Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems: Via Theory, Complex Paradoxical Analyses and Harmonic ... Solutions Based on Mathematical Modeling

Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems addresses different uncertain processes inherent in the complex systems, attempting to provide global and robust optimized solutions distinctively through multifarious methods, technical analyses, modeling, optimization processes, numerical simulations, case studies as well as applications including theoretical aspects of complexity. Foregrounding Multi-chaos, Fractal and Multi-fractional in the era of Artificial Intelligence (AI), the edited book deals with multi- chaos, fractal, multifractional, fractional calculus, fractional operators, quantum, wavelet, entropy-based applications, artificial intelligence, mathematics-informed and data driven processes aside from the means of modelling, and simulations for the solution of multifaceted problems characterized by nonlinearity, non-regularity and self-similarity, frequently encountered in different complex systems. The fundamental interacting components underlying complexity, complexity thinking, processes and theory along with computational processes and technologies, with machine learning as the core component of AI demonstrate the enabling of complex data to augment some critical human skills. Appealing to an interdisciplinary network of scientists and researchers to disseminate the theory and application in medicine, neurology, mathematics, physics, biology, chemistry, information theory, engineering, computer science, social sciences and other far-reaching domains, the overarching aim is to empower out-of-the-box thinking through multifarious methods, directed towards paradoxical situations, uncertain processes, chaotic, transient and nonlinear dynamics of complex systems. Constructs and presents a multifarious approach for critical decision-making processes embodying paradoxes and uncertainty. Includes a combination of theory and applications with regard to multi-chaos, fractal and multi-fractional as well as AI of different complex systems and many-body systems. Provides readers with a bridge between application of advanced computational mathematical methods and AI based on comprehensive analyses and broad theories. Front Cover Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems Copyright Contents List of contributors Preface Acknowledgment 1 - Introduction 2 - Theory of complexity, origin and complex systems 1. Introduction 2. Theory of complexity, origin and complex systems 2.1 A brief history of complexity and the related areas of different complex systems 2.2 Theories pertaining to complexity and their historical account 3. Complex order processes toward modern scientific path: from Darwin and onwards 3.1 A conceptual outline: complexity and complex systems 4. Concluding remarks and future directions References 3 - Multi-chaos, fractal and multi-fractional AI in different complex systems 1. Introduction 2. Challenging dimensions of modern science, complexity and complex systems 2.1 Data reliability and complexity 2.2 Chaos thinking, processes and complexity 2.3 Fractal thinking, processes and complexity 2.4 Fractional thinking, processes and complexity 3. Artificial intelligence way of thinking, processes, complexity and complex systems 4. Concluding remarks and future directions References Further reading 4 - High-performance computing and computational intelligence applications with a multi-chaos perspective 1. Introduction 2. Related works 3. High-performance computing approaches to solving complex problems 3.1 Cloud containers 3.2 Container insights 3.3 GPGPU computing 3.4 GPGPU insights 3.5 GPGPU and neural networks 4. Quantum computing to treat multi-chaos scenarios 4.1 Bits and qubits 4.2 Quantum register 4.3 Relevant quantum algorithms 4.3.1 The Deutsch–Jozsa algorithm 4.3.2 The Grover's algorithm 