Advances in computational intelligence : 21st Mexican International Conference on Artificial Intelligence, MICAI 2022, Monterrey, Mexico, October 24-29, 2022, proceedings. Part I / / edited by Obdulia Pichardo Lagunas, Juan Martínez-Miranda, and Bella Martínez Seis

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (465 pages)
• Disciplina: 006.3
• Soggetto topico: Computational intelligence
• Persona (resp. second.): Pichardo LagunasObdulia; Martínez-MirandaJuan; Martínez SeisBella
• Note generali: Includes index.
• Nota di contenuto: Intro -- Preface -- Conference Organization -- Contents - Part I -- Contents - Part II -- Machine and Deep Learning -- Skipped Nonsynaptic Backpropagation for Interval-valued Long-term Cognitive Networks -- 1 Introduction -- 2 Interval-valued Long-term Cognitive Networks -- 3 Skipped Nonsynaptic Backpropagation -- 3.1 Interval-value Random NSBP Algorithm, IVR-NSBP -- 3.2 Interval-value Skipped NSBP Algorithm, IVS-NSBP -- 3.3 Interval-value Random-Skipped NSBP Algorithm, IVRS-NSBP -- 4 Numerical Simulations -- 4.1 Effect of Uncertainty Level on the Internal Size -- 4.2 Assessing the Prediction Accuracy -- 5 Conclusions -- References -- Cross-target Stance Classification as Domain Adaptation -- 1 Introduction -- 2 Background -- 2.1 Cross-target Stance Classification -- 2.2 Domain Adaptation Using BERT -- 3 Materials and Method -- 3.1 Corpus -- 3.2 Classifier Models -- 4 Results -- 5 Final Remarks -- References -- Impact of Loss Function in Deep Learning Methods for Accurate Retinal Vessel Segmentation -- 1 Introduction -- 2 State of the Art -- 2.1 Rule-Based Methods -- 2.2 Machine Learning Methods -- 2.3 Deep Learning Methods -- 3 Data and Methods -- 3.1 Dataset -- 3.2 Segmentation Metrics -- 3.3 Loss Functions -- 3.4 Deep Learning Architectures -- 3.5 Training -- 4 Results -- 5 Discussion -- 6 Conclusion and Future Work -- References -- Embedded Implementation of the Hypersphere Neural Network for Energy Consumption Monitoring -- 1 Introduction -- 2 Geometric Algebra -- 2.1 Conformal Geometric Algebra -- 3 Hypersphere Neural Network Topology -- 4 IoT Architecture for Energy Consumption Monitoring -- 5 Experiments and Results -- 5.1 NodeMCU Performance -- 6 Conclusions -- References -- MACFE: A Meta-learning and Causality Based Feature Engineering Framework -- 1 Introduction -- 2 Related Work -- 2.1 Meta-learning for Feature Engineering. ; 2.2 Causality Feature Selection -- 3 Problem Definition -- 3.1 Meta-learning and Meta-features -- 4 Proposed Approach -- 4.1 Datasets -- 4.2 Model Training -- 5 Experimental Results -- 5.1 Evaluation Details -- 5.2 Implementation Details -- 5.3 Comparison with Previous Works -- 5.4 Discussion -- 6 Conclusions and Future Work -- References -- Time Series Forecasting with Quantum Machine Learning Architectures -- 1 Introduction -- 2 Preliminaries -- 2.1 The Qubit -- 2.2 Quantum Circuits -- 2.3 Variational Quantum Circuits -- 3 Problem Statement -- 4 Quantum Machine Learning Architectures for Time Series Forecasting -- 4.1 Quantum Neural Network -- 4.2 Hybrid Quantum Neural Network -- 5 Results and Discussion -- 6 Conclusions -- References -- Explainable Model of Credit Risk Assessment Based on Convolutional Neural Networks -- 1 Introduction -- 2 Motivation -- 3 Related Work -- 4 Proposed Approach -- 4.1 Data Preparation -- 4.2 Modeling -- 4.3 Interpretability -- 5 Experimental Results -- 6 Conclusions -- References -- Reinforcement Learning with Success Induced Task Prioritization -- 1 Introduction -- 2 Related Work -- 3 Background -- 4 Success Induced Task Prioritization -- 5 Experiments -- 5.1 Motivational Experiment in POGEMA Environment -- 5.2 Large-Scale Experiment in POGEMA Environment -- 5.3 Procgen Benchmark -- 6 Conclusion -- References -- Cooperative Chaotic Exploration with UAVs Combining Pheromone Dispersion and Hopfield Chaotic Neural Network -- 1 Introduction -- 2 Related Work -- 3 UAV Mobility Models -- 4 Metrics -- 5 Results -- 6 Conclusions -- References -- Machine Learning-Based Decision Making in Evolutionary Multiobjective Clustering -- 1 Introduction -- 2 Related Work -- 3 Machine Learning-Based Decision Making -- 3.1 Description of the Proposed Decision-Making Strategy -- 3.2 Definition of Main Design Components. ; 3.3 Characterization of Pareto Front Approximations -- 4 Experiments and Results -- 4.1 Evaluation Setup -- 4.2 Scenario 1: Unknown PFAs for Known Problems -- 4.3 Scenario 2: PFAs for Completely Unknown Problems -- 5 Concluding Remarks -- References -- RBF Neural Network Based on FT-Windows for Auto-Tunning PID Controller -- 1 Introduction -- 2 Flat-Top Windows for Learning -- 3 Applied FTW for Control Quanser Helicopter -- 4 Numerical Simulation Results -- 4.1 Classical PID -- 4.2 FTW-IIR PID -- 5 Conclusions -- References -- Pursuing the Deep-Learning-Based Classification of Exposed and Imagined Colors from EEG -- 1 Introduction -- 2 Related Works -- 3 Dataset -- 3.1 Preprocessing -- 4 EEGNet -- 5 Experiments and Results -- 5.1 Classification of Exposed Colors -- 5.2 Classification of Imagined Colors -- 5.3 Simultaneous Classification of Imagined and Exposed Colors -- 6 Conclusions and Future Work -- References -- Data Stream Mining for Dynamic Student Modeling -- 1 Introduction -- 2 Related Work -- 3 Proposed Methodology -- 3.1 Overview -- 4 Experiments and Results -- 4.1 Data and Preprocessing -- 4.2 Classification and Evaluation -- 4.3 Student Class Characterization -- 5 Discussion -- 6 Conclusions and Future Work -- References -- CESAMMO: Categorical Encoding by Statistical Applied Multivariable Modeling -- 1 Introduction -- 2 General Methodology -- 3 Experimental Results -- 4 Conclusions -- References -- Heart Failure Disease Prediction Using Machine Learning Models -- 1 Introduction -- 2 Related Work -- 3 Description of the Proposal -- 3.1 Data -- 3.2 Exploratory Data Analysis (EDA) -- 3.3 Machine Learning Workflow -- 4 Experimentation -- 5 Results and Discussion -- 5.1 Application -- 5.2 Discussion -- 6 Conclusions -- References -- Classification of Flood Warnings Applying a Convolutional Neural Network -- 1 Introduction -- 2 Related Work. ; 3 Methodology -- 3.1 Weather Stations -- 3.2 Dataset -- 3.3 CNN Architecture -- 4 Experiments and Results -- 4.1 Validation -- 4.2 Discussion -- 5 Conclusions and Future Work -- References -- Machine Learning Techniques in Credit Default Prediction -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Data Preparation -- 3.2 Building Models -- 3.3 Model Evaluation -- 4 Results and Discussion -- 5 Conclusions -- References -- Convolutional and Dense ANN for Cloud Kinetics Forecasting Using Satellite Images -- 1 Introduction -- 2 Methodology -- 2.1 Processing of Satellite Images for Cloud Kinetics -- 2.2 Neural Networks for Forecasting -- 2.3 Forecasting Errors and Indexes -- 3 Results -- 3.1 Forecasting Cloud Kinetics -- 3.2 Performance Evaluation of Forecasting -- 4 Discussion and Conclusion -- References -- The Role of the Number of Examples in Convolutional Neural Networks with Hebbian Learning -- 1 Introduction -- 2 Related Work -- 2.1 Spiking Neural Networks with Hebbian Learning and Similar Approaches -- 2.2 Conventional Networks with Hybrid Learning -- 2.3 Conventional Networks with Pure Hebbian Learning -- 2.4 Difference of This Proposal with Previous Works -- 3 Methodology -- 3.1 BCM Learning Rule -- 3.2 Empirical Design -- 3.3 Evaluation -- 4 Results -- 4.1 Comparison with Gradient-Based Optimizers -- 5 Conclusions -- 5.1 Further Research -- References -- Image Processing and Pattern Recognition -- Vision-Based Gesture Recognition for Smart Light Switching -- 1 Introduction -- 2 Background -- 3 Applied Methodology for Gesture Recognition and Lamp on/off Control -- 3.1 Actuator -- 3.2 The Sensor and Image Processing -- 3.3 Controller: Convolutional Neural Network -- 4 Results -- 5 Conclusions -- References. ; On the Generalization Capabilities of FSL Methods Through Domain Adaptation: A Case Study in Endoscopic Kidney Stone Image Classification -- 1 Introduction -- 2 Medical Context and Motivation -- 3 Related Work -- 3.1 Few-Shot Learning -- 3.2 Cross-Domain FSL -- 3.3 Kidney Stones Classification -- 4 Proposed Approach -- 4.1 Datasets -- 4.2 Model Training and Design Choices -- 5 Experimental Results -- 5.1 Implementation Details -- 5.2 Training Details -- 5.3 Evaluation Results -- 5.4 Discussion -- 6 Conclusions -- References -- Best Paper Award -- A Novel Hybrid Endoscopic Dataset for Evaluating Machine Learning-Based Photometric Image Enhancement Models -- 1 Introduction -- 1.1 Medical Context -- 1.2 Motivation for Our Proposal -- 1.3 Contributions and Organization of the Article -- 2 State of the Art -- 3 Data and Methodology -- 3.1 Data -- 3.2 Methodology -- 3.3 Training Setup -- 3.4 Metrics -- 4 Experiments and Results -- 4.1 Results -- 5 Conclusion and Future Work -- References -- Comparison of Automatic Prostate Zones Segmentation Models in MRI Images Using U-net-like Architectures -- 1 Introduction -- 2 Motivation and State of the Art -- 2.1 Motivation for Segmenting Prostate Zones -- 2.2 Related Work -- 3 Data and Methods -- 3.1 Dataset -- 3.2 Deep Learning Architectures -- 3.3 Segmentation Metrics -- 3.4 Loss Functions -- 3.5 Training -- 4 Results -- 4.1 Quantitative Results -- 4.2 Qualitative Results -- 5 Conclusion and Future Work -- References -- Towards an Interpretable Model for Automatic Classification of Endoscopy Images -- 1 Introduction -- 2 Related Work -- 2.1 Classification of Endoscopy Images -- 2.2 Interpretability -- 3 Methods and Implementation -- 3.1 Dataset -- 3.2 Optimized CNN -- 3.3 Grad-CAM -- 4 Results -- 4.1 Experimental Settings -- 4.2 Optimized CNN Classification Performance -- 4.3 Visual Explanations Using Grad-CAM. ; 5 Discussion and Conclusions.
• Titolo autorizzato: Advances in Computational Intelligence
• ISBN: 3-031-19493-4
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996495567703316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science