Hybrid Artificial Intelligent Systems : 12th International Conference, HAIS 2017, La Rioja, Spain, June 21-23, 2017, Proceedings / / edited by Francisco Javier Martínez de Pisón, Rubén Urraca, Héctor Quintián, Emilio Corchado

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2017
• Edizione: 1st ed. 2017.
• Descrizione fisica: 1 online resource (XVIII, 725 p. 248 illus.)
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence; Algorithms; Programming languages (Electronic computers); Computer programming; Application software; Artificial Intelligence; Algorithm Analysis and Problem Complexity; Programming Languages, Compilers, Interpreters; Programming Techniques; Information Systems Applications (incl. Internet)
• Persona (resp. second.): Martínez de PisónFrancisco Javier; UrracaRubén; QuintiánHéctor; CorchadoEmilio
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- Data Mining, Knowledge Discovery and Big Data -- Word Embedding Based Event Detection on Social Media -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Data Collection -- 3.2 Data Preprocessing -- 3.3 Word Embedding -- 3.4 Clustering Algorithm -- 4 Experiments and Results -- 5 Conclusion -- References -- Sentiment Analysis on TripAdvisor: Are There Inconsistencies in User Reviews? -- 1 Introduction -- 2 Sentiment Analysis -- 2.1 The Sentiment Analysis Problem -- 2.2 Sentiment Analysis Methods (SAMs) -- 3 Methodology -- 3.1 TripAdvisor -- 3.2 Web Scraping -- 3.3 Experimental Setup -- 4 Experiment Results -- 4.1 The Data Sets -- 4.2 Analysis of Results -- 5 Conclusions and Future Work -- References -- Sentiment Classification from Multi-class Imbalanced Twitter Data Using Binarization -- 1 Introduction -- 2 Proposed Classification System -- 2.1 General Overview -- 2.2 Feature Space Reduction with Multiple Correspondence Analysis -- 2.3 Balancing the Skewed Distributions -- 2.4 Weighted Classifier Combination -- 3 Feature Extraction -- 4 Experimental Study -- 4.1 Dataset -- 4.2 Set-Up -- 4.3 Results and Discussion -- 5 Conclusions and Future Works -- References -- An Ontology for Generalized Disease Incidence Detection on Twitter -- Abstract -- 1 Introduction -- 1.1 Related Work -- 2 Materials and Methods -- 2.1 An Ontology for Disease Incidence Detection on Twitter -- 2.2 Feature Extraction -- 3 The Twitter Disease Incidence Detection Pipeline -- 3.1 Corpus Generation -- 3.2 Model Training -- 3.3 Doc2Vec Tuning -- 4 Evaluation -- 4.1 Results and Discussion -- 5 Conclusion and Future Work -- References -- Hybrid Methodology Based on Bayesian Optimization and GA-PARSIMONY for Searching Parsimony Models by Combining Hyperparameter Optimization and Feature Selection -- 1 Introduction. ; 2 Materials and Methods -- 2.1 Extreme Gradient Boosting Machines -- 2.2 Bayesian Optimization -- 2.3 GA-PARSIMONY Methodology -- 2.4 Hybrid Method Based on Bayesian Optimization and GA-PARSIMONY -- 3 Experiments -- 3.1 Datasets and Validation Process -- 3.2 GA-PARSIMONY Settings -- 3.3 Bayesian Optimization Settings -- 3.4 Hybrid Method Settings -- 4 Results and Discussion -- 5 Conclusions -- References -- Concept Discovery in Graph Databases -- 1 Introduction -- 2 Background -- 2.1 Concept Discovery -- 2.2 Graph Databases -- 3 The Proposed Method -- 4 Experiments -- 4.1 Datasets and Experimental Setting -- 4.2 Experimental Results -- 5 Conclusion -- References -- Leveraging Distributed Representations of Elements in Triples for Predicate Linking -- 1 Introduction -- 2 Problem Definition -- 3 Related Work -- 4 Approach -- 4.1 Statistical Pattern-Based Candidate Generation -- 4.2 Similarity-Based Candidate Generation -- 4.3 Candidate Selection -- 5 Experiment -- 5.1 