4.3.3 The Shor's algorithm 4.4 Quantum computing insights 4.4.1 IBM's QExperience and Qiskit 4.4.2 Google's cirq and tensorflow quantum 4.4.3 Xanadu’s strawberry fields and PennyLane 4.4.4 Microsoft's Q# and Azure quantum 4.4.5 Amazon's AWS Braket 4.4.6 Rigetti's Forest 4.4.7 Quantum Inspire 4.4.8 Quirk 5. Techniques enabling the solution of complex problems based on computational intelligence 5.1 Approaches based on machine learning 5.1.1 Decision trees 5.1.2 Random Forest 5.1.3 Bayesian Classifier 5.1.4 Logistic Regression 5.1.5 K-Nearest Neighbors 5.1.6 Support Vector Machine 5.1.7 Multi-Layer Perceptron 5.1.8 Convolutional Neural Network 5.2 Machine learning insights 6. The dilemma of respecting privacy in multi-chaos situations 6.1 GDPR 6.2 AI and privacy 7. Conclusions 8. Acronyms References 5 - Human hypercomplexity. Error and unpredictability in complex multichaotic social systems 1. Introduction 2. The complexity of living energy and living beings 3. Complicated, complex, and hypercomplex systems 4. Taking a step back: a brief history of complexity 5. An epistemology of error 6. “Objects” are relations 7. Everything depends on everything else 8. Cognitive cages 9. è troppo, o troppo ravvicinato? References 6 - Multifractal complexity analysis-based dynamic media text categorization models by natural language processing ... 1. Introduction 2. Data and methodology 2.1 Complex media text data 2.2 Fractal complexity analysis 2.2.1 Fundamental concepts on Hölder regularity and multifractal analysis 2.2.2 Multifractal Bayesian denoising in S(g,ψ) 2.2.3 Numerical experiments: multifractal Bayesian, multifractal regularization, and wavelet shrinkage methods 2.3 Natural language processing 2.3.1 Bidirectional encoder representations from transformers (BERT) 2.3.2 Input/output representations 2.3.3 Pretraining BERT 2.3.3.1 Masked LM 2.3.4 Fine-tuning BERT 3. Experimental results and discussion 4. Conclusion and future directions References 7 - Mittag-Leffler functions with heavy-tailed distributions' algorithm based on different biology datasets to be f ... 1. Introduction 1.1 The motivation of the integrative method proposed 2. Complex biological datasets and methodology 2.1 Complex biological datasets 2.1.1 Cancer cell dataset 2.1.2 Diabetes dataset 2.2 Methodology 2.2.1 Mittag-Leffler function 2.2.1.1 Mittag-Leffler distribution 2.2.1.2 Pareto distribution 2.2.1.3 Cauchy distribution 2.2.1.4 Weibull distribution 3. Experimental results and discussion: computational application of Mittag-Leffler function based on heavy-tailed distributio ... 3.1 Computational applications for fitting Mittag-Leffler function based on heavy-tailed distributions to the cancer cell dataset 3.2 Computational applications for fitting Mittag-Leffler function based on heavy-tailed distributions to the diabetes dataset 4. Conclusion and future directions References 8 - Artificial neural network modeling of systems biology datasets fit based on Mittag-Leffler functions with heavy ... 1. Introduction 1.1 The motivation of the integrative method proposed 2. Complex biological datasets and methodology 2.1 Complex biological datasets 2.1.1 Cancer cell dataset 2.1.2 Diabetes dataset 2.2 Methodology 2.2.1 Artificial neural network 2.2.1.1 Multi-layer perceptron (MLP) algorithm 3. Experimental results and discussions: artificial neural network modeling of complex biological datasets to be fit based on ... 3.1 Artificial neural network modeling of cancer cell datasets to be fit based on Mittag-Leffler function with heavy-tailed dis ... 3.2 Artificial neural network modeling of diabetes datasets to be fit based on Mittag-Leffler function with heavy-tailed distri ... 4. Conclusion and future directions References 9 - Computational fractional-order calculus and classical calculus AI for comparative differentiability prediction ... 