وبلاگ بلیان

Fuzzy Information Processing 2020: Proceedings of the 2020 Annual Conference of the North American Fuzzy Information Processing Society, NAFIPS 2020 ... in Intelligent Systems and Computing, 1337)

معرفی کتاب «Fuzzy Information Processing 2020: Proceedings of the 2020 Annual Conference of the North American Fuzzy Information Processing Society, NAFIPS 2020 ... in Intelligent Systems and Computing, 1337)» نوشتهٔ Barnabás Bede (editor), Martine Ceberio (editor), Martine De Cock (editor), Vladik Kreinovich (editor)، منتشرشده توسط نشر Springer International Publishing AG در سال 2022. این کتاب در فرمت pdf، زبان انگلیسی ارائه شده است.

This book describes how to use expert knowledge―which is often formulated by using imprecise (fuzzy) words from a natural language. In the 1960s, Zadeh designed special "fuzzy" techniques for such use. In the 1980s, fuzzy techniques started controlling trains, elevators, video cameras, rice cookers, car transmissions, etc. Now, combining fuzzy with neural, genetic, and other intelligent methods leads to new state-of-the-art results: in aerospace industry (from drones to space flights), in mobile robotics, in finances (predicting the value of crypto-currencies), and even in law enforcement (detecting counterfeit banknotes, detecting online child predators and in creating explainable AI systems). The book describes these (and other) applications―as well as foundations and logistics of fuzzy techniques. This book can be recommended to specialists―both in fuzzy and in various application areas―who will learn latest techniques and their applications, and to students interested in innovative ideas. Preface Contents Powerset Operators in Categories with Fuzzy Relations Defined by Monads 1 Introduction 2 Preliminaries 3 Fuzzy Type Relations Defined by Monads 4 Powerset Theory of Categories with Relational Morphisms Defined by Monads 5 Conclusions References Improved Fuzzy Q-Learning with Replay Memory 1 Introduction 1.1 Fuzzy Logic & Q-Learning 1.2 Simulator 2 Methodology 2.1 Fuzzy Logic 2.2 Normal Fuzzy Q-Learning 2.3 Improved Fuzzy Q-Learning with Replay Memory 3 Result Analysis 3.1 Result of Normal Fuzzy Q-Learning 3.2 Results of Fuzzy Q-Learning with Replay Memory 3.3 Robustness Comparison 3.4 Result Summary 4 Conclusion References Agnesi Quasi-fuzzy Numbers 1 Introduction 2 Basic Definitions 3 Agnesi Quasi-fuzzy Numbers 4 Final Remarks References Fuzzy Mathematical Morphology and Applications in Image Processing 1 Introduction 2 The Fuzzy Morphological Operators 3 Application of Fuzzy Morphology to Mycorrhizal Fungi Spores 3.1 Lukasiewicz's Fuzzy Morphology 3.2 Gödel's Fuzzy Morphology 3.3 Weber's and Fodor's Epsilon Functions 4 Final Considerations References Interval Fuzzy Models Based on Evolving Gaussian Clustering—eGauss+ 1 Introduction 2 Gaussian Probability Density Distribution for Clustering from Data Streams 2.1 Recursive Adaptation of Cluster Parameters 2.2 Adding New Clusters 2.3 Merging Clusters 3 Evolving Clustering for Regression 3.1 Estimation of the Local Model Parameters 4 Interval Fuzzy Model 5 Conclusion References Construction of T-Vague Groups for Real-Valued Interference Channel 1 Introduction 2 Interference Alignment onto a Real Ideal Lattice 2.1 Quantization of Real-Valued Channels onto a Lattice 2.2 Construction of Real Nested Ideal Lattices from the Channel Quantization 3 T-Fuzzy Subgroups, T-Indistinguishability Operator and T-Vague Groups Based on Algebraic Lattices 3.1 T-Fuzzy Subgroups 3.2 T-Indistinguishability Operator 3.3 T-Vague Groups 4 Conclusion and Final Remarks References Adaptive Interval Fuzzy Modeling from Stream Data and Application in Cryptocurrencies Forecasting 1 Introduction 2 Adaptive Interval Fuzzy Modeling 2.1 Interval Time Series and Interval Arithmetic 2.2 Adaptive Interval Fuzzy Modeling 2.3 Learning the Antecedent of Interval Fuzzy