Dataset -- 5.2 Setting -- 5.3 Result -- 6 Conclusion -- References -- A Review of Distributed Data Models for Learning -- Abstract -- 1 Introduction -- 2 Taxonomies of Data Distribution Models -- 2.1 The Impact of Data Partitioning -- 2.2 Taxonomy Based on Data Partition -- 2.3 Taxonomy Based on Data Flow Processing -- 2.4 Taxonomy Based on the Data Cooperation Strategies -- 3 MapReduce: A Data Distribution Oriented Paradigm -- 4 New Trends in Distributed Data -- 4.1 Making the Most of In-memory Capability -- 4.2 Allowing Interprocess Communication -- 4.3 Dealing with the Drawback of Data Partitioning -- 4.4 Dealing with Data Pre-processing -- 5 Conclusions -- Acknowledgements -- References -- Bio-inspired Models and Evolutionary Computation -- Incorporating More Scaled Differences to Differential Evolution -- 1 Introduction -- 2 Methodology -- 2.1 Differential Evolution and Its Variants. ; 2.2 Matrix Notation for DE -- 2.3 New Variants for Differential Evolution -- 2.4 Benchmark Functions -- 3 Results and Discussion -- 4 Conclusions -- References -- Topological Evolution of Financial Network: A Genetic Algorithmic Approach -- 1 Introduction -- 2 Discrete Time Warping Genetic Algorithm (dTWGA) -- 2.1 Solution Representation -- 2.2 Mutation -- 2.3 Fitness -- 2.4 Selection -- 2.5 Iteration -- 3 Financial Network Construction -- 3.1 Minimum Spanning Tree -- 3.2 Maximum Degree Ratio -- 3.3 Spectrum -- 4 Experiment -- 5 Results and Discussion -- 6 Conclusion -- References -- Optimization of Joint Sales Potential Using Genetic Algorithm -- Abstract -- 1 Introduction -- 2 Algorithm Design -- 2.1 Initialization -- 2.2 Evaluation -- 2.3 Reproduction -- 2.4 Evolution -- 3 Testing -- 3.1 Sources of Sample Networks -- 3.2 Effects of Exploration: Guided Versus Random -- 3.3 Joint Sales Potential Optimization -- 4 Results -- 5 Discussion -- 5.1 Sparsely-Connected Networks -- 5.2 Guided or Random Exploration? -- 5.3 Number of Generations -- 5.4 Directed Networks -- 6 Conclusion -- Acknowledgement -- References -- Evolutionary Multi-objective Scheduling for Anti-Spam Filtering Throughput Optimization -- Abstract -- 1 Introduction -- 2 State of the Art -- 2.1 Throughput Optimization -- 2.2 Filter Accuracy Optimization -- 3 Problem Formulation and Proposal -- 4 Experimental Study -- 5 Results Discussion -- 6 Conclusions and Future Work -- Acknowledgements -- References -- A Hybrid Diploid Genetic Based Algorithm for Solving the Generalized Traveling Salesman Problem -- 1 Introduction -- 2 Definition of the GTSP -- 3 The Hybrid Diploid Genetic Algorithm -- 3.1 The Upper-Level (Global) Subproblem -- 3.2 The Lower-Level (Local) Subproblem -- 3.3 The Diploid Genetic Algorithm -- 4 Computational Results -- 5 Conclusions -- References. ; A Novel Hybrid Nature-Inspired Scheme for Solving a Financial Optimization Problem -- Abstract -- 1 Introduction -- 2 Literature Review -- 3 Portfolio Optimization Problem -- 4 Combination of Two NII Algorithms for Portfolio Optimization -- 4.1 Differences Between Firefly and Gravitational Search Algorithm -- 5 Experimental Study -- 6 Financial Implications -- 7 Conclusions -- References -- Hypersphere Universe Boundary Method Comparison on HCLPSO and PSO -- Abstract -- 1 Introduction -- 2 Particle Swarm Optimization -- 3 Heterogeneous Comprehensive Learning Particle Swarm Optimization -- 4 Hypersphere Universe Boundary Method -- 5 Experimental Setup -- 6 Results -- 7 Results Discussion -- 8 Conclusion -- Acknowledgements -- References -- PSO with Partial Population Restart Based on Complex Network Analysis -- Abstract -- 1 Introduction -- 2 Particle Swarm Optimization (PSO) -- 3 Proposed Method -- 4 Experiment