Computational intelligence : 11th international joint conference, IJCCI 2019, Vienna, Austria, September 17-19, 2019, revised selected papers / / Juan Julian Merelo [and four others], editors

• Pubblicazione: Cham, Switzerland : , : Springer, , [2021]; ©2021
• Descrizione fisica: 1 online resource (414 pages)
• Disciplina: 006.3
• Soggetto topico: Computational intelligence - Simulation methods; Artificial intelligence; Intel·ligència computacional; Mètodes de simulació; Intel·ligència artificial
• Soggetto genere / forma: Congressos; Llibres electrònics
• Persona (resp. second.): Merelo GuervósJuan Julián <1965->
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- Evolutionary Computation Theory and Applications -- Niching-Based Feature Selection with Multi-tree Genetic Programming for Dynamic Flexible Job Shop Scheduling -- 1 Introduction -- 2 Related Work -- 2.1 Routing and Sequencing Rules -- 2.2 Feature Selection -- 3 Background -- 3.1 Problem Definition -- 3.2 Genetic Programming for Dynamic Job Shop Scheduling -- 3.3 Multi-tree Genetic Programming -- 3.4 Niching-GP Feature Selection -- 3.5 Two-stage Genetic Programming with Feature Selection -- 4 Methods -- 4.1 Feature Selection for Multi-tree Genetic Programming -- 4.2 Two-Stage Multi-tree Genetic Programming -- 5 Experimental Setup -- 5.1 Scenario Generation Configuration -- 5.2 GP Configuration -- 5.3 Method Comparison -- 6 Experimental Results -- 7 Result Discussion -- 8 Conclusion -- 9 Future Work -- References -- Building Market Timing Strategies Using Trend Representative Testing and Computational Intelligence Metaheuristics -- 1 Introduction -- 2 Timing Buy and Sell Decisions -- 3 Related Work -- 4 Trend Representative Testing: Simulating Various Market Conditions While Training and Testing -- 5 Market Timing Algorithms -- 5.1 Individual Encoding and Measuring Fitness -- 5.2 Genetic Algorithms -- 5.3 Particle Swarm Optimization -- 6 Experimental Setup -- 7 Results -- 8 Conclusion -- References -- Hybrid Strategy Coupling EGO and CMA-ES for Structural Topology Optimization in Statics and Crashworthiness -- 1 Introduction -- 2 Problem Representation -- 2.1 Parametrization -- 2.2 Geometry Mapping -- 3 Optimization Problem and Constraints -- 4 Resolution Strategy -- 4.1 Optimization Algorithm -- 4.2 Constraint Handling Techniques -- 5 Test Case -- 5.1 Linear Elastic Case -- 5.2 Nonlinear Crash Case -- 6 Experimental Setup -- 7 Results -- 7.1 9-Variables Linear Elastic Case. ; 7.2 15-Variables Test Cases -- 8 Conclusions -- References -- An Empirical Study on Insertion and Deletion Mutation in Cartesian Genetic Programming -- 1 Introduction -- 2 Related Work -- 2.1 Cartesian Genetic Programming -- 2.2 Advanced Mutation Techniques in Standard CGP -- 3 Insertion and Deletion Mutation in CGP -- 3.1 The Insertion Mutation Technique -- 3.2 The Deletion Mutation Technique -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Search Performance Evaluation -- 4.3 Fitness Range Analysis -- 4.4 Active Function Node Range Analysis -- 5 Comparison to EGGP -- 6 Discussion -- 7 Conclusion -- 8 Future Work -- References -- Handling Complexity in Some Typical Problems of Distributed Systems by Using Self-organizing Principles -- 1 Introduction -- 1.1 Self-organization -- 1.2 Complexity in Application Scenarios -- 1.3 Measurement of Complexity -- 