Intelligent systems : 10th Brazilian conference, BRACIS 2021, virtual event, November 29 - December 3, 2021, proceedings, Part I / / edited by André Britto and Karina Valdivia Delgado

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (564 pages)
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence; Data structures (Computer science); Software engineering
• Persona (resp. second.): BrittoAndré; DelgadoKarina Valdivia
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Agent and Multi-agent Systems, Planning and Reinforcement Learning -- A Conversational Agent to Support Hospital Bed Allocation -- 1 Introduction -- 2 Materials and Methods -- 2.1 Eliciting Bed Allocation Rules -- 2.2 Developing an Approach to Bed Allocation -- 3 Evaluation -- 3.1 First Phase -- 3.2 Second Phase -- 3.3 Third Phase -- 4 Improvements Based on the Evaluation -- 4.1 Bed Allocation Optimisation -- 4.2 Plan Validator -- 5 Related Work -- 6 Conclusions -- References -- A Protocol for Argumentation-Based Persuasive Negotiation Dialogues -- 1 Introduction -- 2 Background -- 3 Building Blocks -- 4 The Proposal -- 4.1 The Proposed Protocol -- 4.2 Argumentation Framework and Dialogue Outcome -- 4.3 Properties of the Proposal -- 5 Applying the Proposal to the Illustrative Example -- 6 Conclusions and Future Work -- References -- Gradient Estimation in Model-Based Reinforcement Learning: A Study on Linear Quadratic Environments -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 A Brief Introduction to RL -- 3.2 Linear Quadratic Gaussian Regulator -- 3.3 Stochastic Value Gradient Methods -- 4 Methodology -- 4.1 Scope of Evaluation -- 4.2 Randomized Environments and Policies -- 5 Empirical Analysis -- 5.1 Gradient Estimation for Fixed Policies -- 5.2 Impact of Gradient Quality on Policy Optimization -- 6 Conclusions and Future Work -- References -- Intelligent Agents for Observation and Containment of Malicious Targets Organizations -- 1 Introduction -- 2 A Literature Review -- 3 The Approach for Observing and Containment of Malicious Targets Organizations -- 3.1 Target Strategy -- 3.2 Robots Strategy -- 3.3 Materials and Methods -- 4 Experiments and Results -- 4.1 Test Settings. ; 4.2 Result of the Classification of Organizational Structures and the Random Model -- 4.3 Results of Achieving Goals for Each Team -- 5 Conclusion -- References -- MAS4GC: Multi-agent System for Glycemic Control of Intensive Care Unit Patients -- 1 Introduction -- 2 Literature Review -- 3 Materials and Methods -- 3.1 Problem Definition -- 3.2 Project Design -- 3.3 MAS4GC Implementation -- 4 Experiments and Results -- 4.1 Experiment 1 -- 4.2 Experiment 2 -- 5 Conclusion -- References -- On the Impact of MDP Design for Reinforcement Learning Agents in Resource Management -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 Batch Job Scheduling -- 3.2 Deep Reinforcement Learning and Job Scheduling -- 3.3 Policy Gradients -- 4 Methodology -- 4.1 The Base, Image-Like MDP -- 4.2 Compact State Representation -- 4.3 Sparse State Transitions -- 4.4 Reducing the Noise of the Reward Signal -- 5 Experiments -- 6 Conclusion -- References -- Slot Sharing Mechanism in Multi-domain Dialogue Systems -- 1 Introduction -- 2 Related Work -- 3 Proposal -- 3.1 Divide-and-Conquer Distributed Architecture -- 3.2 Slot Sharing Mechanism -- 4 Experiments and Results -- 4.1 Experimental Setup -- 4.2 Node Embedding -- 4.3 DCDA Evaluation -- 5 Conclusions -- References -- Evolutionary Computation, Metaheuristics, Constrains and Search, Combinatorial and Numerical Optimization -- A Graph-Based Crossover and Soft-Repair Operators for the Steiner Tree Problem -- 1 Introduction -- 2 Related Works -- 3 Proposed Operator -- 4 Experiments -- 4.1 Experimental Design -- 4.2 Experimental Results and Analysis -- 5 Conclusions -- References -- A Modified NSGA-DO for Solving Multiobjective Optimization Problems -- 1 Introduction -- 2 Multiobjective Optimization Problems -- 3 Multiobjective Genetic Optimization -- 3.1 NSGA-II -- 3.2 NSGA-DO -- 3.3 MNSGA-DO -- 4 Experimental Setup. ; 5 Experimental Results -- 6 Conclusion -- References -- An Enhanced TSP-Based Approach for Active Debris Removal Mission Planning -- 1 Introduction -- 2 Literature Review -- 3 Problem Formulation -- 3.1 Orbit Transfer -- 4 Proposed Approach -- 4.1 Inver-Over -- 4.2 Stochastic 2-Opt -- 4.3 Maximal Open Walk -- 5 Experimental Evaluation -- 5.1 Back-Propagated Instances -- 5.2 Actual Instances -- 6 Conclusions -- References -- Dynamic Learning in Hyper-Heuristics to Solve Flowshop Problems -- 1 Introduction -- 2 Background -- 2.1 Flowshop Problems (FSPs) -- 2.2 Hyper-Heuristics and Their Adaptation Strategies -- 3 Adaptive IG Proposal -- 4 Tuning and Testing Phases -- 5 Results -- 6 Conclusions -- References -- Hyper-Heuristic Based NSGA-III for the Many-Objective Quadratic Assignment Problem -- 1 Introduction -- 2 Background -- 2.1 Many-Objective Quadratic