Rules 2.4 Estimating the Parameters of Interval Fuzzy Rule Consequent 2.5 Adaptive Interval Fuzzy Modeling Procedure 3 Computational Experiments 3.1 Cryptocurrency Trade 3.2 Data 3.3 Performance Measures 3.4 Simulation Results 4 Conclusion References Solving Capacitated Vehicle Routing Problems with Fuzzy Delivery Costs and Fuzzy Demands 1 Introduction and Motivation 2 The Crisp CVRP 3 Fuzzy Sets/Numbers 4 The Proposed FCVRP Optimization Method 4.1 The Proposed Method 5 Application Example 5.1 Crisp Solution 5.2 Fuzzy Solution 6 Concluding Remarks 7 Further Topics References Sugeno Integral over Generalized Semi-quantales 1 Introduction 2 Motivating Preliminaries 3 Sugeno Integral over Generalized Semi-quantales 3.1 Generalized Semi-quantales 3.2 Generalized Sugeno Integral 4 Conclusion and Future Work References Numerical Solution for Reversible Chemical Reaction Models with Interactive Fuzzy Initial Conditions 1 Introduction 2 Preliminaries 2.1 Euler Method 2.2 Fuzzy Set Theory 3 Joint Possibility Distribution 4 Arithmetic for Interactive Fuzzy Numbers 5 Fuzzy Numerical Solution to the Reversible Chemical Reactions 6 Final Remarks References Predictive Maintenance of Aircraft Engines Using Fuzzy Bolt 1 Introduction 2 NASA C-MAPSS Dataset 3 Methodology 3.1 Fuzzy Bolt 4 Results 5 Conclusions References Optimal Number of Classes in Fuzzy Partitions 1 Introduction 2 Preliminaries 3 Optimal Number of Classes in a Fuzzy Partition 3.1 Characteristic Polynomial of a Dissimilarity Matrix 3.2 Optimization Problem Related to Characteristic Polynomials 4 Application 5 Final Comments References Consistence of Interactive Fuzzy Initial Conditions 1 Introduction 2 Preliminaries 3 Choice of Joint Possibility Distribution 4 Consistence of Fuzzy Initial Conditions 5 Final Remarks References An Approximate Perspective on Word Prediction in Context: Ontological Semantics Meets BERT 1 Introduction 2 Bidirectional Encoder Representations from Transformers (BERT) 2.1 Semantic Capabilities of BERT 3 Ontological Semantic Technology 3.1 On OST's Fuzzy Nature 4 Masked Word Prediction as Guessing of an Unknown Word's Meaning 5 Deconstructing BERT's Output Using OST and Fuzzy Inference 6 Conclusion References Using Fuzzy Sets to Assess Differences in Online Grooming Conversations with Victims, Decoys, and Law Enforcement 1 Introduction 2 Relevant Literature 3 Methodology 4 Preliminary Analysis 5 Conclusions and Future Work References An Optimized Intelligent Fuzzy Fractional Order TID Controller for Uncertain Level Control Process with Actuator and System Component Uncertainty 1 Introduction 2 Process Description 3 Fuzzy TID Controller 3.1 Genetic Algorithm 4 Simulation Studies 4.1 Regulatory Performance 4.2 Servo Performance 5 Conclusions References Fuzzy Redundancy Mechanism to Enhance the Resilience of IoT-Based HPC Systems 1 Introduction 2 Problem Definition 3 Related Work 4 The Proposed Solution 5 Testing and Evaluation 6 Conclusion and Future Work References Carbon Emissions Trading as a Constraint in a Fuzzy Optimization Problem 1 Introduction 2 Carbon Market 3 Fuzzy Optimization Problems 4 Carbon Market as a Constraint 5 Final Remarks References Optimization of Neural Network Models for Estimating the Risk of Developing Hypertension Using Bio-inspired Algorithms 1 Introduction 2 Literature Review 2.1 Flower Pollination Algorithm 2.2 Ant Lion Optimizer 2.3 Blood Pressure and Hypertension 2.4 Framingham Heart Study 2.5 Neural Networks 3 Proposed Method 4 Results and Discussion 4.1 Results 4.2 Discussion 5 Conclusions and Future Work References Toward Improving the Fuzzy KNN Algorithm Based on Takagi–Sugeno Fuzzy Inference System 1 Introduction 2 Problem Statement and Proposed Method 3 Review of Important Concepts 3.1 Nearest Neighbor Methods Based on Fuzzy Sets 3.2 K-NN Methods Based on Interval Type-2 Fuzzy Sets 3.3 Possibilistic K-NN Methods 