Оглавление
Группа авторов. Simulation and Analysis of Mathematical Methods in Real-Time Engineering Applications
Table of Contents
Guide
List of Illustrations
List of Tables
Pages
Simulation and Analysis of Mathematical Methods in Real-Time Engineering Applications
Preface
Acknowledgments
1. Certain Investigations on Different Mathematical Models in Machine Learning and Artificial Intelligence
1.1 Introduction
1.1.1 Knowledge-Based Expert Systems
1.1.2 Problem-Solving Techniques
1.2 Mathematical Models of Classification Algorithm of Machine Learning
1.2.1 Tried and True Tools
1.2.2 Joining Together Old and New
1.2.3 Markov Chain Model
1.2.4 Method for Automated Simulation of Dynamical Systems
1.2.5 kNN is a Case-Based Learning Method
1.2.6 Comparison for KNN and SVM
1.3 Mathematical Models and Covid-19
1.3.1 SEIR Model (Susceptible-Exposed-Infectious-Removed)
1.3.2 SIR Model (Susceptible-Infected-Recovered)
1.4 Conclusion
References
2. Edge Computing Optimization Using Mathematical Modeling, Deep Learning Models, and Evolutionary Algorithms
2.1 Introduction to Edge Computing and Research Challenges
2.1.1 Cloud-Based IoT and Need of Edge Computing
2.1.2 Edge Architecture
2.1.3 Edge Computing Motivation, Challenges and Opportunities
2.2 Introduction for Computational Offloading in Edge Computing
2.2.1 Need of Computational Offloading and Its Benefit
2.2.2 Computation Offloading Mechanisms
2.2.2.1 Offloading Techniques
2.3 Mathematical Model for Offloading
2.3.1 Introduction to Markov Chain Process and Offloading
2.3.1.1 Markov Chain Based Schemes
2.3.1.2 Schemes Based on Semi-Markov Chain
2.3.1.3 Schemes Based on the Markov Decision Process
2.3.1.4 Schemes Based on Hidden Markov Model
2.3.2 Computation Offloading Schemes Based on Game Theory
2.4 QoS and Optimization in Edge Computing
2.4.1 Statistical Delay Bounded QoS
2.4.2 Holistic Task Offloading Algorithm Considerations
2.5 Deep Learning Mathematical Models for Edge Computing
2.5.1 Applications of Deep Learning at the Edge
2.5.2 Resource Allocation Using Deep Learning
2.5.3 Computation Offloading Using Deep Learning
2.6 Evolutionary Algorithm and Edge Computing
2.7 Conclusion
References
3. Mathematical Modelling of Cryptographic Approaches in Cloud Computing Scenario
3.1 Introduction to IoT
3.1.1 Introduction to Cloud
3.1.2 General Characteristics of Cloud
3.1.3 Integration of IoT and Cloud
3.1.4 Security Characteristics of Cloud
3.2 Data Computation Process
3.2.1 Star Cubing Method for Data Computation
3.2.1.1 Star Cubing Algorithm
3.3 Data Partition Process
3.3.1 Need for Data Partition
3.3.2 Shamir Secret (SS) Share Algorithm for Data Partition
3.3.3 Working of Shamir Secret Share
3.3.4 Properties of Shamir Secret Sharing
3.4 Data Encryption Process
3.4.1 Need for Data Encryption
3.4.2 Advanced Encryption Standard (AES) Algorithm
3.4.2.1 Working of AES Algorithm
3.5 Results and Discussions
3.6 Overview and Conclusion
References
4. An Exploration of Networking and Communication Methodologies for Security and Privacy Preservation in Edge Computing Platforms
Introduction
4.1 State-of-the-Art Edge Security and Privacy Preservation Protocols
4.1.1 Proxy Re-Encryption (PRE)
4.1.2 Attribute-Based Encryption (ABE)
4.1.3 Homomorphic Encryption (HE)
4.2 Authentication and Trust Management in Edge Computing Paradigms
4.2.1 Trust Management in Edge Computing Platforms
4.2.2 Authentication in Edge Computing Frameworks
4.3 Key Management in Edge Computing Platforms
4.3.1 Broadcast Encryption (BE)
4.3.2 Group Key Agreement (GKA)