Assignment Problem - MaQAP -- 2.2 Hyper-Heuristics (HH) -- 2.3 NSGA-III -- 2.4 Related Works -- 3 Proposed Approach -- 4 Experiments and Discussion -- 4.1 Stage 1: Selecting the Success and Failure Counting Strategy -- 4.2 Stage 2: Selecting the Success and Failure Factor -- 4.3 Stage 3: Effect of Operator Selection by Hyper-Heuristic -- 4.4 Stage 4: Literature Comparison -- 5 Conclusions -- References -- I2DE: Improved Interval Differential Evolution for Numerical Constrained Global Optimization -- 1 Introduction -- 2 Background -- 2.1 Interval Analysis Applied to Global Optimization -- 2.2 Differential Evolution -- 3 Improved Interval Differential Evolution -- 3.1 Interval Population -- 3.2 Interval Operations -- 3.3 Fitness Evaluations -- 4 Experimental Results -- 5 Conclusion -- References -- Improving a Genetic Clustering Approach with a CVI-Based Objective Function -- 1 Introduction -- 2 Genetic Algorithm for Decision Boundary Analysis -- 3 A New Objective Function. ; 3.1 Basic Notations and Definitions -- 3.2 Cluster Validation -- 3.3 Mutual Equidistant-Scattering Criterion -- 4 Results and Analyses -- 4.1 Applied Methodology -- 4.2 Cluster Detection Results -- 4.3 Statistical Significance Analyses -- 5 Conclusions and Further Work -- References -- Improving Particle Swarm Optimization with Self-adaptive Parameters, Rotational Invariance, and Diversity Control -- 1 Introduction -- 2 Theoretical Background -- 3 Related Work -- 4 Improving RI-SAPSO and XPSO -- 4.1 Rotationally Invariant Attractive and Repulsive eXpanded PSO -- 4.2 Rotationally Invariant Semi-autonomous eXpanded PSO -- 5 Experimental Simulations -- 5.1 Swarm Diversity and Solution Convergence -- 5.2 Congress on Evolutionary Computation 2017 Benchmark Functions -- 5.3 Statistical Hypothesis Testing -- 6 Final Considerations -- References -- Improving Rule Based and Equivalent Decision Simplifications for Bloat Control in Genetic Programming Using a Dynamic Operator -- 1 Introduction -- 2 Background -- 2.1 Simplification with RBS and EDS -- 3 Proposed Improvements -- 4 Methodology -- 4.1 Rule Based Simplification -- 4.2 Equivalent Decision Simplification -- 5 Experimental Results -- 5.1 Simplification Methods Performance -- 5.2 Symbolic Regression Problems -- 6 Conclusion and Future Work -- References -- Lackadaisical Quantum Walk in the Hypercube to Search for Multiple Marked Vertices -- 1 Introduction -- 2 Quantum Walk -- 2.1 Quantum Walk on the Hypercube -- 3 Analyzing the Quantum Walk on the Hypercube -- 3.1 Characterizing the Probability Distribution Along the Space -- 3.2 Adjusting the Self-loop Weight for Multiple Marked Vertices -- 3.3 Searching for Adjacent Marked Vertices -- 4 Conclusions -- References -- On the Analysis of CGP Mutation Operators When Inferring Gene Regulatory Networks Using ScRNA-Seq Time Series Data -- 1 Introduction. ; 2 Problem Definition -- 3 Cartesian Genetic Programming -- 3.1 Mutation Operators -- 4 Proposal and Methods -- 5 Computational Experiments -- 5.1 Comparative Analysis of the CGP Techniques -- 5.2 Comparative Analysis with GENIE3 -- 6 Conclusions and Future Work -- References -- Online Selection of Heuristic Operators with Deep Q-Network: A Study on the HyFlex Framework -- 1 Introduction -- 2 Selection Hyper-Heuristic -- 2.1 Dynamic Multi-Armed Bandit -- 2.2 Fitness-Rate-Rank Multi-Armed Bandit -- 2.3 Deep Q-Network -- 3 Experiments -- 3.1 Bin Packing -- 3.2 Flow Shop -- 3.3 Personal Scheduling -- 3.4 MAX-SAT -- 3.5 Traveling Salesman Problem -- 3.6 Vehicle Routing Problem -- 4 Conclusion -- References -- Knowledge Representation, Logic and Fuzzy Systems -- A Systematic Approach to Define Semantics for Prioritised Logic Programs -- 1 Introduction -- 2 Preliminaries -- 3 Semantics for Prioritised Logic Programs -- 4 Expressing Priorities in PLPs -- 4.1 Priorities Between Conjunctive Knowledge -- 4.2 Priorities Between Disjunctive Knowledge -- 4.3 Conditional Priorities -- 4.4 Priorities Between Rules -- 4.5 Bipolar Preferences -- 5 Results -- 6 Related Work -- 7 Conclusion and Future Works -- References -- Active Learning and Case-Based Reasoning for the Deceptive Play in the Card Game of Truco -- 1 Introduction -- 2 Background to This Work -- 2.1 CBR, Active Learning and Games -- 2.2 The Card Game of Truco -- 3 Active Learning and CBR in the Card Game of Truco -- 3.1 The Case Base Formation -- 3.2 Game Actions and Deception -- 3.3 Hand Strength -- 3.4 Triggering the Expert Consultation -- 4 Experiments and Results -- 4.1 The Active Learning Experiment -- 4.2 The Evaluation Experiments -- 5 Final Remarks -- References -- ASPIC? and the Postulates of Non-interference and Crash-Resistance -- 1 Introduction -- 2 The ASPIC? Framework. ; 2.1 Attacks and Defeats.
• Titolo autorizzato: Intelligent Systems
• ISBN: 3-030-91702-9
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996464508703316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science