Metaheuristic Algorithms

✍ Scribed by Gai-Ge Wang, Xiaoqi Zhao, Keqin Li

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 470
• Edition: 1
• Category: Library

✦ Synopsis

This book introduces the theory and applications of metaheuristic algorithms. It also provides methods for solving practical problems in such fields as software engineering, image recognition, video networks, and in the oceans.

In the theoretical section, the book introduces the information feedback model, learning-based intelligent optimization, dynamic multi-objective optimization, and multi-model optimization. In the applications section, the book presents applications of optimization algorithms to neural architecture search, fuzz testing, oceans, and image processing. The neural architecture search chapter introduces the latest NAS method. The fuzz testing chapter uses multi-objective optimization and ant colony optimization to solve the seed selection and energy allocation problems in fuzz testing. In the ocean chapter, deep learning methods such as CNN, transformer, and attention-based methods are used to describe ENSO prediction and image processing for marine fish identification, and to provide an overview of traditional classification methods and deep learning methods.

Rich in examples, this book will be a great resource for students, scholars, and those interested in metaheuristic algorithms, as well as professional practitioners and researchers working on related topics.

✦ Table of Contents

Cover
Half Title
Title
Copyright
Contents
Foreword
Preface
Chapter 1 ▪ Introduction
1.1 Significance of Metaheuristic Algorithm Research
1.2 Generation and Development of the Metaheuristic Algorithm
1.3 Application Scenarios
1.3.1 Neural Architecture Search
1.3.2 Fuzzing
1.3.3 Ocean
1.3.4 Image Processing
1.4 Conclusions
Section I Theoretical
Chapter 2 ▪ Information Feedback Model (IFM) and Its Applications
2.1 Introduction
2.2 Information Feedback Models
2.2.1 Fixed Manner
2.2.2 Random Manner
2.3 Enhancing MOEA/D with IFM for Large-Scale Many-Objective Optimization
2.3.1 Background
2.3.2 MOEA/D
2.3.3 MOEA/D-IFM
2.3.4 Experimental Results and Analysis
2.4 Improving NSGA-III with IFM for Large-Scale Many-Objective Optimization
2.4.1 Background
2.4.2 NSGA-III
2.4.3 NSGAIII-IFM
2.4.4 Experimental Results and Analysis
2.5 Cross-Generation de with IFM for Multi-Objective Optimization
2.5.1 Background
2.5.2 DEHF
2.5.3 Experimental Results and Analysis
2.6 Improved RPD-NSGA-II with IFM for Large-Scale Many-Objective Optimization
2.6.1 Background
2.6.2 RPD-NSGA-II-IFM
2.6.3 Experimental Results and Analysis
2.7 Improving 1by1EA with IFM for Large-Scale Many-Objective Optimization
2.7.1 Background
2.7.2 1by1EA
2.7.3 1by1EA-IFM
2.7.4 Experimental Results and Analysis
2.8 Conclusions
Chapter 3 ▪ Learning-Based Intelligent Optimization Algorithms
3.1 Introduction
3.2 IMEHO
3.2.1 Background
3.2.2 Improved Elephant Herding Optimization Algorithm
3.2.3 Comparison between Different Strategies
3.2.4 IMEHO Algorithm
3.2.5 Experimental Results and Analysis
3.3 BLEHO
3.3.1 Background
3.3.2 BLEHO Algorithm
3.3.3 Comparison between BLEHO and Classical Algorithms
3.3.4 Experimental Results and Analysis
3.4 OBLEHO
3.4.1 Background
3.4.2 OBLEHO Algorithm
3.4.3 Experimental Results and Analysis
3.5 Other Research Work
3.6 Conclusions
Chapter 4 ▪ Dynamic Multi-Objective Optimization
4.1 Introduction
4.2 Dynamic Multi-Objective Optimization Problems
4.2.1 Research Progress
4.2.2 Test Functions
4.2.3 Performance Measures
4.3 Improved NSGA-III Using Transfer Learning and Centroid Distance
4.3.1 Centroid Distance Method
4.3.2 Transfer Learning Method
4.3.3 TCNSGA-III
4.4 Improved NSGA-III with Second-Order Difference Random Strategy
4.4.1 NSGA-III
4.4.2 Change Detection
4.4.3 Second-Order Difference and Random Strategies
4.5 Combining Key-Points-Based Transfer Learning and Hybrid Prediction Strategies
