Advances in computational intelligence : 15th Mexican international conference on artificial intelligence, MICAI 2016, Cancún, Mexico, October 23-28, 2016, proceedings, part I / / edited by Ildar Batyrshin, Alexander Gelbukh, and Grigori Sidorov

• Pubblicazione: Cham, Switzerland : , : Springer, , [2021]; ©2021
• Descrizione fisica: 1 online resource (433 pages)
• Disciplina: 006.3
• Soggetto topico: Computers; Artificial intelligence; Optical data processing
• Persona (resp. second.): GelbukhAlexander <1962->; SidorovGrigori; BatyrshinIldar
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Conference Organization -- Contents - Part I -- Contents - Part II -- Machine and Deep Learning -- Identifying Optimal Clusters in Purchase Transaction Data -- 1 Introduction -- 2 Clustering Taxonomies -- 3 Cluster Validity Indices -- 4 Data Complexity Measures -- 5 Data Sets and Experimental Methodology -- 6 Results and Discussions -- 7 Conclusions -- A Appendix -- References -- Artificial Organic Networks Approach Applied to the Index Tracking Problem -- 1 Introduction -- 1.1 Objectives and Limitations -- 2 The Proposed Approach -- 2.1 AON Properties -- 2.2 Artificial Hydrocarbon Networks Algorithm -- 3 Implementation Considerations -- 3.1 System Identification -- 3.2 Target Function Mathematical Formulation -- 3.3 Financial Analysis and Strategy -- 4 Preliminary Results -- 4.1 Experiment 1: Establishing a Regression -- 4.2 Experiment 2: Comparing MNLR Performance Vs. Other ML Techniques. -- 4.3 Experiment Three: Buy-and-Hold Strategy -- 4.4 Experiment 4: A Hybrid K-Means with AHN Algorithm -- 5 Conclusions and Future Work -- References -- Supervised Learning Approach for Section Title Detection in PDF Scientific Articles -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Dataset Creation -- 3.2 Classifiers Training and Testing -- 4 Results -- 5 Conclusion -- References -- Real-Time Mexican Sign Language Interpretation Using CNN and HMM -- 1 Introduction -- 2 Related Work -- 2.1 Methods -- 2.2 Techniques -- 2.3 Works About MSL in Mexico -- 3 Proposal -- 4 Dataset -- 4.1 Description -- 4.2 Participants -- 4.3 Data Acquisition -- 4.4 Dataset Standardization -- 5 Experiments and Results -- 5.1 Training -- 5.2 Results Experiment 1: Focus on Isolated Words -- 5.3 Results Experiment 2: Focus on Sentences -- 6 Conclusions -- References -- RiskIPN: Pavement Risk Database for Segmentation with Deep Learning. ; 1 Introduction -- 2 Databases -- 2.1 Previous Datasets -- 2.2 RisksIPN -- 3 Segmentation Deep Model -- 4 Experiments and Results -- 4.1 Preprocessing -- 4.2 Training -- 5 Conclusion -- References -- A Comparative Study on Approaches to Acoustic Scene Classification Using CNNs -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Data Organization and Collection -- 3.2 Data Augmentation -- 3.3 Feature Representations -- 3.4 Development of CNNs -- 4 Results and Evaluation -- 5 Conclusion -- References -- Measuring the Effect of Categorical Encoders in Machine Learning Tasks Using Synthetic Data -- 1 Introduction -- 2 General Methodology -- 2.1 Real-World Datasets -- 2.2 Synthetic Datasets -- 3 Experimental Results -- 3.1 Real-World Dataset -- 3.2 Synthetic-Datasets -- 4 Conclusions -- Appendix -- References -- Long-Term Exploration in Persistent MDPs -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 Markov Decision