In this book, recent theoretical developments on fuzzy logic, neural networks and optimization algorithms, as well as their hybrid combinations, are presented. In addition, the above-mentioned methods are presented in application areas such as, intelligent control and robotics, pattern recognition, medical diagnosis, decision-making, time series prediction and optimization of complex problems. The book contains a collection of papers focused on hybrid intelligent systems based on soft computing techniques. There are a group of papers with the main theme of type-1 and type-2 fuzzy logic, which basically consists of papers that propose new concepts and algorithms based on type-1 and type-2 fuzzy logic and their applications. There also a group of papers that offer theoretical concepts and applications of meta-heuristics in different areas. Another group of papers outlines diverse applications of fuzzy logic, neural networks and hybrid intelligent systems in medical problems. There are also some papers that present theory and practice of neural networks in different application areas. In addition, there are papers that offer theory and practice of optimization and evolutionary algorithms in different application areas. Finally, there are a group of papers describing applications of fuzzy logic, neural networks and meta-heuristics in pattern recognition and classification problems.
Author(s): Oscar Castillo, Patricia Melin
Series: Studies in Computational Intelligence, 1096
Publisher: Springer
Year: 2023
Language: English
Pages: 488
City: Cham
Preface
About This Book
Contents
Neural Networks
A Decision-Making Approach Based on Multiple Neural Networks for Clustering and Prediction of Time Series
1 Introduction
2 Case Study
3 Methodology
4 Experiments and Results
5 Conclusions
References
Approximation of Physicochemical Properties Based on a Message Passing Neural Network Approach
1 Introduction
2 Methodology
2.1 Atomic Layer
2.2 Convolutional Layer
2.3 Readout Phase
2.4 Teacher Forcing
3 Results
4 Conclusions
References
Convolutional Neural Networks for Multiclass Classification of Masks
1 Introduction
2 Related Work
3 Proposed Method
3.1 Database
3.2 Testing Models
3.3 Architecture Description
3.4 Models for Classification of Masks
4 Results
4.1 Results of Model A-B-C
4.2 Results of the Proposed Method
5 Conclusions
References
Quanvolutional Neural Network Applied to MNIST
1 Introduction
2 Related Work
3 Fundamentals
3.1 Convolutional Neural Network
3.2 Quantum Computing
4 Methods
4.1 Dataset
4.2 Model Architecture
4.3 Quanvolutional Preprocessing
4.4 Metrics
5 Experiments and Results
6 Discussion
7 Conclusion and Future Work
References
Traffic Sign Recognition Using Fuzzy Preprocessing and Deep Neural Networks
1 Introduction
2 Background
2.1 Fuzzy Logic
2.2 Data Preprocessing
2.3 Convolutional Neural Networks
3 Methodology
3.1 Proposed System
3.2 Databases
3.3 Image Preprocessing
3.4 Architecture Definitions
4 Results
4.1 Results GTSRB Database
4.2 Results BelgiumTS Database
4.3 Results CTSD Database
4.4 Statistical Test
5 Discussion
6 Conclusions
References
Optimization
Fuzzy Dynamic Adaptation of an Artificial Fish Swarm Algorithm for the Optimization of Benchmark Functions
1 Introduction
2 Related Works
3 Artificial Fish Swarm Algorithm
3.1 Original Artificial Swarm Algorithm
3.2 Fuzzy Artificial Swarm Algorithm
4 Benchmark Sets of Functions
5 Experimental Results
6 Statistical Test
7 Conclusions
References
Particle Swarm Optimization Algorithm with Improved Opposition-Based Learning (IOBL-PSO) to Solve Continuous Problems
1 Introduction
2 Structure of the Standard PSO and the VVS-PSO Variant
2.1 General Structure of the Standard PSO
2.2 Structure of the VVS-PSO Variant
3 Proposed Algorithm
3.1 Structure of Improved Opposition-Based Learning (IOBL)
3.2 Structure of the IOBL Particle Swarm Optimization (IOBL-PSO) Algorithm
4 Computational Experiments
5 Results
6 Conclusions
References
Study on the Effect of Chaotic Maps in the Formation of New Universes in the Multiverse Optimizer Algorithm
1 Introduction
2 Background and MVO
3 FCMVO Proposed Methodology
