Bio-inspired computing theories and applications : 16th International Conference, BIC-TA 2021, Taiyuan, China, December 17-19 2021, revised selected papers Part 1

This two-volume set (CCIS 1565 and CCIS 1566) constitutes selected and revised papers from the 16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021, held in Taiyuan, China, in December 2021. The 67 papers presented were thoroughly reviewed and selected from 211 submissions. The papers are organized in the following topical sections: ​evolutionary computation and swarm intelligence; DNA and molecular computing; ​machine learning and computer vision. Preface Organization Contents – Part I Contents – Part II Evolutionary Computation and Swarm Intelligence An Optimization Task Scheduling Model for Multi-robot Systems in Intelligent Warehouses 1 Introduction 2 Related Work 3 Intelligent Warehouses 3.1 Problem Statement 3.2 BHM 4 Improved Intelligent Warehouses 4.1 New Model 4.2 New Model 5 Simulated Experiments 5.1 Performance Metrics 5.2 Parameter Settings 5.3 Analysis of Results 6 Conclusion References A Multi-objective Optimization Algorithm for Wireless Sensor Network Energy Balance Problem in Internet of Things Abstract 1 Introduction 2 WSN Energy Balance Problem 2.1 Problem Analysis 2.2 Problem Model 3 Algorithm Principle 3.1 NSGA-II 3.2 Clustering Mechanism 3.3 Framework of CMNSGA-II 4 Experimental Simulation 4.1 Parameter Setting 4.2 Result Analysis 5 Conclusion References Improved AODV Routing Protocol Based on Multi-objective Simulated Annealing Algorithm Abstract 1 Introduction 2 Ad Hoc Network and AODV Protocol 3 Multi-objective Simulated Annealing 3.1 Single-objective Simulated Annealing 3.2 Multi-objective Simulated Annealing 3.3 Main Process of Multi-target Annealing 4 Multi-objective Optimization AODV Routing Protocol 4.1 Network Model 4.2 Fitness Function 4.3 Perturbation Function 4.4 Multi-objective Simulated Annealing Optimization Algorithm 5 Simulation and Analysis 5.1 Simulation Scenario Description 5.2 Simulation Parameter Setting 5.3 Simulation Experiment Results and Comparative Analysis 6 Conclusion Acknowledgement References Solving Satellite Range Scheduling Problem with Learning-Based Artificial Bee Colony Algorithm Abstract 1 Introduction 2 Problem Description 3 Learning-Based Artificial Bee Colony Algorithm 3.1 Traditional Artificial Bee Colony Algorithm 3.2 Algorithm Overall Framework 3.3 Position-Based Learning Strategy 3.4 Error-Based Learning Strategy 3.5 Parameter Analysis 4 Experiment Analysis 4.1 Analysis of Algorithm 4.2 Comparison to State-Of-The-Art Algorithms 5 Conclusion Acknowledgement References Black Widow Spider Algorithm Based on Differential Evolution and Random Disturbance Abstract 1 Introduction 2 Black Widow Spider Algorithm 3 Improved Black Widow Spider Algorithm 3.1 Population Reproduction for Global Optimization 3.2 Population Mutation Based on Differential Evolution Algorithm 3.3 Random Disturbance Strategy 4 Algorithm Implementation 5 Simulation Experiment 5.1 Test Function 5.2 Design Problems of Tension Spring 6 Summary Acknowledgments References Attribute Selection Method Based on Artificial Bee Colony Algorithm and Neighborhood Discrimination Matrix Optimization 1 Introduction 2 Related Knowledge 2.1 Basic Knowledge of Neighborhood Rough Set 2.2 Artificial Bee Colony and Its Improved Algorithm 3 Improved Attribute Selection Algorithm for Artificial Bee Colony