Simulation and Analysis of Mathematical Methods in Real-Time Engineering Applications
Description
Written and edited by a group of international experts in the field, this exciting new volume covers the state of the art of real-time applications of computer science using mathematics.
This breakthrough edited volume highlights the security, privacy, artificial intelligence, and practical approaches needed by engineers and scientists in all fields of science and technology. It highlights the current research, which is intended to advance not only mathematics but all areas of science, research, and development, and where these disciplines intersect. As the book is focused on emerging concepts in machine learning and artificial intelligence algorithmic approaches and soft computing techniques, it is an invaluable tool for researchers, academicians, data scientists, and technology developers.
The newest and most comprehensive volume in the area of mathematical methods for use in real-time engineering, this groundbreaking new work is a must-have for any engineer or scientist's library. Also useful as a textbook for the student, it is a valuable contribution to the advancement of the science, both a working handbook for the new hire or student, and a reference for the veteran engineer.
More details
Other editions
Additional editions
Persons
T. Ananth Kumar, PhD, is an assistant professor at the IFET College of Engineering, Anna University, Chennai. He received his PhD degree in VLSI design from Manonmaniam Sundaranar University, Tirunelveli. He is the recipient of the Best Paper Award at INCODS 2017. He is a life member of ISTE, has numerous patents to his credit and has written many book chapters for a variety of well-known publishers.
E. Golden Julie, PhD, is a senior assistant professor in the Department of Computer Science and Engineering, Anna university, Regional campus, Tirunelveli. She earned her doctorate in information and communication engineering from Anna University, Chennai in 2017. She has over twelve years of teaching experience and has published over 34 papers in various international journals and presented more than 20 papers at technical conferences. She has written ten book chapters for multiple publishers and is a reviewer for many scientific and technical journals.
Y. Harold Robinson, PhD, is currently teaching at the School of Information Technology and Engineering, Vellore Institute of Technology, Vellore. He earned his doctorate in information and communication engineering from Anna University, Chennai in 2016. He has more than 15 years of experience in teaching and has published more than 50 papers in various international journals. He has also presented more than 45 papers at technical conferences and has written four book chapters. He is a reviewer for many scientific journals, as well.
S. M. Jaisakthi,PhD, is an associate professor at the School of Computer Science & Engineering, at the Vellore Institute of Technology. She earned her doctorate from Anna University, Chennai. She has published many research publications in refereed international journals and in proceedings of international conferences.
Content
Preface xv
Acknowledgments xix
1 Certain Investigations on Different Mathematical Models in Machine Learning and Artificial Intelligence 1
Ms. Akshatha Y and Dr. S Pravinth Raja
1.1 Introduction 2
1.1.1 Knowledge-Based Expert Systems 2
1.1.2 Problem-Solving Techniques 3
1.2 Mathematical Models of Classification Algorithm of Machine Learning 4
1.2.1 Tried and True Tools 5
1.2.2 Joining Together Old and New 6
1.2.3 Markov Chain Model 7
1.2.4 Method for Automated Simulation of Dynamical Systems 7
1.2.5 kNN is a Case-Based Learning Method 9
1.2.6 Comparison for KNN and SVM 10
