Multi-Criteria Decision-Making and Optimum Design with Machine Learning: A Practical Guide

Cover
Half Title
Title
Copyright
Dedication
Contents
Preface
About the Editors
List of Contributors
Acknowledgments
Chapter 1 Innovations in Technical Methodologies: Advancing Decision-Making and Optimization
	1.1 Introduction
	1.2 Recent Advances in Optimization and MCDM
	1.3 Conclusions
	1.4 Acknowledgements
	1.5 Conflicts of Interest
Chapter 2 Fuzzy Systems for Multicriteria Optimization: Applications in Engineering Design
	2.1 Introduction
		2.1.1 Motivation for Multicriteria Optimization in Engineering
		2.1.2 Challenges in Engineering Decision-Making
		2.1.3 Role of Fuzzy Logic in Handling Uncertainty
	2.2 Fundamentals of Fuzzy Logic
		2.2.1 Fuzzy Sets and Membership Functions
		2.2.2 Linguistic Variables and Fuzzy Operations
		2.2.3 Fuzzy Logic in Modeling Uncertainty
	2.3 Fuzzy Inference Systems
		2.3.1 Understanding Fuzzy Inference Systems (Mamdani and Sugeno Models)
		2.3.2 Components of Fuzzy Inference Systems
		2.3.3 FIS Applications in Engineering
	2.4 Fuzzy MCDM
		2.4.1 The Concept of MCDM
		2.4.2 Traditional MCDM Methods and Limitations
		2.4.3 Introduction to Fuzzy MCDM
		2.4.4 Addressing Imprecise Criteria Through Fuzzy MCDM Approaches
	2.5 Fuzzy Goal Programming
		2.5.1 Understanding Fuzzy Goal Programming
		2.5.2 Integrating FGP with MCO
		2.5.3 Handling Conflicting Objectives Using FGP
		2.5.4 Applications of FGP in Engineering
	2.6 Fuzzy TOPSIS
		2.6.1 Introduction to Fuzzy TOPSIS
		2.6.2 Steps Involved in Fuzzy TOPSIS
		2.6.3 Fuzzy TOPSIS in Engineering Decision-Making
		2.6.4 Case Studies Demonstrating the Advantages of Fuzzy TOPSIS
	2.7 A Real-World Case Study
		2.7.1 Fuzzy Systems in Engineering Domains
		2.7.2 Outcomes and Benefits of Fuzzy Systems
		2.7.3 Advantages of Fuzzy Systems over Traditional Optimization Systems
	2.8 Future Trends and Conclusion
		2.8.1 Emerging Trends in Fuzzy Systems for Multicriteria Optimization
		2.8.2 Key Insights
		2.8.3 Contributions and Future Prospects in the Engineering Domain
	References
Chapter 3 Optimizing Ti-6Al-4V Milling under MQL Conditions Using SVR, NSGA-II, and TOPSIS
	3.1 Introduction
	3.2 Experiment Procedure
		3.2.1 Design of Experiments
		3.2.2 Experiment Setup
	3.3 Theoretical Background
		3.3.1 Support Vector Regression
		3.3.2 NSGA-II
		3.3.3 TOPSIS
	3.4 Solving the Multi-Objective Optimization Problem
		3.4.1 Defining the Problem
		3.4.2 Integrating SVR and NSGA-II with Entropy-Weighted TOPSIS
		3.4.3 Validated Experiments
	3.5 Conclusion
	References
Chapter 4 3D Printing Parameters for Optimum Tensile Strength Using the Taguchi-Based Response Surface Method
	4.1 Introduction
	4.2 Problem Statement
	4.3 Materials and Methods
		4.3.1 The FDM 3D Printer
		4.3.2 The PLA Filament
		4.3.3 The Taguchi Method
		4.3.4 Tensile Measurement
	4.4 Results and Discussion
		4.4.1 Process Parameter Selection
		4.4.2 Orthogonal Array Selection
		4.4.3 S/N Ratio and ANOVA Results
		4.4.4 The First Validation Experiment
		4.4.5 Developing the Response Surface Model
		4.4.6 The Second Validation Experiment
		4.4.7 Fracture Morphology Analysis
	4.5 Conclusion
	References
Chapter 5 Network Optimization Using the Max Product for Multicriteria Decision-Making
	5.1 Introduction
	5.2 Preliminaries
		5.2.1 Intuitionistic Fuzzy Graphs
		5.2.2 Strong Arc
		5.2.3 IFG Degrees
		5.2.4 Isolated Vertex
		5.2.5 Cardinality of an IFG
		5.2.6 Dominating Set