4 Test and Results
5 Conclusions
References
Performance Comparative of Surrogate Models as Fitness Functions for Metaheuristic Algorithms
1 Introduction
2 PSO
3 Differential Evolution
4 Surrogate Models
5 Comparison Metrics Appropriate for Surrogate Models
6 Methodology
7 Results
8 Conclusions and Future Work
References
A New Continuous Mycorrhiza Optimization Nature-Inspired Algorithm
1 Introduction
2 Natural Inspiration
3 Literature Review
4 Continuous Mycorrhiza Optimization Algorithm (CMOA)
5 Results
6 Discussion of Results
7 Conclusions
References
Optimal Tuning of an Active Disturbance Rejection Controller Using a Particle Swarm Optimization Algorithm
1 Introduction
2 Active Disturbance Rejection Controller
2.1 Preliminaires
2.2 ADRC Applied to a DC Servomotor
3 Particle Swarm Optimization
3.1 PSO with Inertia Weight
3.2 Fractional PSO
3.3 PSO-AWDV
3.4 Fitness Function
3.5 Set of Feasible Solutions
4 Experiments
4.1 Experimental Platform
4.2 Optimization Procedure
4.3 Experimental Results
5 Conclusion
References
Fuzzy Logic
Optimization of Fuzzy Controllers Using Distributed Bioinspired Methods with Random Parameters
1 Introduction
2 Methodology and Experimental Setup
2.1 Control Problem
2.2 Setup
3 Results
4 Conclusions and Future Work
References
Application of Compensatory Fuzzy Logic in Diabetes Problem Using Pima-Indians Dataset
1 Introduction
2 Background
3 Related Works
4 Proposed Methodology and Algorithms for Classification
5 Conclusions
6 Annex: Algorithms
References
Comparison of the Effect of Parameter Adaptation in Bio-inspired CS Algorithm Using Type-2 Fuzzy Logic
1 Introduction
2 Main Characteristics of Bio-inspired Algorithms
3 Cuckoo Search Algorithm
4 Lévy Flights
5 Algorithm
6 Proposed Approach
7 Simulations Results
8 Conclusions
References
Interpretability of an Archimedean Compensatory Fuzzy Logic in Data Analytics: Some Case Studies
1 Introduction
2 Data Analytics
2.1 Interpretability
2.2 Archimedean Compensatory Fuzzy Logic
2.3 Generalization of Concepts of an Archimedean Compensatory Fuzzy Logic
3 Interpretability of the ACFL in the Context of Decision-Making Theories
4 Interpretability of an ACFL According to Bivalent Logic and Statistics
5 Conclusions
References
A New Selection and Class Prediction Using Type-1 Fuzzy Logic Applied to a Convolutional Neural Network
1 Introduction
2 Literature Review
2.1 Convolutional Neural Networks
3 Proposed Method
4 Results and Discussion
5 Statistical Test
6 Conclusions
References
Relaxed Differential Evolution Algorithm
1 Introduction
2 Differential Evolution Algorithm and Proposed Version
2.1 Relaxed Differential Evolution Algorithm
3 Case Study: Mathematical Benchmark Functions
4 Results and Comparative Analysis
4.1 Configuration and Control parameters values
4.2 Results and Analysis
5 Conclusions and Future Work
References
Optimization: Theory and Applications
Automatic Characterization of Time Series Using Metaheuristic Algorithms for Epidemics Spread Analysis
1 Introduction
2 Related Work
3 Material and Methods
3.1 Current Context of Health in Mexico
3.2 META-COVID19
4 Experimental Setup
4.1 Datasets
4.2 Parameter Settings
4.3 Results
4.4 Features Calculation Examples from Polynomial Models
5 Conclusions
Appendix A: Full Results of the Evolutionary Process
References
Comparative Study of Heuristics for the One-Dimensional Bin Packing Problem
1 Introduction
2 One-Dimensional Bin Packing Techniques
2.1 Heuristic Techniques
2.2 Metaheuristic Techniques
2.3 Exact Techniques
3 Relevant Optimization Methods
3.1 Grouping Genetic Algorithm with Controlled Gene Transmission
3.2 Consistent Neighborhood Search for Bin Packing Problem
3.3 General Arc-Flow Formulation with Graph Compression
4 Comparison of Results
5 Conclusion
References
Experimental Evaluation of Adaptive Operators Selection Methods for the Dynamic Multiobjective Evolutionary Algorithm Based on Decomposition (DMOEA/D)
1 Introduction
2 The Overview of DMOEA/D
2.1 Problem Change Detection
2.2 Mechanism of Reaction to Problem Change
3 The AOS Methods
3.1 Fitness-Rate-Rank-Based Multiarmed Bandit Adaptive Operator Selection (FRRMAB)