1.3 Mathematical Models and Covid-19 12
1.3.1 SEIR Model (Susceptible-Exposed-Infectious-Removed) 13
1.3.2 SIR Model (Susceptible-Infected-Recovered) 14
1.4 Conclusion 15
References 15
2 Edge Computing Optimization Using Mathematical Modeling, Deep Learning Models, and Evolutionary Algorithms 17
P. Vijayakumar, Prithiviraj Rajalingam and S. V. K. R. Rajeswari
2.1 Introduction to Edge Computing and Research Challenges 18
2.1.1 Cloud-Based IoT and Need of Edge Computing 18
2.1.2 Edge Architecture 19
2.1.3 Edge Computing Motivation, Challenges and Opportunities 21
2.2 Introduction for Computational Offloading in Edge Computing 24
2.2.1 Need of Computational Offloading and Its Benefit 25
2.2.2 Computation Offloading Mechanisms 27
2.2.2.1 Offloading Techniques 29
2.3 Mathematical Model for Offloading 30
2.3.1 Introduction to Markov Chain Process and Offloading 31
2.3.1.1 Markov Chain Based Schemes 32
2.3.1.2 Schemes Based on Semi-Markov Chain 32
2.3.1.3 Schemes Based on the Markov Decision Process 33
2.3.1.4 Schemes Based on Hidden Markov Model 33
2.3.2 Computation Offloading Schemes Based on Game Theory 33
2.4 QoS and Optimization in Edge Computing 34
2.4.1 Statistical Delay Bounded QoS 35
2.4.2 Holistic Task Offloading Algorithm Considerations 35
2.5 Deep Learning Mathematical Models for Edge Computing 36
2.5.1 Applications of Deep Learning at the Edge 36
2.5.2 Resource Allocation Using Deep Learning 37
2.5.3 Computation Offloading Using Deep Learning 39
2.6 Evolutionary Algorithm and Edge Computing 39
2.7 Conclusion 41
References 41
3 Mathematical Modelling of Cryptographic Approaches in Cloud Computing Scenario 45
M. Julie Therese, A. Devi, P. Dharanyadevi and Dr. G. Kavya
3.1 Introduction to IoT 46
3.1.1 Introduction to Cloud 46
3.1.2 General Characteristics of Cloud 47
3.1.3 Integration of IoT and Cloud 47
3.1.4 Security Characteristics of Cloud 47
3.2 Data Computation Process 49
3.2.1 Star Cubing Method for Data Computation 49
3.2.1.1 Star Cubing Algorithm 49
3.3 Data Partition Process 51
3.3.1 Need for Data Partition 52
3.3.2 Shamir Secret (SS) Share Algorithm for Data Partition 52
3.3.3 Working of Shamir Secret Share 53
3.3.4 Properties of Shamir Secret Sharing 55
3.4 Data Encryption Process 56
3.4.1 Need for Data Encryption 56
3.4.2 Advanced Encryption Standard (AES) Algorithm 56
3.4.2.1 Working of AES Algorithm 57
3.5 Results and Discussions 59
3.6 Overview and Conclusion 63
References 64
4 An Exploration of Networking and Communication Methodologies for Security and Privacy Preservation in Edge Computing Platforms 69
Arulkumaran G, Balamurugan P and Santhosh J
Introduction 70
4.1 State-of-the-Art Edge Security and Privacy Preservation Protocols 71
4.1.1 Proxy Re-Encryption (PRE) 72
4.1.2 Attribute-Based Encryption (ABE) 73
4.1.3 Homomorphic Encryption (HE) 73
4.2 Authentication and Trust Management in Edge Computing Paradigms 76
4.2.1 Trust Management in Edge Computing Platforms 77
4.2.2 Authentication in Edge Computing Frameworks 78
4.3 Key Management in Edge Computing Platforms 79
4.3.1 Broadcast Encryption (BE) 80
4.3.2 Group Key Agreement (GKA) 80
4.3.3 Dynamic Key Management Scheme (DKM) 80
4.3.4 Secure User Authentication Key Exchange 81
4.4 Secure Edge Computing in IoT Platforms 81
4.5 Secure Edge Computing Architectures Using Block Chain Technologies 84
4.5.1 Harnessing Blockchain Assisted IoT in Edge Network Security 86
4.6 Machine Learning Perspectives on Edge Security 87
4.7 Privacy Preservation in Edge Computing 88
4.8 Advances of On-Device Intelligence for Secured Data Transmission 91
4.9 Security and Privacy Preservation for Edge Intelligence in Beyond 5G Networks 92
4.10 Providing Cyber Security Using Network and Communication Protocols for Edge Computing Devices 95
4.11 Conclusion 96
References 96