Setup -- 5 Conclusion -- Acknowledgements -- References -- Learning Algorithms -- Kernel Density-Based Pattern Classification in Blind Fasteners Installation -- 1 Introduction -- 2 Blind Fasteners Installation -- 3 Kernel Density-Based Pattern Classification Approach -- 3.1 Kernel Density Estimation for Behavioral Patterns Identification -- 3.2 Behavioral Patterns Computation -- 3.3 Distance-Based Classification -- 4 Test Scenario -- 4.1 Description of the Experimental Setup -- 4.2 Results and Discussion -- 5 Conclusions and Future Work -- References -- Training Set Fuzzification Towards Prediction Improvement -- Abstract -- 1 Introduction -- 1.1 Theoretical Background - Continuous Distributions -- 1.2 Fuzzification of Variables Using a Histogram -- 2 Sales Prediction Using Neural Networks -- 2.1 Training Set -- 2.2 Setting the Parameters of the Neural Network for Experimental Part -- 2.3 Experimental Results of a Sale Prediction. ; 3 Conclusion -- Acknowledgments -- References -- On the Impact of Imbalanced Data in Convolutional Neural Networks Performance -- 1 Introduction -- 2 The Imbalance Problem in Classification -- 3 Deep Learning -- 3.1 Convolutional Neural Network -- 4 Impact of Imbalanced Data on Convolutional Neural Networks -- 5 Experimentation -- 5.1 Experimental Framework -- 5.2 CNN Architecture -- 5.3 Results Analysis -- 6 Conclusions -- References -- Effectiveness of Basic and Advanced Sampling Strategies on the Classification of Imbalanced Data. A ... -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Basic and Advanced Resampling Strategies -- 3.1 Basic Resampling Strategies -- 3.2 Advanced Resampling Strategies -- 4 Performance Measures -- 5 Experimental Study -- 6 Experimental Results -- 6.1 Datasets -- 6.2 Applying Resampling Strategies and Machine Learning Algorithms -- 6.3 Statistical Comparison of Classifiers Over Multiple Datasets -- 6.4 Statistical Comparison of Resampling Methods Over Multiple Datasets -- 7 Conclusions -- References -- A Perceptron Classifier, Its Correctness Proof and a Probabilistic Interpretation -- 1 Introduction -- 2 The Perceptron -- 3 Kernel Learning -- 3.1 Positive Definite Kernels -- 3.2 The Optimal Separating Hyperplane -- 3.3 The Representer Theorem, See [18] -- 4 Correctness Proof of the Modified Pocket Algorithm -- 5 Probabilistic Interpretation of the Decision Procedure -- 6 Conclusion and Outlook -- References -- Parallel Implementation of a Simplified Semi-physical Wildland Fire Spread Model Using OpenMP -- 1 Introduction -- 2 The Model -- 3 Parallel Model Implementation -- 4 Experiments and Results -- 4.1 Real Case Study -- 4.2 Performance Analysis/Evaluation -- 5 Conclusions and Further Research -- References -- A Study on the Noise Label Influence in Boosting Algorithms: AdaBoost, GBM and XGBoost -- 1 Introduction. ; 2 Class Noise. Preprocessing vs. Robust Methods.
• Sommario/riassunto: This volume constitutes the refereed proceedings of the 12th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2017, held in La Rioja, Spain, in June 2017. The 60 full papers published in this volume were carefully reviewed and selected from 130 submissions. They are organized in the following topical sections: data mining, knowledge discovery and big data; bioinspired models and evolutionary computing; learning algorithms; visual analysis and advanced data processing techniques; data mining applications; and hybrid intelligent applications.
• Titolo autorizzato: Hybrid artificial intelligent systems
• ISBN: 3-319-59650-0
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910484314803321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Artificial Intelligence ; ; 10334