1. Introduction 1.1 The motivation and challenges of the integrative method proposed 2. Datasets and methodology 2.1 The modeling of different complex datasets 2.1.1 Stroke dataset 2.1.2 Breast cancer cell dataset 2.2 Methods 2.2.1 Fractional-order calculus 2.2.2 Fractional-order derivatives 2.2.3 Caputo fractional-order derivative 2.3 Artificial neural networks 2.3.1 Feed forward back propagation (FFBP) 3. Experimental results and discussion 3.1 Computational application of Caputo fractional-order derivative models 3.1.1 Computational application of Caputo fractional-order derivative and classical derivative models to the cancer cell dataset ... 3.2 Computational application of Caputo fractional-order derivative and classical derivative models for comparative prediction ... 4. Conclusion and future directions References 10 - Pattern formation induced by fractional-order diffusive model of COVID-19 1. Introduction 2. Model 2.1 Stability analysis of E2(ψ1∗,ψ2∗,ψ3∗) 3. Spatiotemporal model 3.1 Conditions for turing instability 4. Weakly nonlinear analysis 5. Numerical simulation 6. Conclusion References 11 - Prony's series and modern fractional calculus: Rheological models with Caputo-Fabrizio operator 1. Introduction 2. Prony's method 3. Exponential sums approximation of functions 3.1 Exponential sum approximation for t−β 3.2 Exponential sums approximation of Mittag-Leffler function 3.3 Exponential sums approximation of the Kohlrausch function 4. Fractional operators in applied rheology 4.1 Caputo derivative 4.2 Caputo-Fabrizio fractional operator 5. Modeling linear viscoelastic responses 5.1 Constitutive equations: time domain 5.2 Frequency domain: sinusoidal responses 5.3 Response function 6. Prony's series in linear viscoelasticity 6.1 Example 1. completely monotone responses as Prony's series and related discrete spectra 6.1.1 Prony's series in the time domain 6.1.2 Prony's series to the viscoelastic responses in the frequency domain 6.2 Example 2: KWW as a stress relaxation function 6.3 Example 3. Mittag-Leffler function as stress relaxation modulus 6.4 Example 4. The Bagley-Torvik equation 7. Final comments References 12 - A chain of kinetic equations of Bogoliubov–Born–Green–Kirkwood–Yvon and its application to nonequilibrium comp ... 1. Introduction 2. Formulation of the problem 3. The solution of the BBGKY hierarchy for many-type particle systems 3.1 Introduction 3.2 Formulation and solution of the problem 4. Derivation of the Gross–Pitaevskii equation from the BBGKY hierarchy 4.1 Formulation of the problem 4.2 Derivation of hierarchy of kinetic equations for correlation matrices 4.3 For the case s=1 4.4 Another method for deriving the Gross–Pitaevskii equation 5. Summary References Further reading 13 - Hearing loss detection in complex setting by stationary wavelet Renyi entropy and three-segment biogeography-b ... 1. Introduction 2. Dataset 3. Methods 3.1 Feature extraction—stationary wavelet Renyi entropy 3.2 Single hidden layer feedforward neural network 3.3 Three-segment biogeography-based optimization 4. Implementation 5. Measure 6. Experiment results and discussions 6.1 Statistical analysis of the proposed method 6.2 Biogeography-based optimization versus three-segment biogeography-based optimization 6.3 Optimal decomposition level 6.4 Comparison to state-of-the-art approaches 7. Conclusions Appendix References 14 - Shannon entropy-based complexity quantification of nonlinear stochastic process: diagnostic and predictive spa ... 1. Introduction 2. Materials and methods 2.1 Materials 2.1.1 Patient details 2.2 Methods 2.2.1 Feature selection methods 2.2.2 Linear transformation technique–based feature selection methods 2.2.2.1 Principal component analysis 2.2.2.2 Linear discriminant analysis 2.2.3 Entropy-based feature selection methods 2.2.3.1 Shannon entropy 2.2.3.2 Minimum redundancy maximum relevance 2.3 k-Nearest neighbor and decision tree algorithms 2.3.1 k-Nearest neighbor algorithm 2.3.2 Decision tree algorithm 3. Experimental results 4. Conclusion and future directions References 15 - Chest X-ray image detection for pneumonia via complex convolutional neural network and biogeography-based opti ... 