5 Nature Inspired Algorithm for Placing Sensors in Structural Health Monitoring System - Mouth Brooding Fish Approach 99
P. Selvaprasanth, Dr. J. Rajeshkumar, Dr. R. Malathy, Dr. D. Karunkuzhali and M. Nandhini
5.1 Introduction 100
5.2 Structural Health Monitoring 101
5.3 Machine Learning 102
5.3.1 Methods of Optimal Sensor Placement 102
5.4 Approaches of ML in SHM 103
5.5 Mouth Brooding Fish Algorithm 116
5.5.1 Application of MBF System 118
5.6 Case Studies On OSP Using Mouth Brooding Fish Algorithms 120
5.7 Conclusions 126
References 128
6 Heat Source/Sink Effects on Convective Flow of a Newtonian Fluid Past an Inclined Vertical Plate in Conducting Field 131
Raghunath Kodi and Obulesu Mopuri
6.1 Introduction 131
6.2 Mathematic Formulation and Physical Design 133
6.3 Discusion of Findings 138
6.3.1 Velocity Profiles 138
6.3.2 Temperature Profile 139
6.3.3 Concentration Profiles 144
6.4 Conclusion 144
References 147
7 Application of Fuzzy Differential Equations in Digital Images Via Fixed Point Techniques 151
D. N. Chalishajar and R. Ramesh
7.1 Introduction 151
7.2 Preliminaries 153
7.3 Applications of Fixed-Point Techniques 154
7.4 An Application 159
7.5 Conclusion 160
References 160
8 The Convergence of Novel Deep Learning Approaches in Cybersecurity and Digital Forensics 163
Ramesh S, Prathibanandhi K, Hemalatha P, Yaashuwanth C and Adam Raja Basha A
8.1 Introduction 164
8.2 Digital Forensics 166
8.2.1 Cybernetics Schemes for Digital Forensics 167
8.2.2 Deep Learning and Cybernetics Schemes for Digital Forensics 169
8.3 Biometric Analysis of Crime Scene Traces of Forensic Investigation 170
8.3.1 Biometric in Crime Scene Analysis 170
8.3.1.1 Parameters of Biometric Analysis 172
8.3.2 Data Acquisition in Biometric Identity 172
8.3.3 Deep Learning in Biometric Recognition 173
8.4 Forensic Data Analytics (FDA) for Risk Management 174
8.5 Forensic Data Subsets and Open-Source Intelligence for Cybersecurity 177
8.5.1 Intelligence Analysis 177
8.5.2 Open-Source Intelligence 178
8.6 Recent Detection and Prevention Mechanisms for Ensuring Privacy and Security in Forensic Investigation 179
8.6.1 Threat Investigation 179
8.6.2 Prevention Mechanisms 180
8.7 Adversarial Deep Learning in Cybersecurity and Privacy 181
8.8 Efficient Control of System-Environment Interactions Against Cyber Threats 184
8.9 Incident Response Applications of Digital Forensics 185
8.10 Deep Learning for Modeling Secure Interactions Between Systems 186
8.11 Recent Advancements in Internet of Things Forensics 187
8.11.1 IoT Advancements in Forensics 188
8.11.2 Conclusion 189
References 189
9 Mathematical Models for Computer Vision in Cardiovascular Image Segmentation 191
S. Usharani, K. Dhanalakshmi, P. Manju Bala, M. Pavithra and R. Rajmohan
9.1 Introduction 192
9.1.1 Computer Vision 192
9.1.2 Present State of Computer Vision Technology 193
9.1.3 The Future of Computer Vision 193
9.1.4 Deep Learning 194
9.1.5 Image Segmentation 194
9.1.6 Cardiovascular Diseases 195
9.2 Cardiac Image Segmentation Using Deep Learning 196
9.2.1 MR Image Segmentation 196
9.2.1.1 Atrium Segmentation 196
9.2.1.2 Atrial Segmentation 200
9.2.1.3 Cicatrix Segmentation 201
9.2.1.4 Aorta Segmentation 201
9.2.2 CT Image Segmentation for Cardiac Disease 201
9.2.2.1 Segmentation of Cardiac Substructure 202
9.2.2.2 Angiography 203
9.2.2.3 CA Plaque and Calcium Segmentation 204
9.2.3 Ultrasound Cardiac Image Segmentation 205
9.2.3.1 2-Dimensional Left Ventricle Segmentation 205
9.2.3.2 3-Dimensional Left Ventricle Segmentation 206
9.2.3.3 Segmentation of Left Atrium 207
9.2.3.4 Multi-Chamber Segmentation 207
9.2.3.5 Aortic Valve Segmentation 207
9.3 Proposed Method 208
9.4 Algorithm Behaviors and Characteristics 209
9.5 Computed Tomography Cardiovascular Data 212