2 Swarm Intelligence in Distributed Systems -- 2.1 Some Selected Distributed Systems' Use-Cases -- 2.2 Algorithm Recommendation for Selected Use Cases -- 3 An Illustration: Bee Algorithm for Dynamic Load Balancing -- 3.1 Bee Algorithm -- 3.2 P2P Network Model -- 3.3 Convergence -- 4 Conclusion -- References -- Fuzzy Computation Theory and Applications -- Markov Decision Processes with Fuzzy Risk-Sensitive Rewards: The Best Coherent Risk Measures Under Risk Averse Utilities -- 1 Introduction -- 2 Coherent Risk Measures Derived from Risk Averse Utilities -- 3 Fuzziness and Extended Criteria -- 4 Estimation of Fuzziness with Evaluation Weights and θ-mean Functions -- 5 Markov Decision with Risk Allocation by Coherent Risk Measures -- 6 Maximization of Risk-Sensitive Running Rewards Under Feasible Risk Constraints -- 7 Maximization of Risk-Sensitive Terminal Rewards Under Feasible Risk Constraints -- 8 Numerical Examples -- 9 Conclusion -- References. ; Correlation Analysis Via Intuitionistic Fuzzy Modal and Aggregation Operators -- 1 Introduction -- 1.1 The Relevance for Contextualizing A-CC -- 1.2 Main Contribution -- 1.3 Paper Outline -- 2 Related Works -- 3 Preliminary -- 3.1 Intuitionistic Fuzzy Negations -- 3.2 Intuitionistic Fuzzy T-norms and T-conorms -- 3.3 Intuitionistic Fuzzy Modal Operators -- 3.4 Intuitionistic Fuzzy α-level Modal Operators -- 3.5 Action of Conjugate Operators on Aggregation Operators -- 4 Correlation from A-IFL -- 5 Results on Conjugate Modal Operators -- 6 A-CC Results on Modal Operators -- 7 A-CC Results α-Level Modal Operators -- 8 A-CC Results on Triangular (Co)Norms and Modal Operators -- 9 Conclusion and Further Work -- References -- Fuzzy Geometric Approach to Collision Estimation Under Gaussian Noise in Human-Robot Interaction -- 1 Introduction -- 2 Gaussian Noise and the Intersection Problem -- 2.1 Computation of Intersections-Analytical Approach -- 2.2 Transformation of Gaussian Distributions -- 3 Inverse Solution -- 4 Fuzzy Solution -- 5 Extension to Six Inputs and Two Outputs -- 5.1 General Approach -- 5.2 Fuzzy Approach -- 5.3 The Energetic Approach -- 6 Mixed Gaussian Distributions -- 7 Robots and Humans in Motion -- 8 Simulation Results -- 9 Conclusions -- References -- Predicting Cardiovascular Death with Automatically Designed Fuzzy Logic Rule-Based Models -- 1 Introduction -- 2 Evolutionary Fuzzy Logic Rule-Based Predictive Modeling -- 3 Data Description -- 4 Experiments and Results -- 5 Conclusions -- References -- Neural Computation Theory and Applications -- Neural Models to Quantify the Determinants of Truck Fuel Consumption -- 1 Introduction -- 2 Collection of Fuel Consumption and Input Factor Data -- 3 Extracting Statistics for Route and Driver Fuel Economy -- 4 Extracting Empirical Fuel Economy Models. ; 5 Estimating Model Compensation Impact on Driver Performance Measurements -- 6 Extracting Statistics for Fuel Shrinkage -- 7 Extracting Empirical Fuel Shrinkage Models -- 8 Conclusions and Future Work -- References -- Towards a Class-Aware Information Granulation for Graph Embedding and Classification -- 1 Introduction -- 2 Embedding via Data Granulation -- 3 The GRALG Classification System -- 3.1 Extractor -- 3.2 Granulator -- 3.3 Embedder -- 3.4 Classifier -- 3.5 Training Phase -- 3.6 Synthesized Classification Model and Test Phase -- 4 Extractor