and Neighborhood Discrimination Matrix 3.1 Definition of Attribute Importance of Neighborhood Discernibility Matrix 3.2 Fitness Function Construction 3.3 Neighborhood Discernibility Matrix Importance and Artificial Bee Colony Feature Selection Algorithm 4 Experiment Analysis 4.1 Selection of 4.2 Algorithm Comparison Results 4.3 Algorithm Performance Comparison 5 Concluding Remarks References A Cuckoo Quantum Evolutionary Algorithm for the Graph Coloring Problem Abstract 1 Introduction 2 Problem Description 3 The Cuckoo Quantum Evolutionary Algorithm for GCP 3.1 Representation of the Solution to the Graph Coloring Problem 3.2 Quantum Matrix in the Cuckoo Quantum Evolutionary Algorithm 3.3 Framework of the Cuckoo Quantum Evolutionary Algorithm 3.4 Initialization of the CQEA 3.5 Local Search in the Solution Space 3.6 The Cuckoo Search 3.7 The Perturbance Strategy 4 Experimental Results 5 Conclusion References Feature Selection Algorithm Based on Discernibility Matrix and Fruit Fly Optimization 1 Introduction 2 Related Knowledge 2.1 Rough Set Theory 2.2 Fruit Fly Optimization Algorithm 3 Feature Selection Algorithm Based on Discernibility Matrix and Fruit Fly Optimization 3.1 Method of Defining Attribute Importance Based on Discernibility Matrix 3.2 Rough Set Fitness Function 3.3 Feature Selection Algorithm Based on Discernibility Matrix and Improved Fruit Fly Optimization 3.4 Algorithm Time Complexity 4 Experimental Data Analysis 4.1 Instance Verification 4.2 UCI Data Sets Experimental Data Analysis 5 Concluding Remarks References Feature Selection Method Based on Ant Colony Optimization Algorithm and Improved Neighborhood Discernibility Matrix 1 Introduction 2 Related Knowledge 2.1 Neighborhood Rough Set Theory 2.2 Ant Colony Algorithm and Its Optimized Feature Selection Method 3 Feature Selection Method Based on ACO and Improved Neighborhood Discernibility Matrix 3.1 The Definition of Attribute Importance of Neighborhood Discernibility Matrix 3.2 Description of Algorithm Steps 3.3 Analysis of Algorithm Time Complexity 4 Analysis of Experimental Data 4.1 Case Analysis 4.2 Analysis of UCI Data Set 5 Concluding Remarks References Implementation and Application of NSGA-III Improved Algorithm in Multi-objective Environment Abstract 1 Introduction 2 Many-Objective Problems and EMO Methodologies 2.1 Potential Difficulties in Dealing with Multi-objective Problems 2.2 Two Strategies to Face These Difficulties 3 NSGA-III Algorithm and Its Improvement 3.1 Determines the Reference Point on the Hyperplane 3.2 Normalization of Population Members 3.3 Association Operation 3.4 Inheritance of Population Offspring 3.5 Evaluation of Service Performance 4 Experiment 4.1 Experimental Environment Setting 4.2 Analysis of Experimental Results 5 Conclusion References A Differential Evolution Algorithm for Multi-objective Mixed-Variable Optimization Problems Abstract 1 Introduction 2 Related Work 3 Overview 3.1 Review of NSGA-II 3.2 Review of MCDEmv 4 The Proposed MO-MCDEmv 4.1 Selection of the Optimal Individual 4.2 The Modifications of Statistics-Based Local Search 4.3 The Framework of MO-MCDEmv 5 Numerical Experiment 5.1 Set Relevant Parameters 5.2 The Results of Two Practical MO-MVOPs 6 Conclusion Acknowledgments References An Effective Data Balancing Strategy Based on Swarm Intelligence Algorithm for Malicious Code Detection and Classification 1 Introduction 2 Swarm Intelligence Optimization Model 