation Calling 13.3.5 Variant Annotation 13.3.6 Metagenomics 13.4 Big Data in Biomedical Research 13.5 Healthcare as a Big Data Repository 13.5.1 Electronic Health Records (EHR) 13.5.2 Digital Information about Healthcare and Big Data 13.6 Management of Big Data 13.7 Challenges in Healthcare Data 13.7.1 Storage 13.7.2 Data Cleansing 13.7.3 Combined Format 13.7.4 Accuracy 13.7.5 Image Preprocessing 13.7.6 Security 13.7.7 Metadata 13.7.8 Querying 13.7.9 Visualization 13.7.10 Data Distribution 13.8 Tribal Research in India 13.8.1 Indigenous Data 13.9 Conclusion 13.9.1 Priorities Acknowledgments References Chapter 14. PySpark toward Data Analytics 14.1 Introduction 14.1.1 Apache Spark 14.1.1.1 Spark Architecture I Resilient Distributed Datasets (RDD) II Directed Acyclic Graph (DAG) III Spark Context (SC) 14.1.2 PySpark 14.1.2.1 Prerequisites to PySpark 14.1.2.2 PySpark - Environment Setup 14.2 PySpark: SparkContext 14.2.1 SparkContext Parameters 14.2.2 SparkContext Example 14.3 PySpark Shared Variables 14.3.1 Broadcast Variables 14.3.1 Accumulators 14.4 PySpark: RDD (Resilient Distributed Dataset) 14.4.1 Transformations 14.4.2 Actions 14.4.3 Features of PySpark RDDs 14.4.3.1 In-Memory Computations 14.4.3.2 Lazy Evaluation 14.4.3.3 Fault-Tolerant 14.4.3.4 Immutability 14.4.3.5 Partitioning 14.4.3.6 Persistence 14.4.3.7 Coarse-Grained Operations 14.4.4 Creating RDD 14.4.3 Operations in RDD 14.5 PySpark DataFrames 14.5.1 Need of DataFrames 14.5.1.1 Processing Heterogeneous Data 14.5.1.2 Slicing and Dicing 14.5.2 Features of DataFrame 14.5.3 PySpark DataFrames 14.5.4 Creating DataFrame from RDD 14.5.5 Creating the DataFrame from CSV, JSON and Text Files 14.5.6 DataFrame Manipulations 14.5.6.1 How to Retrieve the Datatype of Columns in Our Dataset? 14.5.6.2 How to View the First n Observation? 14.5.6.3 How to Get the Statistics Summary of Numerical Columns in a DataFrame (Standard Deviance, Mean, Max, Count, Min)? 14.5.6.4 How to Find the Distinct Data and Remove Duplicate Values? 14.5.6.5 Removing and Filling Null Values from Data Frames 14.6 PySpark MLlib (Machine Learning Libraries) 14.6.1 Various Tools Provided by MLlib 14.6.1.1 Why PySpark MLlib 14.6.2 PySpark MLlib Algorithms 14.6.2.1 Classification Using PySpark MLlib 14.6.2.2 Logistic Regression 14.6.2.3 Logistic Regression Using Logistic Regression With LBFGS 14.6.2.4 Collaborative Filtering 14.6.2.5 Rating Class in pyspark.mllib.recommendation 14.6.2.6 Alternating Least Squares (ALS) 14.6.2.7 Model Evaluation Using MSE 14.6.2.8 Clustering Chapter 15. How to Implement Data Lake for Large Enterprises 15.1 What Is a Data Warehouse? 15.1.1 Roles of Data Warehouse for Industries 15.2 What Is a Data Lake? 15.3 Why Do We Need Data Lake? 15.4 Overview of Data Lake in Cloud 15.5 Key Considerations for Data Lake Architecture 15.6 Phases of Data Lake Implementation 15.6.1 Data Lake Architecture on Amazon Web Services 15.6.2 Data Lake Architecture on Google Cloud Platform 15.6.3 Azure Cloud Data Lake 15.7 What to Load into Your Data Lake? 15.8 A Cloud Data Lake Journey 15.8.1 Cloud Infrastructures 15.8.2 Data Lake Storage 15.8.3 Data Transformation 15.8.4 Data Security 15.9 Conclusion References Chapter 16. A Novel Application of Data Mining Techniques for Satellite Performance Analysis 16.1 Introduction 16.2 Data Generation and Analysis 16.3 Data Mining 16.4 Artificial Satellites and Data Mining 16.5 Statistical Techniques for Satellite Data Analysis 16.6 Novel Application 16.7 Selection of an Appropriate Data Mining Technique 16.8 Satellite Telemetry Data: Association Mining 16.9 Satellite Telemetry Data: Decision Tree Technique 16.10 Satellite Telemetry Data: A Modified Brute-Force Rule-Induction Algorithm 16.11 Methodology 16.12 Conclusion References Chapter 17. Big Data Analytics: A Text Mining Perspective and Applications in Biomedicine and Healthcare 17.1 Introduction 17.1.1 Big Data 17.1.2 Text Mining 17.1.3 Applications in Biomedicine and Healthcare 17.2 Text Mining Overview and Related Fields 17.2.1 Definition and Overview 17.2.2 Data Mining 17.2.3 Natural Language Processing 17.2.4 Machine Learning 17.2.5 Text Mining: Big Picture 17.3 Phases and Tasks of Text Mining 17.3.1 Information Retrieval 17.3.1.1 IR and Big Data 17.3.1.2 Big Data File System Architecture 17.3.2 Information Extraction 17.3.2.1 Named Entity Recognition 17.3.2.2 Relation Extraction 17.3.2.3 Event Extraction 17.3.2.4 IE and Big Data 17.3.3 Knowledge Discovery and Hypothesis Generation 17.3.3.1 TM and Big Data 17.4 Applications in Biomedicine 17.4.1 Biomedical Text Mining 17.4.2 Biomedical Text Mining Resources 17.4.3 Bio-Named Entity Recognition 17.4.4 Bio-Relation Extraction 17.4.5 Event Extraction 17.4.6 Applications 17.4.7 Case Studies in Cancer Literature 17.5 Applications in Healthcare 17.5.1 Healthcare Text Mining 17.5.2 Electronic Health Records Mining 17.5.3 Health-Related Social Media Mining 17.6 Conclusion References Index