Role of Data-Intensive Distributed Computing Systems in Designing Data Solutions

This book discusses the application of data systems and data-driven infrastructure in existing industrial systems in order to optimize workflow, utilize hidden potential, and make existing systems free from vulnerabilities. The book discusses application of data in the health sector, public transportation, the financial institutions, and in battling natural disasters, among others. Topics include real-time applications in the current big data perspective; improving security in IoT devices; data backup techniques for systems; artificial intelligence-based outlier prediction; machine learning in OpenFlow Network; and application of deep learning in blockchain enabled applications. This book is intended for a variety of readers from professional industries, organizations, and students. Foreword Preface Part I: On Integration of Data Systems and Traditional Computing Research Part II: Data-Driven Decision-Making Systems Part III: Data-Intensive Systems in Healthcare Acknowledgment Contents Part I On Integration of Data Systems and Traditional Computing Research Energy Conscious Scheduling for Fault-Tolerant Real-Time Distributed Computing Systems 1 Introduction 2 Energy Management 2.1 Dynamic Power Management 2.2 Dynamic Voltage and Frequency Scaling 3 Fault Tolerance 3.1 Fault-Tolerant Techniques 4 Joint Optimization of Energy and Fault Management 5 Conclusion References Secret Data Transmission Using Advanced Morphological Component Analysis and Steganography 1 Introduction 2 Suggested Method's Proposed Goals 3 Review of Literature 4 Suggested Method 5 Results and Discussion 6 Conclusions References Data Detection in Wireless Sensor Network Based on Convex Hull and Naïve Bayes Algorithm 1 Introduction 2 Related Work 2.1 Challenges and Problem Statement 2.2 Contributions 3 Proposed Methodology 3.1 *-25pt 3.1.1 N-Gram Extraction 3.2 Attribute-Based Encryption 3.3 Symmetric-Key Algorithm 3.4 Cipher Text Attribute–Based Encryption 3.5 Performs the Naïve Bayes Classifier on the Remaining Data Points 4 Experimental Results 4.1 Dataset 4.2 Performance Evaluation Parameters 5 Conclusions and Future Work References DSPPTD: Dynamic Scheme for Privacy Protection of Trajectory Data in LBS 1 Introduction 1.1 Problem Statement 2 Related Work 3 Our Proposed Scheme 3.1 Trajectory Processing Model 3.2 Trajectory Generator 3.3 Multilayer Perceptron and Deep Neural Network 3.4 K-Paths Trajectory Clustering 3.5 Trajectory Release 4 Performance Analysis of Privacy Protection Scheme 5 Conclusion References Part II Data-Driven Decision-Making Systems n-Layer Platform for Hi-Tech World 1 Introduction 2 Information Management Issues 3 Indian Administrative System 4 System Model 5 System Architecture 6 Unique Citizen Identification Code (UCIC) 7 Implementation and Performance Study 8 Discussion 9 Conclusion and Future Work References A Comparative Study of Machine Learning Techniques for Phishing Website Detection 1 Introduction 2 Literature Review 3 Phishing Websites Features 3.1 Address Bar Features 3.2 Abnormal Features 3.3 HTML and JavaScript Features 3.4 Domain Features 4 Proposed Method 5 Results and Discussions 6 Conclusions References Source Camera Identification Using Hybrid Feature Set and Machine Learning Classifiers 1 Introduction 2 Literature Review 2.1 Correlation-Based Method 2.2 Feature-Based Method 3 Method and Model 3.1 Image Preprocessing 3.2 Feature Extraction 3.3 Classification 4 Experiment and Result Analysis 5 Conclusion References Analysis of Blockchain Integration with Internet of Vehicles: Challenges, Motivation, and Recent Solution 1 Introduction 1.1 Organization and Reading Map 2 Architecture of IoV 2.1 Physical Layer 2.2 Communication Layer 2.3 Computation Layer 2.4 Application Layer 3 Challenges of IoV 3.1 Privacy Leak 3.1.1 Leakage in the Communication Layer 3.1.2 Vulnerabilities in the Computation Layer 3.1.3 Vulnerabilities in the Application Layer 3.2 High Mobility 3.3 Complexity in Wireless Networks 3.4 Latency-Critical Applications 3.5 Scalability and Heterogeneity 4 Overview of Blockchain Technology 4.1 Blocks 4.2 Miners 4.3 Nodes 5 Types of Blockchain Network 5.1 Public Blockchain 5.1.1 Benefits 5.1.2 Drawbacks 5.1.3 Applications 5.2 Private Blockchain 5.2.1 Benefits 5.2.2 Drawbacks 