3 Dynamic Sampling Strategy Based on Swarm Intelligence Algorithm 3.1 Dynamic Sampling Model 3.2 Dynamic Sampling Based on Swarm Intelligence Algorithm 4 Experimental Evaluation 4.1 Experimental Setup 4.2 Type of Unbalanced Data 4.3 Data Sets and Models 4.4 Result Analysis 5 Conclusion References Adaptive Multi-strategy Learning Particle Swarm Optimization with Evolutionary State Estimation 1 Introduction 2 Related Works 2.1 Canonical PSO 2.2 Variants of PSO 3 Proposed AMSLPSO Algorithm 3.1 Evolutionary State Estimation 3.2 Random Elite and Mainstream Learning Exemplars 3.3 Choose Learning Strategy 3.4 Framework of AMSLPSO 4 Experimental Results and Analysis 4.1 Benchmark Functions and Comparison Algorithms 4.2 Experimental Results 5 Conclusion References Water Wave Optimization with Distributed-Learning Refraction 1 Introduction 2 The Basic WWO Algorithm 2.1 Propagation 2.2 Refraction 2.3 Breaking 2.4 The Algorithmic Framework of WWO 3 The Proposed DLWWO Algorithm 3.1 Nonlinear Dimension Reduction 3.2 Distributed-Learning Refraction 3.3 The Framework of DLWWO 3.4 Runtime Complexity of DLWWO 4 Numerical Experiments 4.1 Experimental Parameter Setting 4.2 Comparative Experiments 5 Conclusion References Adaptive Differential Privacy Budget Allocation Algorithm Based on Random Forest Abstract 1 Introduction 2 Related Work 3 Algorithm-Related Definitions 3.1 Solving for Feature Weights and Decision Tree Weights. 3.2 Filtering of Feature Sets 3.3 Adaptive Allocation of Privacy Protection Budgets 4 Algorithm Implementation and Analysis 4.1 Algorithm Flow 4.2 Algorithm Description 5 Experimental Results and Analysis 5.1 Experimental Design 6 Experimental Results and Analysis 7 Conclusion and Discussion References A Node Influence Based Memetic Algorithm for Community Detection in Complex Networks Abstract 1 Introduction 2 Background Knowledge 2.1 Modularity 2.2 Transition Probability Matrix 3 Proposed Algorithm 3.1 Representation 3.2 Framework 3.3 Initialization 3.4 Selection 3.5 Crossover 3.6 Mutation 3.7 Multi-level Greedy Search 4 Experimental Study and Results Analysis 4.1 Experimental Settings 4.2 Experimental Results and Analysis 5 Conclusions Acknowledgements References Adaptive Constraint Multi-objective Differential Evolution Algorithm Based on SARSA Method Abstract 1 Introduction 2 Literature Review 3 Basic Concepts 3.1 Constrained Multi-objective Optimization Problems 3.2 Concepts in Multi-objective Optimization Problems 3.3 Performance Metrics 3.4 Basics of DE 4 Proposed Algorithm 4.1 Adaptive Constraint Handling Technology 4.2 Adaptive Mutation Strategy 4.3 Adaptive Crossover Strategy 4.4 Overall Implementation of the Proposed Algorithm 5 Experimental Studies 5.1 Test Instance 5.2 Parameter Settings 5.3 Compared with Other Four CMOEAs 5.4 Experimental Analyses 6 Conclusion References A Hybrid Multi-objective Coevolutionary Approach for the Multi-user Agile Earth Observation Satellite Scheduling Problem 1 Introduction 2 Related Work 3 Multi-user Agile Earth Observation Satellite Scheduling Problem (MU-AEOSSP) 3.1 Problem Description 3.2 Assumptions 3.3 Notations and Variables 3.4 Time-Dependent Transition Time 3.5 Mathematical Modelling 4 A Hybrid Multi-objective Coevolutionary Approach (HMOCA) 4.1 Framework 4.2 Individual Representation and Initialization 4.3 Selection Operation 4.4 Offspring Generation 4.5 Local Search Operation 5 Computational Experiment 5.1 Experimental