4.3.3 Dynamic Key Management Scheme (DKM)
4.3.4 Secure User Authentication Key Exchange
4.4 Secure Edge Computing in IoT Platforms
4.5 Secure Edge Computing Architectures Using Block Chain Technologies
4.5.1 Harnessing Blockchain Assisted IoT in Edge Network Security
4.6 Machine Learning Perspectives on Edge Security
4.7 Privacy Preservation in Edge Computing
4.8 Advances of On-Device Intelligence for Secured Data Transmission
4.9 Security and Privacy Preservation for Edge Intelligence in Beyond 5G Networks
4.10 Providing Cyber Security Using Network and Communication Protocols for Edge Computing Devices
4.11 Conclusion
References
5. Nature Inspired Algorithm for Placing Sensors in Structural Health Monitoring System - Mouth Brooding Fish Approach
5.1 Introduction
5.2 Structural Health Monitoring
5.3 Machine Learning
5.3.1 Methods of Optimal Sensor Placement
5.4 Approaches of ML in SHM
5.5 Mouth Brooding Fish Algorithm
5.5.1 Application of MBF System
5.6 Case Studies On OSP Using Mouth Brooding Fish Algorithms
5.7 Conclusions
References
6. Heat Source/Sink Effects on Convective Flow of a Newtonian Fluid Past an Inclined Vertical Plate in Conducting Field
6.1 Introduction
6.2 Mathematic Formulation and Physical Design
6.3 Discusion of Findings. 6.3.1 Velocity Profiles
6.3.2 Temperature Profile
6.3.3 Concentration Profiles
6.4 Conclusion
References
7. Application of Fuzzy Differential Equations in Digital Images Via Fixed Point Techniques
7.1 Introduction
7.2 Preliminaries
7.3 Applications of Fixed-Point Techniques
7.4 An Application
7.5 Conclusion
References
8. The Convergence of Novel Deep Learning Approaches in Cybersecurity and Digital Forensics
8.1 Introduction
8.2 Digital Forensics
8.2.1 Cybernetics Schemes for Digital Forensics
8.2.2 Deep Learning and Cybernetics Schemes for Digital Forensics
8.3 Biometric Analysis of Crime Scene Traces of Forensic Investigation. 8.3.1 Biometric in Crime Scene Analysis
8.3.1.1 Parameters of Biometric Analysis
8.3.2 Data Acquisition in Biometric Identity
8.3.3 Deep Learning in Biometric Recognition
8.4 Forensic Data Analytics (FDA) for Risk Management
8.5 Forensic Data Subsets and Open-Source Intelligence for Cybersecurity
8.5.1 Intelligence Analysis
8.5.2 Open-Source Intelligence
8.6 Recent Detection and Prevention Mechanisms for Ensuring Privacy and Security in Forensic Investigation. 8.6.1 Threat Investigation
8.6.2 Prevention Mechanisms
8.7 Adversarial Deep Learning in Cybersecurity and Privacy
8.8 Efficient Control of System-Environment Interactions Against Cyber Threats
8.9 Incident Response Applications of Digital Forensics
8.10 Deep Learning for Modeling Secure Interactions Between Systems
8.11 Recent Advancements in Internet of Things Forensics
8.11.1 IoT Advancements in Forensics
8.11.2 Conclusion
References
9. Mathematical Models for Computer Vision in Cardiovascular Image Segmentation
9.1 Introduction. 9.1.1 Computer Vision
9.1.2 Present State of Computer Vision Technology
9.1.3 The Future of Computer Vision
9.1.4 Deep Learning
9.1.5 Image Segmentation
9.1.6 Cardiovascular Diseases
9.2 Cardiac Image Segmentation Using Deep Learning
9.2.1 MR Image Segmentation
9.2.1.1 Atrium Segmentation. 9.2.1.1.1 Fully Convolutional Network Based Segmentation
9.2.1.1.2 Analysis of Images in Both Memory and Time Efficiency
9.2.1.1.3 Smearing Structural Conditions
9.2.1.1.4 Multi-Task Learning
9.2.1.1.5 Multi-Step Systems
9.2.1.1.6 Hybrid Segmentation Methods
9.2.1.2 Atrial Segmentation
9.2.1.3 Cicatrix Segmentation
9.2.1.4 Aorta Segmentation
