Bioinspired Optimization Methods and Their Applications: 10th International Conference, BIOMA 2022, Maribor, Slovenia, November 17–18, 2022, Proceedings

Description

This book constitutes the refereed proceedings of the 10th International Conference on Bioinspired Optimization Methods and Their Applications, BIOMA 2022, held in Maribor, Slovenia, in November 2022. The 19 full papers presented in this book were carefully reviewed and selected from 23 submissions. The papers in this BIOMA proceedings specialized in bioinspired algorithms as a means for solving the optimization problems and came in two categories: theoretical studies and methodology advancements on the one hand, and algorithm adjustments and their applications on the other. Preface Organization Contents An Agent-Based Model to Investigate Different Behaviours in a Crowd Simulation 1 Introduction 2 The Mathematical Model 3 NetLogo Model 4 Experimental Results 5 Conclusions and Future Works References Accelerating Evolutionary Neural Architecture Search for Remaining Useful Life Prediction 1 Introduction 2 Background 3 Method 3.1 Multi-objective Optimization 3.2 Speeding up Evaluation 4 Experimental Setup 4.1 Computational Setup and Benchmark Dataset 4.2 Data Preparation and Training Details 5 Results 6 Conclusions References ACOCaRS: Ant Colony Optimization Algorithm for Traveling Car Renter Problem 1 Introduction 2 Related Work 3 Problem Description 4 ACOCaRS Algorithm 5 Experiment 5.1 Testbed 5.2 Results 6 Discussion 7 Conclusion and Future Work References A New Type of Anomaly Detection Problem in Dynamic Graphs: An Ant Colony Optimization Approach 1 Introduction 2 Anomaly Detection Problem 3 Proposed Approach 4 Numerical Experiments 4.1 Benchmarks 4.2 Parameter Setting 4.3 Anomaly Detection in Real-World Networks 5 Conclusion and Further Work References .28em plus .1em minus .1emCSS–A Cheap-Surrogate-Based Selection Operator for Multi-objective Optimization 1 Introduction 2 Background 2.1 Spherical Search 2.2 Cheap Surrogate Selection (CSS) 3 Proposed Method 3.1 General Framework of CSS-MOEA 3.2 The Detailed Process of CSS-MOEA 4 Experiment Results 5 Conclusion References Empirical Similarity Measure for Metaheuristics 1 Introduction 2 Related Works 3 Preliminaries 3.1 Metaheuristic Algorithms 3.2 Benchmark Functions 3.3 Parameter Tuning 4 Proposed Comparison Method 4.1 Algorithm Instances 4.2 Algorithm Profiling 4.3 Measuring Similarity 5 Results 5.1 Comparing Instances of the Same Algorithm 5.2 Comparing Instances of the Same Tuning Function 5.3 Clustering the Algorithms' Instances Based on Similarity 5.4 Discussion 6 Conclusion References Evaluation of Parallel Hierarchical Differential Evolution for Min-Max Optimization Problems Using SciPy 1 Introduction 2 Definition of the Problem 3 Differential Evolution for MinMax Problems 3.1 Overview of Differential Evolution 3.2 Hierarchical (Nested) Differential Evolution and Parallel Model 4 Experimental Setup and Results 4.1 Benchmark Test Functions 4.2 Parameter Settings 4.3 Results and Discussion 5 Conclusion and Future Work References Explaining Differential Evolution Performance Through Problem Landscape Characteristics 1 Introduction 2 Related Work 3 Experimental Setup 3.1 Benchmark Problem Portfolio 3.2 Landscape Data 3.3 Algorithm Portfolio 3.4 Performance Data 3.5 Regression Models 3.6 Leave-One Instance Out Validation 3.7 SHAP Explanations 4 Results and Discussion 4.1 Optimization Algorithms Performance 4.2 Performance Prediction 4.3 Linking ELA Features to DE Performance 5 Conclusions References Genetic Improvement of TCP Congestion Avoidance 1 Introduction 2 Background 3 Related Works 4 Method 4.1 Code Simplification Procedure 5 Experimental Results 6 Conclusions and Future Work References Hybrid