Setting 5.2 Experimental Results 6 Conclusion and Future Work References Surrogate-Assisted Artificial Bee Colony Algorithm 1 Introduction 2 Artificial Bee Colony Algorithm(ABC) 3 Proposed Approach 3.1 Multi-strategy 3.2 Radial Basis Function Network 3.3 Surrogate-Assisted Strategy Selection Mechanism 4 Experimental Study 4.1 Test Functions and Parameter Settings 4.2 Results on 30-Dimensional Problems 5 Conclusion References An Improved Bare-Bones Multi-objective Artificial Bee Colony Algorithm 1 Introduction 2 Multi-objective Optimization Problems 3 Artificial Bee Colony Algorithm 4 An Improved Bare-Bones Multi-objective ABC 5 Experimental Study 5.1 Performance Metrics 5.2 Comparison of BMOABC with Other Algorithms 6 Conclusion References Fitness Landscape Analysis: From Problem Understanding to Design of Evolutionary Algorithms Abstract 1 Introduction 2 Brief Introduction to FLA 3 Some FLA Techniques and the Applications to EAs 3.1 Fitness-Distance Correlation (FDC) 3.2 Information Landscape Measure (ILM) 3.3 Information Characteristics Analysis (ICA) 4 Further Discussion 5 Conclusion Acknowledgment References Optimal Overbooking Appointment Scheduling in Hospitals Using Evolutionary Markov Decision Process 1 Introduction 2 Background 2.1 CTMDP Model 2.2 Policy Iteration (PI) 2.3 Genetic Algorithm (GA) 3 Evolutionary CTMDP 3.1 Initialization 3.2 Policy Switching 3.3 Policy Mutation 3.4 Proposed Algorithm 4 Numerical Analysis 4.1 Case Study 4.2 Optimal Policy 5 Conclusion References A Multi-direction Prediction Multi-objective Hybrid Chemical Reaction Optimization Algorithm for Dynamic Multi-objective Optimization Abstract 1 Introduction 2 Background 2.1 Dynamic Multi-objective Optimization 2.2 Dynamic Multi-objective Evolutionary Algorithms 2.3 Hybrid Chemical Reaction Optimization Algorithm 3 Multi-direction Prediction Based Multi-objective Hybrid Chemical Reaction Algorithm 3.1 Exponential Smoothing Forecasting Model 3.2 Multi-directional Prediction Strategy 3.3 Proposed Framework and Implementation 4 Experimental Study 4.1 Test Instances and Performance Metrics 4.2 Parameter Settings 4.3 Experimental Results 5 Experimental Study Acknowledgements References Automatic Particle Swarm Optimizer Based on Reinforcement Learning Abstract 1 Introduction 2 Preliminary 2.1 PSO Variant Principle 2.2 Reinforcement Learning 3 Automatic PSO Based on Reinforcement Learning 3.1 Q-Learning Strategy 3.2 RLAPSO 4 Automatic PSO Based on Reinforcement Learning 4.1 Experimental Conditions 5 Experimental Results 6 Conclusion Acknowledgment References A Multi-UUV Formation Control and Reorganization Method Based on Path Tracking Controller and Improved Ant Colony Algorithm 1 Introduction 2 Multi-UUV Formation Control Method 2.1 UUV Kinematics and Dynamics Model 2.2 Multi-UUV Formation Controller Design 3 Formation Reorganization Method Based on Ant Colony Algorithm 3.1 Problem Description 3.2 Standard Ant Colony Algorithm 3.3 Improved Ant Colony Algorithm 4 Simulation Experiments 5 Conclusion References Firefly Algorithm with Opposition-Based Learning 1 Introduction 2 Introduction to FA 2.1 FA Concept 2.2 Improved FA Based on a Proportionally Decreasing Random Factor 3 Firefly Algorithm with Opposition-Based Learning 3.1 OL Principle 3.2 Opposition Learning FA 4 Experiment 4.1 Experiment Setup 4.2 Effect Analysis of Random Parameters 4.3 Comparison with Other Algorithms 5 Conclusion References