| Description |
1 online resource |
| Contents |
Preface xv List of Contributors xxi List of Figures xxv List of Tables xxix List of Abbreviations xxxi 1 Pattern Analysis of COVID-19 Death and Recovery Cases Data of Countries Using Greedy Biclustering Algorithm 1 1.1 Introduction 2 1.2 Problem Description 3 1.2.1 Greedy Approach: Bicluster Size Maximization Based Fitness Function 4 1.2.2 Data Description 5 1.3 Proposed Work: COVID 19 Pattern Identification Using Greedy Biclustering 7 1.4 Results and Discussions 8 1.5 Conclusion 18 1.6 Acknowledgements 18 References 18 2 Artificial Fish Swarm Optimization Algorithm with Hill Climbing Based Clustering Technique for Throughput Maximization in Wireless Multimedia Sensor Network 23 2.1 Introduction 24 2.2 The Proposed AFSA-HC Technique 27 2.2.1 AFSA-HC Based Clustering Phase 28 2.2.2 Deflate-Based Data Aggregation Phase 33 2.2.3 Hybrid Data Transmission Phase 34 2.3 Performance Validation 34 2.4 Conclusion 40 References 40 3 Analysis of Machine Learning Techniques for Spam Detection 43 3.1 Introduction 44 3.1.1 Ham Messages 44 3.1.2 Spam Messages 44 3.2 Types of Spam Attack 45 3.2.1 Email Phishing 45 3.2.2 Spear Phishing 45 3.2.3 Whaling 46 3.3 Spammer Methods 46 3.4 Some Prevention Methods From User End 46 3.4.1 Protect Email Addresses 46 3.4.2 Preventing Spam from Being Sent 47 3.4.3 Block Spam to be Delivered 48 3.4.4 Identify and Separate Spam After Delivery 48 3.4.4.1 Targeted Link Analysis 48 3.4.4.2 Bayesian Filters 48 3.4.5 Report Spam 48 3.5 Machine Learning Algorithms 48 3.5.1 Naïve Bayes (NB) 48 3.5.2 Random Forests (RF) 49 3.5.3 Support Vector Machine (SVM) 49 3.5.4 Logistic Regression (LR) 50 3.6 Methodology 51 3.6.1 Database Used 51 3.6.2 Work Flow 51 3.7 Results and Analysis 52 3.7.1 Performance Metric 52 3.7.2 Experimental Results 52 3.7.2.1 Cleaning Data by Removing Punctuations, White Spaces, and Stop Words 54 3.7.2.2 Stemming the Messages 55 3.7.2.3 Analyzing the Common Words from the Spam and Ham Messages 55 3.7.3 Analyses of Machine Learning Algorithms 55 3.7.3.1 Accuracy Score Before Stemming 55 3.7.3.2 Accuracy Score After Stemming 55 3.7.3.3 Splitting Dataset into Train and Test Data 56 3.7.3.4 Mapping Confusion Matrix 58 3.7.3.5 Accuracy 58 3.8 Conclusion and Future Work 59 References 59 4 Smart Sensor Based Prognostication of Cardiac Disease Prediction Using Machine Learning Techniques 63 4.1 Introduction 64 4.2 Literature Survey 65 4.3 Proposed Method 67 4.4 Data Collection in IoT 67 4.4.1 Fetching Data from Sensors 68 4.4.2 K-Nearest Neighbor Classifier 69 4.4.3 Random Forest Classifier 70 4.4.4 Decision Tree Classifier 70 4.4.5 Extreme Gradient Boost Classifier 71 4.5 Results and Discussions 72 4.6 Conclusion 78 4.7 Acknowledgements 78 References 78 5 Assimilate Machine Learning Algorithms in Big Data Analytics: Review 81 5.1 Introduction 82 5.2 Literature Survey 86 5.3 Big Data 89 5.4 Machine Learning 92 5.5 File Categories 95 5.6 Storage And Expenses 95 5.7 The Device Learning Anatomy 96 5.8 Machine Learning Technology Methods in Big Data Analytics 97 5.9 Structure Mapreduce 97 5.10 Associated Investigations 98 5.11 Multivariate Data Coterie in Machine Learning 99 5.12 Machine Learning Algorithm 99 5.12.1 Machine Learning Framework 99 5.12.2 Parametric and Non-Parametric Techniques in Machine Learning 99 5.12.2.1 Bias 100 5.12.2.2 Variance 100 5.12.3 Parametric Techniques 101 5.12.3.1 Linear Regression 101 5.12.3.2 Decision Tree 101 5.12.3.3 Naive Bayes 102 5.12.3.4 Support Vector Machine 102 5.12.3.5 Random Forest 102 5.12.3.6 K-Nearest Neighbor 103 5.12.3.7 Deep Learning 104 5.12.3.8 Linear Vector Quantization (LVQ) 104 5.12.3.9 Transfer Learning 104 5.12.4 Non-Parametric Techniques 105 5.12.4.1 K-Means Clustering 105 5.12.4.2 Principal Component Analysis 105 5.12.4.3 A Priori Algorithm 105 5.12.4.4 Reinforcement Learning (RL) 105 5.12.4.5 Semi-Supervised Learning 106 5.13 Machine Learning Technology Assessment Parameters 106 5.13.1 