9.5.1 Graph Cuts to Segment Specific Heart Chambers 212
9.5.2 Ringed Graph Cuts with Multi-Resolution 213
9.5.3 Simultaneous Chamber Segmentation using Arbitrary Rover 214
9.5.3.1 The Arbitrary Rover Algorithm 215
9.5.4 Static Strength Algorithm 217
9.6 Performance Evaluation 219
9.6.1 Ringed Graph Cuts with Multi-Resolution 219
9.6.2 The Arbitrary Rover Algorithm 220
9.6.3 Static Strength Algorithm 220
9.6.4 Comparison of Three Algorithm 221
9.7 Conclusion 221
References 221
10 Modeling of Diabetic Retinopathy Grading Using Deep Learning 225
Balaji Srinivasan, Prithiviraj Rajalingam and Anish Jeshvina Arokiachamy
10.1 Introduction 225
10.2 Related Works 228
10.3 Methodology 231
10.4 Dataset 236
10.5 Results and Discussion 236
10.6 Conclusion 243
References 243
11 Novel Deep-Learning Approaches for Future Computing Applications and Services 247
M. Jayalakshmi, K. Maharajan, K. Jayakumar and G. Visalaxi
11.1 Introduction 248
11.2 Architecture 250
11.2.1 Convolutional Neural Network (CNN) 252
11.2.2 Restricted Boltzmann Machines and Deep Belief Network 252
11.3 Multiple Applications of Deep Learning 254
11.4 Challenges 264
11.5 Conclusion and Future Aspects 265
References 266
12 Effects of Radiation Absorption and Aligned Magnetic Field on MHD Cassion Fluid Past an Inclined Vertical Porous Plate in Porous Media 273
Raghunath Kodi, Ramachandra Reddy Vaddemani and Obulesu Mopuri
12.1 Introduction 274
12.2 Physical Configuration and Mathematical Formulation 275
12.2.1 Skin Friction 279
12.2.2 Nusselt Number 280
12.2.3 Sherwood Number 280
12.3 Discussion of Result 280
12.3.1 Velocity Profiles 280
12.3.2 Temperature Profiles 284
12.3.3 Concentration Profiles 284
12.4 Conclusion 289
References 290
13 Integrated Mathematical Modelling and Analysis of Paddy Crop Pest Detection Framework Using Convolutional Classifiers 293
R. Rajmohan, M. Pavithra, P. Praveen Kumar, S. Usharani, P. Manjubala and N. Padmapriya
13.1 Introduction 294
13.2 Literature Survey 295
13.3 Proposed System Model 295
13.3.1 Disease Prediction 296
13.3.2 Insect Identification Algorithm 297
13.4 Paddy Pest Database Model 308
13.5 Implementation and Results 309
13.6 Conclusion 312
References 313
14 A Novel Machine Learning Approach in Edge Analytics with Mathematical Modeling for IoT Test Optimization 317
D. Jeya Mala and A. Pradeep Reynold
14.1 Introduction: Background and Driving Forces 318
14.2 Objectives 319
14.3 Mathematical Model for IoT Test Optimization 319
14.4 Introduction to Internet of Things (IoT) 320
14.5 IoT Analytics 321
14.5.1 Edge Analytics 322
14.6 Survey on IoT Testing 324
14.7 Optimization of End-User Application Testing in IoT 327
14.8 Machine Learning in Edge Analytics for IoT Testing 327
14.9 Proposed IoT Operations Framework Using Machine Learning on the Edge 328
14.9.1 Case Study 1 - Home Automation System Using IoT 329
14.9.2 Case Study 2 - A Real-Time Implementation of Edge Analytics in IBM Watson Studio 335
14.9.3 Optimized Test Suite Using ML-Based Approach 338
14.10 Expected Advantages and Challenges in Applying Machine Learning Techniques in End-User Application Testing on the Edge 339
14.11 Conclusion 342
References 343
Index 345
1
Certain Investigations on Different Mathematical Models in Machine Learning and Artificial Intelligence
Ms. Akshatha Y* and Dr. S Pravinth Raja┼
Dept. of CSE, Presidency University, Bengaluru, Karnataka, India
Abstract