9.2.2 CT Image Segmentation for Cardiac Disease
9.2.2.1 Segmentation of Cardiac Substructure
9.2.2.1.1 2-Step Segmentation
9.2.2.1.2 CNN Multiple Views
9.2.2.1.3 Hybrid Loss
9.2.2.2 Angiography
9.2.2.2.1 CNN Post and (or) Preprocessing Phases
9.2.2.2.2 Point to Point CNNs
9.2.2.3 CA Plaque and Calcium Segmentation
9.2.2.3.1 Two-Step Segmentation
9.2.2.3.2 Direct Segmentation
9.2.3 Ultrasound Cardiac Image Segmentation
9.2.3.1 2-Dimensional Left Ventricle Segmentation. 9.2.3.1.1 DL+ Deformable Models
9.2.3.1.2 Incorporating Temporal Consistency
9.2.3.1.3 Incorporating Unmarked Data
9.2.3.1.4 Incorporating Data from Different Domains
9.2.3.2 3-Dimensional Left Ventricle Segmentation
9.2.3.3 Segmentation of Left Atrium
9.2.3.4 Multi-Chamber Segmentation
9.2.3.5 Aortic Valve Segmentation
9.3 Proposed Method
9.4 Algorithm Behaviors and Characteristics
9.5 Computed Tomography Cardiovascular Data
9.5.1 Graph Cuts to Segment Specific Heart Chambers
9.5.2 Ringed Graph Cuts with Multi-Resolution
9.5.3 Simultaneous Chamber Segmentation using Arbitrary Rover
9.5.3.1 The Arbitrary Rover Algorithm
9.5.4 Static Strength Algorithm
9.6 Performance Evaluation. 9.6.1 Ringed Graph Cuts with Multi-Resolution
9.6.2 The Arbitrary Rover Algorithm
9.6.3 Static Strength Algorithm
9.6.4 Comparison of Three Algorithm
9.7 Conclusion
References
10. Modeling of Diabetic Retinopathy Grading Using Deep Learning
10.1 Introduction
10.2 Related Works
10.3 Methodology
10.4 Dataset
10.5 Results and Discussion
10.6 Conclusion
References
11. Novel Deep-Learning Approaches for Future Computing Applications and Services
11.1 Introduction
11.2 Architecture
11.2.1 Convolutional Neural Network (CNN)
11.2.2 Restricted Boltzmann Machines and Deep Belief Network
11.3 Multiple Applications of Deep Learning
11.4 Challenges
11.5 Conclusion and Future Aspects
References
12. Effects of Radiation Absorption and Aligned Magnetic Field on MHD Cassion Fluid Past an Inclined Vertical Porous Plate in Porous Media
12.1 Introduction
12.2 Physical Configuration and Mathematical Formulation
12.2.1 Skin Friction
12.2.2 Nusselt Number
12.2.3 Sherwood Number
12.3 Discussion of Result
12.3.1 Velocity Profiles
12.3.2 Temperature Profiles
12.3.3 Concentration Profiles
12.4 Conclusion
References
13. Integrated Mathematical Modelling and Analysis of Paddy Crop Pest Detection Framework Using Convolutional Classifiers
13.1 Introduction
13.2 Literature Survey
13.3 Proposed System Model
13.3.1 Disease Prediction
13.3.2 Insect Identification Algorithm
13.4 Paddy Pest Database Model
13.5 Implementation and Results
13.6 Conclusion
References
14. A Novel Machine Learning Approach in Edge Analytics with Mathematical Modeling for IoT Test Optimization
14.1 Introduction: Background and Driving Forces
14.2 Objectives
14.3 Mathematical Model for IoT Test Optimization
14.4 Introduction to Internet of Things (IoT)
14.5 IoT Analytics
14.5.1 Edge Analytics
14.6 Survey on IoT Testing
14.7 Optimization of End-User Application Testing in IoT
14.8 Machine Learning in Edge Analytics for IoT Testing
14.9 Proposed IoT Operations Framework Using Machine Learning on the Edge
14.9.1 Case Study 1 - Home Automation System Using IoT
14.9.2 Case Study 2 – A Real-Time Implementation of Edge Analytics in IBM Watson Studio
14.9.3 Optimized Test Suite Using ML-Based Approach
14.10 Expected Advantages and Challenges in Applying Machine Learning Techniques in End-User Application Testing on the Edge
14.11 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