Ranking Performance 106 5.13.2 Loss in Logarithmic Form 106 5.13.3 Assessment Measures 107 5.13.3.1 Accuracy 107 5.13.3.2 Precision/Specificity 107 5.13.3.3 Recall 107 5.13.3.4 F-Measure 108 5.13.4 Mean Definite Error (MAE) 108 5.13.5 Mean Quadruple Error (MSE) 108 5.14 Correlation of Outcomes of ML Algorithms 109 5.15 Applications 109 5.15.1 Economical Facilities 109 5.15.2 Business and Endorsement 110 5.15.3 Government Bodies 110 5.15.4 Hygiene 110 5.15.5 Transport 110 5.15.6 Fuel and Energy 111 5.15.7 Spoken Validation 111 5.15.8 Perception of the Device 111 5.15.9 Bio-Surveillance 111 5.15.10 Mechanization or Realigning 111 5.15.11 Mining Text 112 5.16 Conclusion 112 References 113 6 Resource Allocation Methodologies in Cloud Computing: A Review and Analysis 115 6.1 Introduction 116 6.1.1 Cloud Services Models 116 6.1.1.1 Infrastructure as a Service 117 6.1.1.2 Platform as a Service 118 6.1.1.3 Software as a Service 118 6.1.2 Types of Cloud Computing 118 6.1.2.1 Public Cloud 119 6.1.2.2 Private Cloud 119 6.1.2.3 Community Cloud 120 6.1.2.4 Hybrid Cloud 121 6.2 Resource Allocations in Cloud Computing 121 6.2.1 Static Allocation 122 6.2.2 Dynamic Allocation 122 6.3 Dynamic Resource Allocation Models in Cloud Computing 123 6.3.1 Service-Level Agreement Based Dynamic Resource Allocation Models 124 6.3.2 Market-Based Dynamic Resource Allocation Models 125 6.3.3 Utilization-Based Dynamic Resource Allocation Models 126 6.3.4 Task Scheduling in Cloud Computing 127 6.4 Research Challenges 130 6.5 Future Research Paths 131 6.6 Advantages and Disadvantages 131 6.7 Conclusion 135 References 135 7 Role of Machine Learning in Big Data 139 7.1 Introduction 140 7.2 Related Work 141 7.3 Tools in Big Data 142 7.3.1 Batch Analysis Big Data Tools 142 7.3.2 Stream Analysis Big Data Tools 143 7.3.3 Interactive Analysis Big Data Tools 144 7.4 Machine Learning Algorithms in Big Data 145 7.5 Applications of Machine Learning in Big Data 151 7.6 Challenges of Machine Learning in Big Data 154 7.6.1 Volume 154 7.6.2 Variety 156 7.6.3 Velocity 157 7.6.4 Veracity 159 7.7 Conclusion 160 References 161 8 Healthcare System for COVID-19: Challenges and Developments 165 8.1 Introduction 166 8.2 Related Work 167 8.3 IoT with Architecture 169 8.4 IoHT Security Requirements and Challenges 170 8.5 COVID-19 (Coronavirus Disease 2019) 172 8.6 The Potential of IoHT in COVID-19 Like Disease Control 173 8.7 The Current Applications of IoHT During COVID-19 175 8.7.1 Using IoHT to Dissect an Outbreak 175 8.7.2 Using IoHT to Ensure Compliance to Quarantine 176 8.7.3 Using IoHT to Manage Patient Care 176 8.8 IoHT Development for COVID-19 177 8.8.1 Smart Home 178 8.8.2 Smart Office 178 8.8.3 Smart Hotel 178 8.8.4 Smart Hospitals 178 8.9 Conclusion 179 References 179 9 An Integrated Approach of Blockchain & Big Data in Health Care Sector 183 9.1 Introduction 184 9.2 Blockchain for Health care 185 9.2.1 Healthcare data sharing through gem Network 186 9.2.2 OmniPHR 187 9.2.3 Medrec 188 9.2.4 PSN (Pervasive Social Network) System 189 9.2.5 Healthcare Data Gateway 190 9.2.6 Resources that are virtual 190 9.3 Overview of Blockchain & Big data in health care 191 9.3.1 Big Data in Healthcare 191 9.3.2 Blockchain in Health Care 192 9.3.3 Benefits of Blockchain in Healthcare 193 9.3.3.1 Master patient indices 193 9.3.3.2 Supply chain management 193 9.3.3.3 Claims adjudication 193 9.3.3.4 Interoperability 194 9.3.3.5 Single, longitudinal patient records 194 9.4 Application of Big Data for Blockchain 194 9.4.1 Smart Ecosystem 194 9.4.2 Digital Trust 195 9.4.3 Cybersecurity 195 9.4.4 Fighting Drugs 195 9.4.5 Online Accessing of Patient's Data 196 9.4.6 Research as well as Development 196 9.4.7 Management of Data 196 9.4.8 Due to privacy storing of off-chain data 196 9.4.9 Collaboration of patient data 197 9.5 Solutions of Blockchain For Big Data in Health Care 197 9.6 Conclusion and Future Scope 198 References 199 10 Cloud Resource Management for Network Cameras 