Artificial Intelligence (AI) is as wide as the other branches of computer science, including computational methods, language analysis, programming systems, and hardware systems. Machine learning algorithm has brought greater change in the field of artificial intelligence which has supported the power of human perception in a splendid way. The algorithm has different sections, of which the most common segment is classification. Decision tree, logistic regression, naïve bays algorithm, support vector machine algorithm, boosted tree, random forest and k nearest neighbor algorithm come under the classification of algorithms. The classification process requires some pre-defined method leading the process of choosing train data from the user's sample data. A host of AI Advanced AI programming languages and methodologies can provide high-level frameworks for implementing numerical models and approaches, resulting in simpler computational mechanics codes, easier to write, and more adaptable. A range of heuristic search, planning, and geometric reasoning algorithms can provide efficient and comprehensive mechanisms for resolving problems such as shape description and transformation, and model representation based on constraints. So behind every algorithm there lies a strong mathematical model, based on conditional probability. This article is the analysis of those mathematical models and logic behind different classification algorithms that allow users to make the training dataset based on which computer can predict the correct performance.
Keywords: Artificial intelligence, classification, computation, machine learning
1.1 Introduction
The increasing popularity of large computing power in recent years, due to the availability of big data and the relevant developments in algorithms, has contributed to an exponential growth in Machine Learning (ML) applications for predictive tasks related to complex systems. In general, by utilizing an appropriate broad dataset of input features coupled to the corresponding predicted outputs, ML automatically constructs a model of the scheme under analysis. Although automatically learning data models is an extremely powerful approach, the generalization capability of ML models can easily be reduced in the case of complex systems dynamics, i.e., the predictions can be incorrect if the model is extended beyond the limits of ML models [1]. A collection of AI ideas and techniques has the potential to influence mathematical modelling study. In particular, information-based systems and environments may include representations and associated problem-solving techniques that can be used in model generation and result analysis to encode domain knowledge and domain-specific strategies for a variety of ill-structured problems. Advanced AI programming languages and methodologies may include high-level frameworks to implement numerical models and solutions, resulting in codes for computational mechanics that are cleaner, easier to write and more adaptable. A variety of heuristic search, scheduling, and geometric reasoning algorithms may provide efficient and comprehensive mechanisms for addressing issues such as shape definition and transformation, and model representation based on constraints. We study knowledge-based expert systems and problem-solving methods briefly before exploring the applications of AI in mathematical modelling.
1.1.1 Knowledge-Based Expert Systems
Knowledge-based systems are about a decade old as a distinctly separate AI research field. Many changes in the emphasis put on different elements of methodology have been seen in this decade of study. Methodological transition is the most characteristic; the emphasis has changed from application areas and implementation instruments to architectures and unifying concepts underlying a range of tasks for problem-solving. The presentation and analysis were at two levels in the early days of knowledge-based systems: 1) the primitive mechanisms of representation (rules, frames, etc.) and their related primitive mechanisms of inference (forward and backward chaining, inheritance, demon firing, etc.), and 2) the definition of the problem.