3.4 Intuitionistic K-NN Methods 3.5 K-NN Methods Based on Fuzzy Rough Sets 3.6 K-NN Methods Based on Fuzzy Rough Sets 3.7 Fuzzy K-Nearest Neighbor Algorithm 3.8 Euclidean Distance 3.9 Hamming Distance 3.10 Cosine Similarity Distance 3.11 City Block Distance 3.12 Electrocardiograms, Arrhythmias 4 Experiments 4.1 MIT-BIH Arrhythmia Database 4.2 Results 5 Conclusions References Random Fuzzy-Rule Foams for Explainable AI 1 Explaining Neural Black Boxes with Fuzzy Rule Foams 2 Standard Additive Model (SAM) Fuzzy Systems 2.1 Fuzzy Approximation Theorem for Gaussian SAMs 2.2 Conditional Variance 2.3 Bayesian Posteriors of Subsystems and Rules 2.4 SAM Combination of Throughput Rules 3 Fuzzy Rule Foam 3.1 Training with Adaptive Vector Quantization (AVQ) 4 Random Foams 5 Experiments on MNIST Data 6 Conclusions 7 Appendix : Fuzzy Approximation Theorem for a Combination of Gaussian SAMs References An Approach for Solving Fully Interval Production Planning Problems 1 Introduction and Motivation 2 The Interval LP Problem 2.1 Real-Interval Numbers 2.2 Interval LP Model 3 The Fully Interval Mixed Production Planning Problem (IMPP) 4 The Proposed Approach 5 Application Example 5.1 Obtained Results 6 Concluding Remarks References Enhanced Cascaded Genetic Fuzzy System for Counterfeit Banknote Detection 1 Introduction 2 Preliminaries 2.1 Banknote Authentication Dataset 2.2 Fuzzy Inference System 2.3 Genetic Algorithm 3 Suggested Approach 3.1 Cascaded Fuzzy Inference System 3.2 GA-based Parameter Optimization 4 Simulation Results 5 Conclusion References ExTree—Explainable Genetic Feature Coupling Tree Using Fuzzy Mapping for Dimensionality Reduction with Application to NACA 0012 Airfoils Self-Noise Data Set 1 Introduction 2 NASA Airfoil Self-Noise Data Set 3 Objectives of the Research 4 Methodology 4.1 Dimensionality Reduction, Structure of the Tree 4.2 Fine Tuning, Genetic Algorithm 4.3 Expansion, Filling Unknown Entries 5 Results 5.1 Genetic Algorithm 5.2 Control Surfaces 5.3 Predicted Values 6 Conclusion References Fast Training Algorithm for Genetic Fuzzy Controllers and Application to an Inverted Pendulum with Free Cart 1 Introduction 1.1 Problem 1.2 Main Purpose 1.3 Approach 1.4 Nature of the Case Study 2 Related Work 3 Theoretical Background 4 Methodology 5 Preliminary Results 6 Conclusions References Genetic Fuzzy Systems: Genetic Fuzzy Based Tetris Player 1 Introduction 2 Methodology 2.1 Fuzzy Logic Tetris Player Expert Training 2.2 Fuzzy Logic Tetris Player with Genetic Algorithm Training 2.3 Fuzzy Logic Tetris Player with Genetic Algorithm Training (Membership Functions) 3 Results 3.1 Results: Fuzzy Logic Tetris Player Expert Training 3.2 Results: Fuzzy Logic Tetris Player with Genetic Algorithm Training 3.3 Results: Fuzzy Logic Tetris Player with Genetic Algorithm Training (Membership Functions) 4 Discussion 5 Summary and Conclusions References A Dynamic Hierarchical Genetic-Fuzzy Sugeno Network 1 Introduction 2 Methodology 2.1 Takagi-Sugeno Fuzzy Model 2.2 Hierarchical Network 2.3 Genetic Algorithm 2.4 Artificial Neural Networks 3 Results 3.1 Forest Fires 3.2 O-Rings 3.3 QSAR Fish Toxicity 4 Conclusion References Obstacle Avoidance and Target Tracking by Two Wheeled Differential Drive Mobile Robot Using ANFIS in Static and Dynamic Environment 1 Introduction 2 The Architecture and Design of the Mobile Robot’s ANFIS Controller 3 Target Reaching ANFIS Controller 4 Obstacle Avoidance ANFIS Controller References An Investigation into the Impact of System Transparency on Work Flows of Fuzzy Tree Based AIs 1 Introduction 2 Problem Statement 3 Experimental Setup 4 Proposed Solution 5 Work Flow Analysis 5.1 White Box Process 5.2 Black Box Process 6 Results Comparison 7 Conclusion References Formal Verification of a Genetic Fuzzy System for Unmanned Aerial Vehicle Navigation and Target Capture in a Safety Corridor 1 Introduction 2 