Acquisition Processes in Surrogate-Based Optimization. Application to Covid-19 Contact Reduction 1 Introduction 2 Background on Surrogate-Based Optimization 3 COVID-19 Contact Reduction Problem 4 Hybrid Acquisition Processes 5 Experiments 6 Conclusion References Investigating the Impact of Independent Rule Fitnesses in a Learning Classifier System 1 Introduction 2 Related Work 3 The Supervised Rule-Based Learning System 4 Evaluation 4.1 Experiment Design 4.2 Results 5 Conclusion References Modified Football Game Algorithm for Multimodal Optimization of Test Task Scheduling Problems Using Normalized Factor Random Key Encoding Scheme 1 Introduction 2 Problem Description and Mathematical Modeling 3 The Proposed Modified Football Game Algorithm (mFGA) 3.1 Classic FGA 3.2 Modified FGA 4 Normalized Factor Random Key Encoding Scheme 5 Multimodal Single-Objective Optimization of TTSP 6 Comparison and Discussion 7 Conclusion and Future Works References Performance Analysis of Selected Evolutionary Algorithms on Different Benchmark Functions 1 Introduction 2 Related Work 3 Experiment 3.1 CEC 2022 Single Objective Bound Constrained Numerical Optimization 3.2 CEC 2021 Single Objective Bound Constrained Optimization 3.3 CEC 2017 Single Objective Bound Constrained Optimization 4 Discussion 5 Conclusion References Refining Mutation Variants in Cartesian Genetic Programming 1 Introduction 2 Related Work 3 Cartesian Genetic Programming 3.1 Introduction to Cartesian Genetic Programming 3.2 Mutation Algorithm 4 Further Changes in the Mutation Algorithm 4.1 Probabilistic Mutation 4.2 Single and Multiple Mutation 5 Preliminaries 5.1 Experiment Description 5.2 Datasets 6 Experiments 6.1 Impact of Different Probabilistic Mutation Strategies 6.2 Impact of Multi-n and DMulti-n 7 Conclusion References Slime Mould Algorithm: An Experimental Study of Nature-Inspired Optimiser 1 Introduction 1.1 Slime Mould Algorithm 1.2 Previous Works 2 Newly Proposed Variants of SMA 2.1 Linear Reduction of the Population Size 2.2 Eigen Transformation 2.3 Perturbation 2.4 Adaptation of Parameter z 3 Methods Used in Experiments 4 Experimental Settings 5 Results 6 Conclusion References SMOTE Inspired Extension for Differential Evolution 1 Introduction 2 Background 2.1 Differential Evolution 2.2 Synthetic Minority Oversampling Technique (SMOTE) 2.3 Literature Overview 3 Proposed Mechanism for Differential Evolution 4 Experimental Analysis 4.1 Setup 4.2 Comparison Against Other Mechanisms 4.3 Incorporation into Improved Algorithm Variants 5 Conclusion References The Influence of Local Search on Genetic Algorithms with Balanced Representations 1 Introduction 2 Background 2.1 Balanced Crossover Operators 2.2 Boolean Functions 3 Local Search of Boolean Functions 4 Experiments 4.1 Experimental Setting 4.2 Results 4.3 Discussion 5 Conclusions References Trade-Off of Networks on Weighted Space Analyzed via a Method Mimicking Human Walking Track Superposition 1 Introduction and Related Work 2 Simulation Model of WTSN on Weighted Space 2.1 Generation Process of WTSN on a Mixture of Different Ground Conditions 2.2 Pareto-Optimal Path Between Two Demand Vertices 2.3 Algorithm for WTSN on Weighted Space 3 Analysis of Differences in Pareto Frontier by Weighted Space 3.1 Experimental Spaces Setting 3.2 Result of Pareto Frontier Approximation 4 Discussion 5 Conclusion and Further Work References Towards Interpretable Policies in Multi-agent Reinforcement Learning Tasks 1 Introduction 2 Related Work 3 Method 3.1 Creation of the Teams 3.2 Fitness Evaluation 3.3 Individual Encoding 3.4 Operators 4 Experimental Setup 4.1 Environment 4.2 Parameters 5 Experimental Results 5.1 Interpretation 5.2 Comparison with a Non Co-Evolutionary Approach 6 Conclusions and Future Works References Author Index