and Granulation Improvements -- 4.1 Class-Aware Extractor -- 4.2 Class-Aware Granulator -- 4.3 Class-Aware Granulator with Uniform Q Scaling -- 4.4 Class-Aware Granulator with Frequency-Based Q Scaling -- 5 Test and Results -- 6 Conclusions -- References -- Near Optimal Solving of the (N2-1)-puzzle Using Heuristics Based on Artificial Neural Networks -- 1 Introduction -- 1.1 Contributions -- 2 Background -- 2.1 The (N2-1)-puzzle -- 2.2 Artificial Neural Networks -- 3 Related Work -- 4 Designing a New Heuristic -- 4.1 Encoding the Input and Output -- 4.2 Design of the Neural Networks -- 4.3 Training Data and Training -- 4.4 Resulting ANN-distance Heuristics -- 5 Experimental Evaluation -- 5.1 Evaluation on Single Estimations -- 5.2 Evaluation on A* Searches -- 5.3 Competitive Comparison Against Heuristics Presented in Other Studies -- 5.4 Analysis of the Behavior of A* Search with the Underlying ANN-distance Heuristic -- 6 Discussion and Conclusion -- References -- Deep Convolutional Neural Network Processing of Images for Obstacle Avoidance -- 1 Introduction -- 2 Deep Learning for Image Processing -- 2.1 Components of a Deep Learning System -- 2.2 Relevant Previous Works -- 3 Obstacle Avoidance Task -- 3.1 The Robot -- 3.2 The Environment -- 3.3 Relevant Previous Works. ; 4 Deep Learning Applied to Obstacle Avoidance -- 4.1 Data Collection -- 4.2 Deep Learning Application -- 5 Results -- 5.1 Robot Performance in the Environment -- 5.2 Examining Network Weights and Activations -- 6 Conclusions -- References -- CVaR Q-Learning -- 1 Introduction -- 2 Preliminaries -- 2.1 Conditional Value-at-Risk -- 2.2 Q-Learning -- 2.3 Distributional Transition Operator -- 2.4 Problem Formulation -- 3 CVaR Value Iteration -- 3.1 Bellman Equation for CVaR -- 3.2 CVaR Value Iteration with Linear Interpolation -- 3.3 Accelerated Value Iteration for CVaR -- 3.4 Computing ξ -- 3.5 Experiments -- 4 CVaR Q-Learning -- 4.1 Estimating CVaR -- 4.2 Temporal Difference Updates -- 4.3 CVaR and Policy Improvement -- 4.4 CVaR Q-Learning with VaR-Based Policy Improvement -- 4.5 Experiments -- 5 Deep CVaR Q-Learning -- 5.1 Loss Functions -- 5.2 Experiments -- 6 Conclusion -- A Proofs of Theoretical Results -- A.1 Proof of Theorem 1 -- A.2 Proof of Theorem 2 -- B Other Results -- B.1 CVaR Value Iteration -Linear Program -- References -- Rule Extraction from Neural Networks and Other Classifiers Applied to XSS Detection -- 1 Introduction -- 2 Background and Related Work -- 2.1 Overview of Minimising Boolean Expressions -- 2.2 Cross-Site Scripting -- 3 Methodology -- 3.1 Datasets -- 3.2 Selected Features -- 3.3 Training Classifiers -- 3.4 Classifiers and Boolean Functions -- 3.5 Sampling -- 3.6 Extracting Rules -- 4 Results -- 4.1 Neural Networks -- 4.2 Support Vector Machines -- 4.3 k-NN -- 4.4 Timings -- 4.5 Labelling via Sampling -- 5 Discussion -- 6 Conclusion -- References -- Introduction to Sequential Heteroscedastic Probabilistic Neural Networks -- 1 Introduction -- 2 A Review of RHPNN -- 3 Derivation of SHPNN Formulation -- 4 The SHPNN Algorithm -- 5 Results -- 6 Conclusion -- References -- Author Index.
• Titolo autorizzato: Computational Intelligence
• ISBN: 3-030-70594-3
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910488702003321
• Lo trovi qui: Univ. Federico II
• Serie: Studies in Computational Intelligence