5.2.3 Applications 5.3 Consortium Blockchain 5.3.1 Benefits 5.3.2 Drawbacks 5.3.3 Applications 5.4 Hybrid Blockchain 5.4.1 Benefits 5.4.2 Drawbacks 5.4.3 Applications 6 Motivations of Using Blockchain in IoV 6.1 Decentralization 6.2 Availability 6.3 Transparency 6.4 Immutability 6.5 Exchanges Automation 7 Recent Solutions for IoV Integration with Blockchain 8 Applications of Blockchain in IoV 8.1 Incentive Mechanisms 8.2 Trust Establishment 8.3 Security and Privacy 9 Use Cases of Blockchained IoV 9.1 Supply-Chain Management 9.2 Manufacturing and Production 9.3 Settlements of Insurance Claim 9.4 Management of Fleet 9.5 Tracking of Vehicle 10 Future Scope of Blockchained IoV 10.1 Off-Chain Data Trust 10.2 Evaluation Criteria 10.3 Management of Resources 10.4 Data-Centric consensus 10.5 Blockchain for the Environment 10.6 Administration of Blockchain Platform 10.7 Evaluation of Performance 10.8 Design of New Services 10.9 Future Architecture Integrations 11 Conclusion References Reliable System for Bidding System Using Blockchain 1 Introduction 1.1 Features of Blockchain 1.1.1 Decentralization 1.1.2 Traceability 1.1.3 Immutability 1.1.4 Currency 2 Literature Survey 3 Notations Used in the Study 4 Proposed Work 5 Security Analysis 6 Conclusion References Security Challenges and Solutions for Next-Generation VANETs: An Exploratory Study 1 Introduction 2 Security Requirements 2.1 Security Services 2.2 Security Attacks 3 Security Mechanisms 3.1 Hybrid Device to Device (D2D) Message Authentication (HDMA) Scheme 3.2 Blockchain-Based Secure and Trustworthy Approach 3.3 Searchable Encryption with Vehicle Proxy Re-encryption-Based Scheme 3.4 Secure and Efficient AOMDV (SE-AOMDV) Routing Protocol 3.5 Socially Aware Security Message Forwarding Mechanism 3.6 Puzzle-Based Co-authentication (PCA) Scheme 3.7 Intelligent Drone-Assisted Security Scheme 3.8 Efficient Privacy-Preserving Anonymous Authentication Protocol 4 Comparative Study of Security Solutions 5 Conclusion and Future Work References iTeach: A User-Friendly Learning Management System 1 Introduction 2 Literature Review 3 Proposed Model 4 Comparison 5 Users Feedback Analysis 6 Conclusion and Future Scope References Part III Data-Intensive Systems in Health Care Analysis of High-Resolution CT Images of COVID-19 Patients 1 Introduction 2 Review of Literature 3 Materials and Methods 4 Results and Discussion 5 Conclusion References Attention-Based Deep Learning Approach for Semantic Analysis of Chest X-Ray Images Modality 1 Introduction 2 Literature Review 2.1 Image Captioning 2.2 Attention Mechanism 2.3 Medical Report Generation 3 Methodology 3.1 Overview 3.2 CNN Encoder 3.3 LSTM Decoder 3.4 Attention Mechanism 3.5 Model Architecture 4 Experiments 4.1 Dataset 4.2 Exploratory Data Analysis 4.3 Pre-processing and Training 4.4 Model without Attention Mechanism 4.4.1 Encoder Architecture 4.4.2 Decoder Architecture 4.4.3 Model Training 4.4.4 Model with an Attention Mechanism 4.4.5 Model Evaluation 4.5 Results 4.5.1 Case 1 4.5.2 Case 2 4.5.3 Case 3 4.5.4 Case 4 4.5.5 Case 5 4.5.6 Case 6 4.5.7 Conclusion References Medical Image Processing by Swarm-Based Methods 1 Introduction 2 Swarm-Based Methods 3 Feature Selection 4 Image Segmentation 5 Image Classification 6 Image Registration and Fusion 7 Conclusions A.1 Appendix A. Flowcharts of Swarm-Based Algorithms References Left Ventricle Volume Analysis in Cardiac MRI Images Using Convolutional Neural Networks 1 Introduction 1.1 Convolutional Neural Networks 1.2 Network Layers 1.3 CNN Tuning 1.4 Max Pooling 1.5 ReLU 1.6 Sigmoid 1.7 Dropout 1.8 Hyperparameters 1.8.1 Learning Rate 1.8.2 Patch Size 1.8.3 Batch Size 1.8.4 Epochs 1.9 Augmentation 1.9.1 Shift Augmentation 1.9.2 Rotation Augmentation 2 Literature Review 3 Overview of Our Work 4 Methodology 4.1 Dataset 4.2 Preprocess 4.3 Load and Split Dataset 4.4 Augmentation 4.5 Model 4.6 Training the Model 5 Results and Discussion 5.1 Environment 5.2 Evaluation Metrics 5.3 Training Details and Evaluation 5.4 Comparison with Other Models and Pre-processing Methods 6 Conclusion References MRI Image Analysis for Brain Tumor Detection Using Deep Learning 1 Introduction 2 Related Work 3 Proposed Work 3.1 Dataset Description 3.2 Data Augmentation 3.3 Loading and Splitting Augmented Data 3.4 CNN Architecture 4 Result and Analysis 5 Conclusion References Index