4.5.1 Overall Framework
4.5.2 Determine Key Points
4.5.3 Key Points-Based Prediction
4.5.4 Transfer
4.5.5 Center-Point-Based Feed-Forward Prediction
4.6 Conclusions
Chapter 5 ▪ Multimodal Multi-Objective Optimization
5.1 Introduction
5.2 Multimodal Multi-Objective Optimization
5.2.1 Benchmarks
5.2.2 Measure Indexes
5.3 MMODE_TSM_MMED
5.3.1 Background
5.3.2 Two-Stage Mutation Strategy
5.3.3 Modified Maximum Extension Distance
5.3.4 MMED-Best Individual Selection
5.3.5 Environmental Selection
5.3.6 MMODE_TSM_MMED
5.3.7 Parameter Settings
5.3.8 Experimental Results and Analysis
5.4 MMODE_ICD
5.4.1 Background
5.4.2 Adaptive Individual Selection to Generate Difference Vector
5.4.3 Embed the Non-Dominated Rank into SCD
5.4.4 Ratio Selection
5.4.5 MMODE_ICD
5.4.6 Parameter Settings
5.4.7 Experimental Results and Analysis
5.5 CMMODE
5.5.1 Background
5.5.2 CMMODE
5.5.3 Design of CMMFs
5.5.4 Experimental Results and Analysis
5.6 MMPDNB
5.6.1 Background
5.6.2 Framework of MMPDNB
5.6.3 Experimental Results and Analysis
5.7 Conclusions
Section II Applications
Chapter 6 ▪ Neural Architecture Search
6.1 Introduction
6.1.1 Survey on Neural Architecture Search
6.1.2 ECNN: Architecture Evolution of Convolutional Neural Network Using Monarch Butterfly Optimization
6.2 Neural Architecture Search
6.3 Related Work on Neural Architecture Search
6.3.1 Search Strategy
6.3.2 Architecture Space
6.4 ECNN: Architecture Evolution of CNN Using MBO
6.4.1 Background
6.4.2 Design
6.4.3 Experimental Results and Analysis
6.5 Mutation-Based NAS Algorithm Using Blocks
6.5.1 Background
6.5.2 Design
6.5.3 Experimental Results and Analysis
6.6 Conclusions
Chapter 7 ▪ Fuzz Testing
7.1 Introduction
7.1.1 Many-Objective Optimization Seed Schedule for Fuzzing
7.1.2 Adaptive Mutation Schedule for Fuzzing
7.1.3 Adaptive Energy Allocation for Greybox Fuzzing
7.2 Fuzzing
7.3 Many-Objective Optimization Seed Schedule for Fuzzer
7.3.1 Many-Objective Optimization Problem
7.3.2 MOOFuzz
7.3.3 Experimental Results and Analysis
7.4 An Adaptive Mutation Schedule for Fuzzing
7.4.1 Background and Motivation
7.4.2 AMSFuzz
7.4.3 Experimental Results and Analysis
7.5 An Adaptive Energy Allocation for Fuzzing
7.5.1 Ant Colony Optimization Algorithm
7.5.2 Motivation
7.5.3 ACOFuzz
7.5.4 Experimental Results and Analysis
7.6 Conclusions
Chapter 8 ▪ Application of Intelligent Algorithms in the Ocean
8.1 Introduction
8.2 ENSO Phenomenon and its Influence
8.2.1 ENSO Phenomenon
8.2.2 ENSO Index
8.2.3 Recent Research of ENSO Theory
8.3 ENSO Prediction and its Development
8.3.1 Deep Learning for Multiyear ENSO Forecasts
8.3.2 Prediction of ENSO beyond SPB Using Deep ConvLSTM
8.3.3 Transformer for EI Niño–Southern Oscillation Prediction
8.3.4 Forecasting ENSO Using Improved Attention Mechanism
8.3.5 Multimodality of the Ocean
8.4 Fish Classification Methods
8.4.1 Image Acquisition
8.4.2 Image Preprocessing
8.4.3 Traditional Approaches
8.4.4 Deep Learning Approaches
8.5 Conclusions
Chapter 9 ▪ Image Processing
9.1 Introduction
9.1.1 Neural Network Design
9.1.2 Semantic Segmentation
9.1.3 Object Detection
9.2 Image Processing
9.2.1 Image Introduction
9.2.2 Common Methods
9.2.3 Image Analysis
9.2.4 Medical Image Processing
9.3 Convunext
9.3.1 Background
9.3.2 Model Design
9.3.3 Experimental Results and Analysis
9.4 YOLO-AA
9.4.1 Background
9.4.2 Improvement of YOLOv4 Structure Based on CBAM
9.4.3 Improvement of YOLOv4 Structure Based on ASPP
9.5 VSD
9.5.1 Background
9.5.2 VSD
9.5.3 Experimental Results and Analysis
9.6 FSL
9.6.1 Background
9.6.2 FSL Methods
9.6.3 Feature Extraction Network
9.6.4 DC-EPNet
9.6.5 AM-EPNet
9.7 Conclusions
9.7.1 How to Obtain High-Quality Object Detection Datasets
9.7.2 How to Better Apply to Video Object Detection
9.7.3 How to Quickly Design an Object Detection Algorithm That Makes It Easier to Actually Implement the Project
References