A level of definition is needed that describes adequately what heuristic programmers do and know, a computational characterization of their competence that is independent of the implementation of both the task domain and the programming language. Recently in the study, many characterizations of generic tasks that exist in a multitude of domains have been described. The kind of information they rely on and their control of problem solving are represented by generic tasks. For expert systems architecture, generic tasks constitute higher-level building blocks. Their characteristics form the basis for the study of the content of the knowledge base (completeness, accuracy, etc.) in order to explain system operations and limitations and to establish advanced tools for acquiring knowledge.
1.1.2 Problem-Solving Techniques
Several problem-solving tasks can be formulated as a state-space search. A state space is made up of all the domain states and a set of operators that transform one state into another. In a connected graph, the states can best be thought of as nodes and the operators as edges. Some nodes are designated as target nodes, and when a path from an initial state to a goal state has been identified, a problem is said to be solved. State spaces can get very big, and different search methods are necessary to monitor the effectiveness of the search [7].
A) Problem Reduction: To make searching simpler, this strategy requires transforming the problem space. Examples of problem reduction include: (a) organizing in an abstract space with macro operators before getting to the real operator details; (b) mean-end analysis, which tries to reason backwards from a known objective; and (c) sub-goaling.
B) Search Reduction: This approach includes demonstrating that the solution to the problem cannot rely on searching for a certain node. There are several explanations why this may be true: (a) There can be no solution in this node's subtree. This approach has been referred to as "constraint satisfaction" and includes noting that the circumstances that can be accomplished in the subtree below a node are inadequate to create any minimum solution requirement. (b) In the subtree below this node, the solution in another direction is superior to any possible solution. (c) In the quest, the node has already been investigated elsewhere.
C) Use information of domains: The addition of additional information to non-goal nodes is one way to monitor the quest. This knowledge could take the form of a distance from a hypothetical target, operators that can be applied to it usefully, possible positions of backtracking, similarities to other nodes that could be used to prune the search, or some general formation goodness.
D) Adaptive searching techniques: In order to extend the "next best" node, these strategies use assessment functions. The node most likely to contain the optimal solution will be extended by certain algorithms (A *). The node that is most likely to add the most information to the solution process will be expanded by others (B *).
1.2 Mathematical Models of Classification Algorithm of Machine Learning
In the artificial learning area, the machine learning algorithm has brought about a growing change, knowledge that spoke of human discerning power in a splendid manner. There are various types of algorithms, the most common feature of which is grouping. Computer algorithm, logistic regression, naive bay algorithm, decision tree, enhanced tree, all under classification algorithms, random forest and k nearest neighbour algorithm support vector support. The classification process involves some predefined method that leads to the train data method of selection from the sample data provided by the user. Decision-making is the centre of all users, and the algorithm of classification as supervised learning stands out from the decision of the user.
Machine learning (ML) and deep learning (DL) are common right now, as there is a lot of fascinating work going on there, and for good reason. The hype makes it easy to forget about more tried and tested methods of mathematical modelling, but that doesn't make it easier to forget about those methods.
We can look at the landscape in terms of the Gartner Hype Cycle:
Figure 1.1 is curve that first ramps up to a peak, then falls down into a low and gets back up into a plateau. We think that ML, and DL in particular, is (or at least is very close to) the Height of Unrealistic Expectations. Meanwhile, the Shortage of Productivity has several other methods. People understand them and use them all the time, but nobody speaks about them. They're workhorses. They're still important, though, and we at Manifold understand that. You also have to deploy the full spectrum of available resources, well beyond ML, to build effective data items. What does that mean in practice?
Figure 1.1 Gartner hyper cycle.
1.2.1 Tried and True Tools
Let's look at a couple of these advanced tools that continue to be helpful: the theory of control, signal processing, and optimization of mathematics.
Control...