Background and Problem Statement 3 Proposed Solution 4 Verification 4.1 Formal Verification 5 Results 5.1 Specification 1 5.2 Specification 2 5.3 Specification 3 5.4 Specification 4 6 Conclusion References How to Reconcile Randomness with Physicists' Belief that Every Theory Is Approximate: Informal Knowledge Is Needed 1 Randomness: An Algorithmic Description (A Brief Reminder) 2 Remaining Challenge and Our Proposed Solution to This Challenge References Scale-Invariance and Fuzzy Techniques Explain the Empirical Success of Inverse Distance Weighting and of Dual Inverse Distance Weighting in Geosciences 1 Formulation of the Problem 2 What Is Scale Invariance and How It Explains the Empirical Success of Inverse Distance Weighting 3 Scale Invariance and Fuzzy Techniques Explain Dual Inverse Weighting References Is There a Contradiction Between Statistics and Fairness: From Intelligent Control to Explainable AI 1 Formulation of the Problem 2 How Current Techniques Lead to Unfair Decisions: Simplified Examples 3 Using More Detailed Models Helps 4 How Is This Idea Applicable to Fuzzy References Which Algorithms Are Feasible and Which Are Not: Fuzzy Techniques Can Help in Formalizing the Notion of Feasibility 1 Formulation of the Problem 2 Analysis of the Problem and Possible Solution References Centroids Beyond Defuzzification 1 Formulation of the Problem 2 Fuzzy-Related Meaning of the ``Other'' Component of the Centroid References Equations for Which Newton's Method Never Works: Pedagogical Examples 1 Formulation of the Problem 2 First Example 3 Other Examples Reference Optimal Search Under Constraints 1 Where This Problem Came From 2 Towards Formulating the Problem in Precise Terms 3 Precise Formulation of the Problem and the Optimal Algorithm Reference How User Ratings Change with Time: Theoretical Explanation of an Empirical Formula 1 Formulation of the Problem 2 Our Explanation 2.1 First Technical Comment 2.2 First Idea: The Description Should Not Depend on the Unit for Measuring Time 2.3 This Has to Be Related to a Change in How We Measure Ratings 2.4 Formal Description of Unit-Independence 2.5 What Can We Conclude Based on This Independence. 2.6 Second Idea: The Change in Rating Should Be the Same Before and After tu References Why a Classification Based on Linear Approximation to Dynamical Systems Often Works Well in Nonlinear Cases 1 Formulation of the Problem 1.1 Dynamical Systems Are Ubiquitous 1.2 Simplest Case: Linear Systems 1.3 A Similar Classification Works Well in Non-linear Cases, But Why? 2 Our Explanation 2.1 We Need Finite-Dimensional Approximations 2.2 Shift-Invariance 2.3 Towards the Explanation References How Mathematics and Computing Can Help Fight the Pandemic: Two Pedagogical Examples 1 First Example: Need for Social Distancing 2 Second Example: Need for Fast Testing References Natural Invariance Explains Empirical Success of Specific Membership Functions, Hedge Operations, and Negation Operations 1 Formulation of the Problem 1.1 Need to Select Proper Membership Functions, Proper Hedge Operations, and Proper Negation Operations 1.2 What We Do in This Paper 2 Analysis of the Problem 2.1 Re-scaling 2.2 Scale-Invariance: Idea 2.3 Let Us Apply This Idea to the Membership Function 2.4 So, What Are Reasonable Transformations of the Degree of Confidence? 2.5 What Membership Functions We Consider 2.6 Discussion 3 Which Symmetric Membership Functions Should We Select: Definitions and the Main Result 3.1 Discussion 4 Which Hedge Operations and Negation Operations Should We Select 4.1 Discussion 4.2 Discussion 5 Proofs 5.1 Proof of Proposition 1 5.2 Proof of Proposition 2 5.3 Proof of Proposition 3 References
دانلود کتاب Fuzzy Information Processing 2020: Proceedings of the 2020 Annual Conference of the North American Fuzzy Information Processing Society, NAFIPS 2020 ... in Intelligent Systems and Computing, 1337)