	5.3 Maximal Product of Three Intuitionistic Fuzzy Graphs
	5.4 Applications
	5.5 Results and Discussion
	5.6 Conclusion
	References
Chapter 6 Optimizing the Surface Roughness of H13 Steel Machined by Wire Electrical Discharge
	6.1 Introduction
	6.2 Problem Statement
	6.3 Materials and Methods
		6.3.1 Materials
		6.3.2 Taguchi Method
	6.4 Results and Discussion
		6.4.1 Microstructure
		6.4.2 Surface Roughness
	6.5 Conclusion
	6.6 Conflicts of Interest
	6.7 Questions
	6.8 Acknowledgement
	References
Chapter 7 The Impact Toughness of PBT/PA6 Composite Reinforced with Glass Fibers
	7.1 Introduction
	7.2 Materials and Methods
		7.2.1 Materials
		7.2.2 Measurement Methods
	7.3 Results and Discussion
		7.3.1 The Impact Toughness of PBT/PA6/GF Blends
		7.3.2 The Sample Microstructures
	7.4 Polynomial Regression Analysis
	7.5 Conclusion
	7.6 Questions
	7.7 Acknowledgment
	7.8 Conflicts of Interest
	References
Chapter 8 The Effect of Chamber Temperature on the Flexural Strength of Thermoplastic Polyurethane Plastic via FDM Technology
	8.1 Introduction
	8.2 The Experiment
	8.3 Results and Discussion
	8.4 Polynomial Regression Analysis
	8.5 Conclusion
	8.6 Conflicts of Interest
	8.7 Questions
	8.8 Acknowledgment
	References
Chapter 9 Enhancing Underwater Imagery Using Multicriteria Decision-Making with Machine Learning Techniques
	9.1 Introduction
	9.2 Rationale for the Study
	9.3 Materials and Methods
		9.3.1 Image Reading
		9.3.2 Color Space Conversion
		9.3.3 Splitting RGB Images
		9.3.4 Histogram Equalization
		9.3.5 Manual White Balancing
	9.4 Result and Discussion
		9.4.1 Contrast Improvement
		9.4.2 Color Accuracy
		9.4.3 Overall Image Quality Evaluation
	9.5 Conclusion
	References
Chapter 10 Selecting Optimal Electric Vehicle Charging Station Sites Based on Analytic Hierarchy and VIKOR
	10.1 Introduction
		10.1.1 Literature Review
	10.2 Traditional Methods of MCDM
		10.2.1 AHP
		10.2.2 The VIKOR Method
	10.3 The Proposed Hybrid Model
	10.4 Results and Discussion
	10.5 Conclusion
	References
Chapter 11 Optimum Topological Indices for Intuitionistic Fuzzy Graphs
	11.1 Introduction
	11.2 Preliminaries
		11.2.1 Intuitionistic Fuzzy Graphs
	11.3 Intuitionistic Topological Indices
		11.3.1 First Zagreb Index
		11.3.2 Theorem
		11.3.3 Second Zagreb Index
		11.3.4 Forgotten Index
		11.3.5 Harmonic Index
		11.3.6 Randić Index
		11.3.7 Theorem
	11.4 Algorithms for Harmonic Index and Randić Index in Intuitionistic Fuzzy Graph
	11.5 Conclusion
	References
Chapter 12 Advancements in Multicriteria Decision-Making: Exploring Innovative Approaches
	12.1 Introduction
	12.2 Advancements in Multicriteria Decision-Making: Exploring Innovative Approaches
	12.3 Conclusions
	12.4 Acknowledgments
	12.5 Conflicts of Interest
Chapter 13 Machine Learning Techniques for Multicriteria Decision-Making
	13.1 Introduction
		13.1.1 The Contribution of the Chapter
		13.1.2 The Chapter Structure
	13.2 MCDM
		13.2.1 Fundamental MCDM Concepts
		13.2.2 The Importance of ML for MCDM
	13.3 The Role of ML in MCDM
		13.3.1 Data Handling and Analysis, Pattern Recognition, and Insights
		13.3.2 Predictive Modeling and Complex Decision Patterns
		13.3.3 Optimization and Adaptive Decision-Making
		13.3.4 Reducing Subjectivity and Ensemble Methods
		13.3.5 Handling Uncertainty and Real-Time Decision Support
	13.4 Classifying ML Techniques for MCDM
		13.4.1 Supervised Learning
		13.4.2 Unsupervised Learning
		13.4.3 Reinforcement Learning
		13.4.4 Deep Learning
	13.5 Specific ML Techniques