Processes -- 3.2 Persistent MDPs -- 4 Exploration via State Space Clustering -- 4.1 Similarity Model -- 4.2 Graph of Clusters -- 5 The Prince of Persia Domain -- 6 Experiments -- 6.1 Experimental Setup -- 6.2 Exploring the Prince of Persia Environment -- 6.3 Ablation Study -- 7 Conclusion -- References -- Source Task Selection in Time Series via Performance Prediction -- 1 Introduction -- 2 Transfer Learning -- 3 Related Work -- 4 Performance Prediction for Source Task Selection -- 4.1 Feature Extraction -- 4.2 Regression Model -- 5 Experimental Results -- 6 Conclusions and Future Work -- References -- Finding Significant Features for Few-Shot Learning Using Dimensionality Reduction -- 1 Introduction -- 2 Materials and Methods -- 2.1 Meta-learning Tasks -- 2.2 MiniImageNet Dataset -- 3 Proposed Model -- 3.1 Feature Reduction Techniques -- 3.2 Inter and Intra Class Nearest Neighbors Score (ICNN Score) -- 4 Experiments. ; 4.1 Implementation Details -- 4.2 Model Design Choices -- 4.3 Comparison with Baselines -- 5 Conclusion -- References -- Seasonality Atlas of Solar Radiation in Mexico -- 1 Introduction -- 1.1 Related Work -- 2 Mexico's Solar Radiation -- 3 Methodology -- 3.1 Designing the Atlas -- 3.2 Cluster Analysis -- 3.3 Algorithms -- 3.4 Validation of the Results -- 4 Results -- 4.1 1-Dimensional Cluster Analysis -- 4.2 2-Dimensional Cluster Analysis -- 5 Discussion -- 6 Conclusions -- References -- Best Paper Award, Third Place -- Comparing Machine Learning Based Segmentation Models on Jet Fire Radiation Zones -- 1 Introduction -- 2 State of the Art -- 2.1 Deep Learning Architectures -- 2.2 Traditional Computer Vision Methods -- 3 Proposed Approach -- 4 Data Set -- 4.1 Image Processing -- 5 Metrics and Loss Functions -- 5.1 Metrics -- 5.2 Loss Functions -- 6 Training -- 7 Testing -- 8 Results and Discussion -- 8.1 Selected Metrics -- 8.2 Best Loss Function -- 8.3 Traditional and Deep Learning Segmentation -- 8.4 Discussion -- 9 Conclusions -- References -- A Machine Learning Approach for Modeling Safety Stock Optimization Equation in the Cosmetics and Beauty Industry -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 4 Machine Learning Workflow -- 5 Results and Discussion -- 6 Conclusions -- References -- DBSCAN Parameter Selection Based on K-NN -- 1 Introduction -- 2 Related Work -- 3 DBSCAN Parameter Selection Based on K-Distance -- 4 Experiments -- 4.1 Parameter Selection DBSCAN -- 4.2 ACND -- 4.3 Clustering -- 4.4 Border Definition -- 5 Conclusion -- References -- Deep Learning Architectures Applied to Mosquito Count Regressions in US Datasets -- 1 Introduction -- 2 Methods -- 2.1 Multi-Layer Perceptron (MLP) -- 2.2 Approach 2 (MLP + Weather Data) -- 2.3 Approach 3: CNN -- 2.4 Approach 4: Hybrid Model (CNN + MLP) -- 2.5 Approach 5: Sentinel CNN + MLP. ; 2.6 Approach 6: VAE + MLP -- 2.7 Approach 7: Recurrent Neural Network (LSTM) -- 3 Analysis and Conclusions -- References -- Causal Based Action Selection Policy for Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Assumptions and Limitations -- 3.2 Action Selection -- 4 Experimental Set Up -- 4.1 Environment -- 4.2 Implementation and Compared Approaches -- 4.3 Evaluation Metric and Exploration Rate Decay -- 5 Results -- 5.1 Modifying the Causal Graph -- 5.2 Exploit or Keep Exploring -- 5.3 Using Visual Observations of the Environment -- 6 