1. Introduction 2. Dataset 3. Methodology 3.1 Complex convolutional neural network 3.1.1 Convolutional layer 3.1.2 Pooling layer 3.1.3 Fully connected layer 3.1.4 Complex convolutional neural network model of our proposed 3.2 Biogeography-based optimization 3.2.1 Migration 3.2.2 Mutation 3.3 Implementation 3.4 Measure 4. Experiment results and discussions 4.1 Confusion matrix of the proposed method 4.2 Statistical results 4.3 Optimal number of fully connected layers 4.4 Comparison to state-of-the-art approaches 5. Conclusions References bksec1_1 16 - Facial expression recognition by DenseNet-121 1. Introduction 2. Dataset 3. Methodology 3.1 Convolution 3.1.1 Standard convolution 3.2 Pooling 3.2.1 Max pooling 3.2.2 Average pooling 3.3 Batch normalization 3.4 Rectified linear unit 3.5 K-fold cross-validation 3.6 DenseNet-121 4. Experiment result and discussions 4.1 Statistical analysis 4.2 Comparison with state-of-the-art approaches 5. Conclusions References 17 - Quantitative assessment of local warming based on urban dynamics 1. Introduction 2. Study areas 3. Materials and methods 3.1 Urbanization dynamics 3.2 Land surface temperature 4. Results and discussion 5. Conclusions References 18 - Managing information security risk and Internet of Things (IoT) impact on challenges of medicinal problems wit ... 1. Introduction to information security 1.1 Various vulnerabilities in healthcare 1.1.1 Ransomware 1.1.2 Data breaches 1.1.3 DDoS attacks 1.1.4 Insider threat 1.1.5 Business email compromise 2. Information security in healthcare 2.1 Background of health information privacy and security 2.2 State of information security research in healthcare 2.3 Threats to information privacy 3. Impact of IoT in medical problems 3.1 Internet of Things in healthcare 3.2 Challenges of IoT in medical problems 3.2.1 Data security and privacy 3.2.2 Integration: multiple devices and protocols 3.2.3 Data overload and accuracy 3.2.4 Cost 3.3 Applications of IoT in healthcare 3.3.1 Hearables 3.3.2 Ingestible sensors 3.3.3 Moodables 3.3.4 Computer vision technology 3.3.5 Healthcare charting 4. Medical problems with complex settings 4.1 The challenge of interoperability 4.2 Keeping up with old technology 4.3 User-unfriendly interfaces 4.4 Exacerbating malpractice claims 4.5 Overcomplicated asset tracking 4.6 Overall implementation 5. IoT and information security 5.1 Understanding the needs of IoT security 5.2 Data interoperability and information security 5.3 Information security issues of e-health 5.4 Healthcare information system with complex settings 5.5 Providers' perspective of regulatory compliance 5.6 Information-access control 6. Challenges of medicinal problems using IoT: a case study 7. Conclusion References 19 - An extensive discussion on utilization of data security and big data models for resolving healthcare problems 1. Information security 1.1 Confidentiality 1.2 Integrity 1.3 Availability 1.4 Information security policy 1.5 Information security measures 1.6 Managing information security 2. Internet of Things 2.1 Connecting with the IoT 2.2 IoT for physicians 2.3 IoT for hospitals 2.4 IoT for health insurance companies 2.5 IoT for patients 2.6 Redefining healthcare 3. Information security and IoT 3.1 Information security threats 3.2 Information security threats? 4. Data security and IoT in medicine 4.1 Benefits of IoT healthcare 4.2 Challenges in information security and IoT with respect to medicine 4.2.1 Hidden HTTPS tunnels 4.2.2 Hidden DNS tunnels 4.2.3 Ransomware and botnet 5. Big data and its applications 6. IoT and big data applications in medicine 7. Complex system in healthcare 8. Role of IoT and big data applications in medicine 9. Conclusion References Index A B C D E F G H I K L M N O P Q R S T U V W X Back Cover