An Optimization Method of Course Scheduling Problem Based on Improved Genetic Algorithm 1 Introduction 2 Mathematical Model of the Problem 2.1 Model Hypothesis 2.2 Constraints Analysis 3 Basic Genetic Algorithm 3.1 Representation of Solution 3.2 Objective Function 3.3 Selection 3.4 Crossover 3.5 Mutation 3.6 Reservation of Elites from Father Generation 3.7 Correcting of Schedule 4 Improvement of Genetic Algorithm 4.1 Dynamic Objective Function 4.2 Improvement on Mutation and Crossover 5 Experiments and Results 5.1 Setup of Experiments 5.2 Simulation Experiment 5.3 Convergence Performance Comparison Experiment 6 Conclusion References DNA and Molecular Computing Graphene Oxide-triplex Structure Based DNA Nanoswitches as a Programmable Tetracycline-Responsive Fluorescent Biosensor Abstract 1 Introduction 2 Experiment 2.1 Reagents and Materials 2.2 Construction of Triple Helix DNA and P1/GO Platform 2.3 Fluorescent Signal Detection 3 Principle 4 Results and Discussion 4.1 Feasibility Study 4.2 Condition Optimization 4.3 Performance Analysis 5 Conclusion References Construction of Complex Logic Circuit Based on DNA Logic Gate AND and OR Abstract 1 Introduction 2 Experimental principle 3 Experimental Materials and Methods 3.1 Chemicals and Materials 3.2 Instrumentation 3.3 Fluorescence Verification of Functional Logic Gates 4 Results and Discussion 4.1 OR Logic Gate 4.2 AND Logic Gate 4.3 Cascade Circuit 5 Conclusion Acknowledgement References Tetracycline Intelligent Target-Inducing Logic Gate Based on Triple-Stranded DNA Nanoswitch Abstract 1 Introduction 2 Experimental 2.1 Materials and Reagents 2.2 Synthesis of Triple-Stranded DNA (Ts-DNA) 2.3 Procedure for Logic Gate Operation and Fluorescent Detection 2.4 Sequences Design 3 Results and Discussion 3.1 Model Principle 3.2 Sensor System Algorithm Model 3.3 Optimization of Assay Conditions 4 Conclusion Conflicts Interest References Application of Chain P Systems with Promoters in Power Coordinated Control of Multi-microgrid 1 Introduction 2 Multi-microgrid 3 Application of PCPS to Power Coordinated Control in Multi-microgrid 3.1 Chain P Systems with Promoters 3.2 Modeling Process 3.3 Reasoning Test 4 Simulation Analysis 5 Conclusion References Solution to Satisfiability Problem Based on Molecular Beacon Microfluidic Chip Computing Model Abstract 1 Introduction 2 Satisfiability Problem 3 Establishment of Computing Model of Microfluidic Chip 3.1 Biological Algorithm 3.2 Example Analysis 3.3 Simulated Analysis 4 Conclusion Acknowledgements References Construction of Four-Variable Chaotic System Based on DNA Strand Displacement 1 Introduction 2 Modules Construction 2.1 Principle of DNA Strand Displacement 2.2 Modules of Four-Variable Chaotic System 3 Construction and Simulation of Chaotic System 4 Conclusions References Synchronization of Chaos with a Single Driving Variable Feedback Control Based on DNA Strand Displacement 1 Introduction 2 Construction of Chaotic System 2.1 DNA Strand Displacement Modules 2.2 Chaotic System Implementation 3 Synchronization of Chaotic System by PID Control 4 Conclusion References Sequential Spiking Neural P Systems with Polarizations Based on Minimum Spike Number Working in the Accepting Mode 1 Introduction 2 Spiking Neural P Systems with Polarizations 3 Turing Universality of PSN P Systems Based on Minimum Spike Number Working in the Accepting Mode 4 Conclusions and Discussions References Author Index