207 10.1 Introduction 207 10.2 Resource Analysis 210 10.2.1 Network Cameras 210 10.2.2 Resource Management on Cloud Environment 210 10.2.3 Image and Video Analysis 213 10.3 Cloud Resource Management Problems 214 10.4 Cloud Resource Manager 216 10.4.1 Evaluation of Performance 217 10.4.2 View of Resource Requirements 217 10.5 Bin Packing 218 10.5.1 Analysis of Dynamic Bin Packing 219 10.5.2 MinTotal DBP Problem 220 10.6 Resource Monitoring and Scaling 222 10.7 Conclusion 224 References 225 11 Software-Defined Networking for Healthcare Internet of Things 231 11.1 Introduction 231 11.2 Healthcare Internet of Things 233 11.2.1 Challenges in H-IoT 238 11.3 Software-Defined Networking 239 11.4 Opportunities, challenges, and possible solutions 243 11.5 Conclusion 245 References 246 12 Cloud Computing in the Public Sector: A Study 249 12.1 Introduction 250 12.2 History and Evolution of Cloud Computing 251 12.3 Application of Cloud Computing 252 12.4 Advantages of Cloud Computing 258 12.5 Challenges 263 12.6 Conclusion 269 13 Big Data Analytics: An overview 271 13.1 Introduction 271 13.2 Related Work 272 13.2.1 Big Data: What Is It? 275 13.2.1.1 Characteristics of Big Data 276 13.2.2 Big Data Analytics: What Is It? 277 13.3 Hadoop and Big Data 278 13.4 Big Data Analytics Framework 279 13.5 Big Data Analytics Techniques 280 13.5.1 Partitioning on Big Data 280 13.5.2 Sampling on Big Data 281 13.5.3 Sampling-Based Approximation 281 13.6 Big Social Data Analytics 281 13.7 Applications 282 13.7.1 Manufacturing Production 282 13.7.2 Smart Grid 283 13.7.3 Outbreak of Flu Prediction from Social Site 283 13.7.4 Sentiment Analysis of Twitter Data 283 13.8 Electricity Price Forecasting 284 13.9 Security Situational Analysis for Smart Grid 285 13.10 Future Scope 285 13.11 Challenges 285 13.12 Conclusion 286 References 286 14 Video Usefulness Detection in Big Surveillance Syst .. |
| Summary |
Cloud Computing and Big Data technologies have become the new descriptors of the digital age. The global amount of digital data has increased more than nine times in volume in just five years and by 2030 its volume may reach a staggering 65 trillion gigabytes. This explosion of data has led to opportunities and transformation in various areas such as healthcare, enterprises, industrial manufacturing and transportation. New Cloud Computing and Big Data tools endow researchers and analysts with novel techniques and opportunities to collect, manage and analyze the vast quantities of data. In Cloud and Big Data Analytics, the two areas of Swarm Intelligence and Deep Learning are a developing type of Machine Learning techniques that show enormous potential for solving complex business problems. Deep Learning enables computers to analyze large quantities of unstructured and binary data and to deduce relationships without requiring specific models or programming instructions. This book introduces the state-of-the-art trends and advances in the use of Machine Learning in Cloud and Big Data Analytics. The book will serve as a reference for Data Scientists, systems architects, developers, new researchers and graduate level students in Computer and Data science. The book will describe the concepts necessary to understand current Machine Learning issues, challenges and possible solutions as well as upcoming trends in Big Data Analytics |
| Notes |
Subhendu Kumar Pani, Somanath Tripathy, George Jandieri, Sumit Kundu, Talal Ashraf Butt |
| Subject |
Big data.
|
|
Machine learning.
|
|
Cloud computing.
|
|
COMPUTERS / Database Management / Data Mining
|
|
SCIENCE / Energy
|
|
Big data
|
|
Cloud computing
|
|
Machine learning
|
| Form |
Electronic book
|
| Author |
Pani, Subhendu Kumar, 1980- editor.
|
|
Tripathy, Somanath, editor.
|
|
Jandieri, George, editor.
|
|
Kundu, Sumit, editor.
|
|
Butt, Talal Ashraf, editor.
|
| ISBN |
9788770221818 |
|
8770221812 |
|
9781003337218 |
|
100333721X |
|
9781000793550 |
|
1000793559 |
|
9781000796322 |
|
1000796329 |
|