3.2 Adaptive Operator Selection Based on Dynamic Thompson Sampling
3.3 Adaptive Operator Selection with Test-and-Apply Structure (TAOS)
3.4 Operator Pool
4 Computational Experiments
5 Results
5.1 Hypervolume
5.2 Generalized Spread
5.3 Inverted Generational Distance
6 Conclusions
References
Automated Machine Learning to Improve Stock-Market Forecasting Using PSO and LSTM Networks
1 Introduction
2 Related Work
3 Theoretical Background
3.1 Convolutional Neural Networks
3.2 Optimization Engine
4 Methodology
5 Experimental Results
6 Conclusions
References
Evolutionary Gaussian-Gradient: A New Optimization Algorithm for the Electromechanical Design of Gravitational Batteries
1 Introduction
2 Methodology
2.1 Interpolation of the Fitness Function in the Hypervolume
2.2 Gradient Interpolation of the Fitness Function
2.3 Gaussian-Gradient Approximation
3 Smoothed Gradient in Population-Based Metaheuristics
3.1 Diferential Evolution and Smoothed Gradient
4 Analytical Gravity Battery Model
4.1 Gravitational Energy Transmission
4.2 Mathematical Model of the Gravitational Battery
4.3 Gravitational Energy Transmission
5 Results
5.1 Sperimental Setup
5.2 Comparison of Smoothed Gradient with Control Algorithms
5.3 Statistical Tests of Algorithmic Performance
5.4 Example of an Optimized Gravity Battery
6 Conclusions
References
A Comparison Between Selection Operators Heuristics of Perturbation in CSP
1 Introduction
2 Background
2.1 Constraint Satisfaction Problems
2.2 Heuristics
2.3 Acceptance Criteria
2.4 Selection Method
2.5 Hyperheuristics
3 Methodology
4 Results
5 Discussion and Future Work
References
Hybrid Intelligent Systems
Trajectory Tracking Control of Wheeled Mobile Robots Using Neural Networks and Feedback Control Techniques
1 Introduction
2 Intelligent Methods for Trajectory Generation
2.1 HybridNets
2.2 Ultra-Fast Structure Aware Deep Lane Detection Algorithm
3 Kinematic Model and Control Design
3.1 Controller Design
3.2 Control Architecture
4 Numerical Results
5 Conclusion
References
An Evolutionary Bilevel Optimization Approach for Neuroevolution
1 Introduction
2 Theoretical Foundations and Background
2.1 Convolutional Neural Networks
2.2 Neural Architecture Search
2.3 Neuroevolution
2.4 Multi-objective Bilevel Optimization
3 Neural Architecture Search as a Bilevel Optimization Problem
3.1 Decision Variables
3.2 Upper-Level Objective Function
3.3 Lower-Level Objective Function
3.4 Bilevel Optimization Model
4 Solution Proposal
4.1 Upper-Level Optimizer
4.2 Lower-Level Optimizer
5 Experiments and Discussion
5.1 Experiment 1: Single-Level Approach
5.2 Experiment 2: Bilevel Approach
5.3 Experiment 3: Comparison
6 Conclusion
References
Recovering from Population Extinction in the Animal Life Cycle Algorithm (ALCA)
1 Introduction
2 Proposal
2.1 Algorithm Model
2.2 Problem
2.3 Proposed Solution
3 Experiments
3.1 Experimental Setup
3.2 Experiment Results
4 Discussion
5 Conclusions
References
Multi-objective Optimization Through Coevolution and Outranking Methods with Uncertainty Management
1 Introduction
2 Background
2.1 Multi-objective Optimization
2.2 Representing Uncertainty with Interval Mathematics
2.3 Interval Outranking Model
2.4 Performance Indicators for RoI
2.5 Coevolution
3 Solution Methodology
4 Experimentation and Results
5 Conclusions
References
Experimental Proposal with Mallows Distribution Applied to the Mixed No-Idle Permutation Flowshop Scheduling Problem
1 Introduction
2 Generalized Mallows Model (GMM)
2.1 Parameter Estimation for GMM
3 Algorithm Proposal EDA-GMMp
4 Proposed Learning Model
4.1 Position Parameter
4.2 Spread Parameter
5 Differences Between EDA-GMMc and EDA-GMMp
6 Experiments
7 Results
7.1 Statistic Analysis
8 Conclusion
References
Interval Type-3 Fuzzy Decision Making in Material Surface Quality Control
1 Introduction
2 Interval Type-3 Fuzzy Systems
3 Decision Making Application: Surface Quality Control
4 Conclusions
References
Interval Type-3 Fuzzy Decision Making in Quality Evaluation for Speaker Manufacturing
1 Introduction
2 Interval Type-3 Fuzzy System Design
3 Application in Quality Control
4 Conclusions
References