		13.5.1 Decision Trees for Rule-Based Decision-Making
		13.5.2 Clustering Algorithms for Grouping Similar Criteria
		13.5.3 Neural Networks for Complex Decision Patterns
		13.5.4 RL for Adaptive Decision-Making
	13.6 Challenges and Considerations
		13.6.1 Data Quality and Availability and Model Complexity
		13.6.2 Overfitting Generalization and Model Selection
		13.6.3 Feature Engineering and Interpretable Models
		13.6.4 Scalability, Changing Preferences, and Criteria
		13.6.5 Model Validation and Evaluation and Ethics and Bias Concerns
		13.6.6 Decision-Maker Involvement and Transparent Communication
	13.7 Case Studies
		13.7.1 Healthcare Resource Allocation
		13.7.2 Energy Efficiency in Buildings
		13.7.3 Environmental Impact Assessment
		13.7.4 Financial Portfolio Management
		13.7.5 Supply Chain Optimization
		13.7.6 Smart City Traffic Management
	13.8 Comparison and Evaluation
		13.8.1 Supervised Learning
		13.8.2 Unsupervised Learning
		13.8.3 Reinforcement Learning
		13.8.4 Deep Learning
	13.9 Future Directions
		13.9.1 Hybrid Approaches and Explainable AI for MCDM
		13.9.2 Handling Uncertainty and Dynamic Criteria Learning
		13.9.3 Human–AI Collaboration, Ethical Considerations, and Bias Mitigation
		13.9.4 Customization, Personalization, and RL in Real-World Scenarios
		13.9.5 Big Data, Scalability, and Human-Centric Design
	13.10 Conclusion
	References
Chapter 14 Locating Electric Vehicle Power Stations Using Neutrosophic TOPSIS
	14.1 Introduction
	14.2 Preliminaries
		14.2.1 Fuzzy TOPSIS
		14.2.2 Neutrosophic TOPSIS
		14.2.3 Criteria
		14.2.4 Decision Matrix
		14.2.5 Normalized Decision Matrix
		14.2.6 Weighted Normalized Matrix
		14.2.7 Ranking
	14.3 Defining the Neutrosophic TOPSIS Algorithm
	14.4 Applying the Algorithm
	14.5 Numeric Illustration
	14.6 Conclusion
	References
Chapter 15 Multicriteria Decision-Making Modeling Using Spherical Neutrosophic Similarity Measures
	15.1 Introduction
	15.2 Basic Concepts
		15.2.1 Spherical Neutrosophic Set
		15.2.2 Operation of SNS
		15.2.3 Similarity Measures between SNSs
		15.2.4 Trigonometric Similarity Measures
		15.2.5 Properties of Trigonometric Similarity Measures
	15.3 The Decision-Making Algorithm
	15.4 Applying the Trigonometric Similarity Measures
	15.5 Conclusion
	References
Chapter 16 A Study on Machine Learning Twig Graphs on the Hyper Wiener Index of Complete Graph
	16.1 Introduction
	16.2 Preliminary Definitions
		16.2.1 Definition
		16.2.2 Definition
		16.2.3 Definition
		16.2.4 Definition
		16.2.5 Definition
		16.2.6 Definition
		16.2.7 Definition
		16.2.8 Definition
	16.3 Results and Discussion
		16.3.1 Hyper-Wiener Index of a Graph
	16.4 Performance Analysis
		16.4.1 The C++ Coding for HWTG (KmΘ(PmΘK1))
		16.4.2 The C++ Coding for HWTG (KmΘTm)
	16.5 Conclusion
	References
Chapter 17 Enhancing Multicriteria Decision-Making through Cryptographic Security Systems
	17.1 Introduction
	17.2 Key Generation
		17.2.1 Encryption
		17.2.2 Decryption
	17.3 Illustration
	17.4 Applications
	17.5 Conclusion
	References
Chapter 18 AI-Powered Decision-Making Applications for Sustainable Development
	18.1 Introduction
		18.1.1 Evolution and Impact of AI
		18.1.2 Leveraging AI for Sustainable Development: Opportunities, Challenges, and Ethical Considerations
	18.2 Benefits of AI for Sustainable Development
		18.2.1 AI for Inclusive Education and Sustainable Development
		18.2.2 AI for Sustainable Development and Financial Inclusion