Conclusions -- References -- Performance Evaluation of Artificial Neural Networks Applied in the Classification of Emotions -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 3.1 Data Acquisition -- 3.2 Preprocessing -- 3.3 Artificial Neural Networks -- 3.4 Experimental Settings -- 4 Results and Discussion -- 5 Conclusion and Future Directions -- References -- Machine Learning Algorithms Based on the Classification of Motor Imagination Signals Acquired with an Electroencephalogram -- 1 Introduction -- 2 Background -- 2.1 CNN -- 2.2 LSTM -- 2.3 GRU -- 2.4 Bidirectional RNN -- 2.5 DT -- 2.6 Random Forest -- 2.7 MLP -- 2.8 Gaussian Naïve Bayes -- 2.9 SVM -- 2.10 LDA and Logistic Regression -- 2.11 AdaBoost -- 2.12 KNN -- 3 Methodology -- 4 Results -- 5 Conclusions -- References -- Image Processing and Pattern Recognition -- Touchless Fingerphoto Extraction Based on Deep Learning and Image Processing Algorithms -- A Preview -- 1 Introduction -- 2 Related Work -- 2.1 Image Acquisition -- 2.2 Background Removal -- 2.3 Fingerprint Enhancement -- 3 Methods and Materials -- 3.1 Fingerphoto Acquisition -- 3.2 Background Removal -- 3.3 Fingerphoto Segmentation and Enhancement -- 3.4 Equivalent Touch-Based Image -- 3.5 NIST Fingerprint Image Quality. ; 4 Experiments and Results -- 4.1 Fingerphoto Dataset -- 4.2 U-Net for Background Removal -- 4.3 Fingerphoto Extraction -- 5 Conclusions and Feature Work -- References -- Real Time Distraction Detection by Facial Attributes Recognition -- 1 Introduction -- 1.1 Previous Work -- 2 Method and Data -- 2.1 Image Acquisition -- 2.2 Face Detection -- 2.3 Facial Attributes Recognition -- 2.4 Classification -- 3 Results -- 3.1 Classic Evaluation -- 3.2 5-Fold Cross Validation Evaluation -- 3.3 Real Time Environment Evaluation -- 4 Discussion -- 4.1 Future Work -- 5 Conclusions -- References -- Urban Perception: Can We Understand Why a Street Is Safe? -- 1 Introduction -- 2 Related Works -- 2.1 Urban Perception -- 2.2 Model Interpretation -- 3 Methodology -- 3.1 Datasets and Data Pre-processing -- 3.2 Visual Components Extraction -- 4 Experiments and Discussions -- 5 Conclusions -- References -- Continual Learning for Multi-camera Relocalisation -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dataset Generation -- 3.2 Continual Learning -- 4 Experiments and Results -- 5 Conclusion -- References -- Facing a Pandemic: A COVID-19 Time Series Analysis of Vaccine Impact -- 1 Introduction -- 2 Related Work -- 2.1 COVID-19 World Vaccination Progress with Tableau -- 2.2 COVID-19: Can We Predict the Future? -- 2.3 COVID-19 EDA: Man Vs. Disease -- 2.4 Remarks -- 3 Methodology -- 3.1 Data Understanding -- 3.2 Data Preparation -- 3.3 Modeling -- 4 Results -- 4.1 Model Evaluation -- 4.2 Deployment -- 5 Conclusion -- References -- COVID-19 on the Time, Countries Deaths Monitoring and Comparison Dealing with the Pandemic -- 1 Introduction -- 2 Focus on Deaths Instead of Reported Infections -- 3 Methods -- 3.1 Moving Average -- 3.2 Plateau -- 3.3 Maximum Value -- 3.4 Economics Information Per Country -- 4 Results -- 5 Conclusions and Future Work -- 6 Related Work. ; References.
• Titolo autorizzato: Advances in Computational Intelligence
• ISBN: 3-030-89817-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910506398403321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Computer Science