		18.2.3 AI for Sustainable Urban Development and Environmental Management
		18.2.4 Fostering Sustainable Development in Business Ecosystems Through AI
		18.2.5 Overcoming the Limitations and Possibilities at the Crossroads of AI and Sustainable Development
	18.3 Challenges for AI in Sustainable Development
	18.4 AI-Powered Decision-Making in Sustainable Development
	18.5 Conclusion
	References
Chapter 19 Artificial Intelligence Algorithms for Better Decision-Making
	19.1 Introduction
	19.2 Literature Review
		19.2.1 Software Reliability
		19.2.2 Supervised Learning
		19.2.3 Unsupervised Learning
	19.3 Methodology
		19.3.1 Classification
		19.3.2 Optimization
		19.3.3 Development Cycle
	19.4 Implementation
		19.4.1 Data Requirements
		19.4.2 Data Preparation
		19.4.3 Model Development
		19.4.4 Model Evaluation
		19.4.5 Building the Interface
		19.4.6 Model Deployment
	19.5 Results and Discussion
	19.6 Conclusion
	References
Chapter 20 Multicriterion Analysis of Fusion Sort: A Hybrid Approach to Sorting Algorithms
	20.1 Introduction
	20.2 Problem Statement
	20.3 The Proposed Work
		20.3.1 Methodology
		20.3.2 Algorithms
	20.4 Results and Discussion
	20.5 Performance Analysis
		20.5.1 Execution Time
		20.5.2 Number of Comparisons
		20.5.3 Time Complexity
	20.6 Conclusion
	References
Chapter 21 Cruising through the Choices: Unraveling Destination Decision-Making Dilemmas with Social Networks via MCDM
	21.1 Introduction
	21.2 Literature Review
		21.2.1 Theoretical Foundation
		21.2.2 Tourist Motivation with Destination Decision-Making
		21.2.3 Information Searching in Tourists’ Destination Decision-Making
		21.2.4 Travel Planning and Destination Decision-Making
	21.3 Research Design and Methodology
		21.3.1 The MCDM Framework and Validation
		21.3.2 DEMATEL
		21.3.3 The Research Procedure
		21.3.4 Questionnaire Design and Sampling
	21.4 Results and Discussion
		21.4.1 Experts’ DEMATEL Results
		21.4.2 Tourists’ DEMATEL Results
	21.5 Conclusions and Suggestions
		21.5.1 Conclusions
		21.5.2 Practical Implications and Suggestions
	References
Chapter 22 Analyzing Outcome-Based Education Using Multicriteria Decision-Making
	22.1 Introduction
	22.2 Standard Definitions
		22.2.1 Attributes
		22.2.2 Criteria
		22.2.3 Decision Matrix
		22.2.4 Normalized Decision Matrix
		22.2.5 Weighted Normalized Matrix
		22.2.6 TOPSIS Score
		22.2.7 Ranking
	22.3 The Outranking Algorithm
	22.4 The TOPSIS Algorithm
	22.5 Conclusion
	References
Chapter 23 Selecting a Best Professor Awardee Using Multicriteria Decision-Making
	23.1 Introduction
	23.2 Standard Definitions
		23.2.1 Attributes
		23.2.2 Criteria
		23.2.3 Decision Matrix
		23.2.4 Normalized Decision Matrix
		23.2.5 Variance
		23.2.6 Weighted Normalized Matrix
		23.2.7 Concordance Matrix
		23.2.8 Disconcordance Matrix
		23.2.9 Pure Concordance Index
		23.2.10 Pure Disconcordance Index
		23.2.11 Ranking Table
	23.3 Methodology
	23.4 MCDM Results and Discussion
	23.5 Results and Discussion
	23.6 Conclusion
	References
Chapter 24 Predicting Lumpy Skin Disease Using Machine Learning
	24.1 Introduction
	24.2 Characteristics of Lumpy Skin Disease
		24.2.1 LSD Transmission Routes
		24.2.2 Factors Influencing Transmission
		24.2.3 Prevention and Control Measures
	24.3 Problem Statement
		24.3.1 Supervised Education
		24.3.2 Unsupervised Learning
	24.4 The Model Development Hierarchy
	24.5 The LSD Prediction Model
	24.6 Results and Discussion
	24.7 Conclusion
	References
Author Index
Subject Index