Foundations of intelligent systems : 26th international symposium, ISMIS 2022, Cosenza, Italy, October 3-5, 2022, proceedings / / edited by Michelangelo Ceci [and four others]

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (497 pages)
• Disciplina: 060
• Soggetto topico: Artificial intelligence
• Persona (resp. second.): CeciMichelangelo
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Invited Talks -- Adaptive Machine Learning for Data Streams -- Interactive Machine Learning -- Contents -- Social Media and Recommendation -- Granular Emotion Detection in Social Media Using Multi-Discipline Ensembles -- 1 Introduction -- 2 Related Work -- 2.1 Classifiers -- 2.2 Ensembles -- 3 Ensemble Approach and Evaluation -- 3.1 Experimental Setup -- 3.2 Analysis of Individual Component Approaches -- 3.3 Analysis of Ensemble Approaches -- 4 Results and Discussion -- 5 Conclusions and Future Work -- References -- Sentiment Polarity and Emotion Detection from Tweets Using Distant Supervision and Deep Learning Models -- 1 Introduction -- 2 Related Work -- 3 Design and Research Methodology -- 4 Experimental Settings -- 4.1 Dataset -- 4.2 Conventional Machine Learning Models -- 4.3 Deep Neural Networks -- 5 Results and Analysis -- 6 Conclusion and Future Work -- References -- Disruptive Event Identification in Online Social Network -- 1 Introduction -- 2 Disruptive Event Identification Framework -- 2.1 Data Acquisition and Preprocessing -- 2.2 Clustering and Event Identification -- 3 Result and Discussion -- 3.1 Dataset Used -- 3.2 Performance Metrics Used -- 4 Conclusion -- References -- Modeling Polarization on Social Media Posts: A Heuristic Approach Using Media Bias -- 1 Introduction -- 2 Related Work -- 3 Datasets -- 3.1 News Domains Data -- 3.2 Social Media Posts -- 4 Methodology -- 4.1 Type-1: News Domain Labeling -- 4.2 Type-2: Sentiment Labeling -- 5 Results -- 5.1 Political Leaning Labeling -- 5.2 Methods for Learning Text Representations -- 5.3 Political Leaning Prediction -- 6 Conclusion and Future Work -- References -- Sarcasm Detection in Tunisian Social Media Comments: Case of COVID-19 -- 1 Introduction -- 2 Background -- 2.1 Related Work -- 2.2 Tunisian Dialect -- 3 Dataset. ; 3.1 Data Collection and Preprocessing -- 3.2 Data Annotation -- 4 Experimental Results -- 5 Conclusion -- References -- Multimodal Deep Learning and Fast Retrieval for Recommendation -- 1 Introduction -- 2 Multimodal Embedding of Text and Images -- 3 Search and Retrieval Through LSH -- 4 Experimental Analysis -- References -- Natural Language Processing -- Mining News Articles Dealing with Food Security -- 1 Introduction -- 2 Proposed Approach -- 2.1 Text Mining Approaches -- 2.2 Our Food Security Pipeline -- 3 Experiments -- 3.1 Corpus of Newspapers -- 3.2 Results -- 4 Conclusion and Future Work -- References -- Identification of Paragraph Regularities in Legal Judgements Through Clustering and Textual Embedding -- 1 Introduction -- 2 The Proposed Method JPReg -- 2.1 Training of Document and Paragraph Embedding Models -- 2.2 Embedding of the Paragraph of the Reference Set -- 2.3 Identification of Paragraph Regularities -- 3 Experiments -- 3.1 Results -- 4 Conclusions -- References -- Aspect Term Extraction Improvement Based on a Hybrid Method -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 Step 1: Linguistic Knowledge-Based Method for Aspect Terms Extraction -- 3.2 Step 2: Deep Learning-Based Method for Aspect Terms Extraction -- 3.3 Step 3: Improvement of the Aspect Final List with an Out-Domain Pruning Algorithm -- 4 Experiments and Results -- 4.1 Dataset -- 4.2 Evaluation of Our Proposed Method for Aspect Terms Extraction -- 5 Conclusion -- References -- Exploring the Impact of Gender Bias Mitigation Approaches on a Downstream Classification Task -- 1 Introduction -- 2 Related Work -- 3 Approach -- 4 Results -- 5 Conclusion -- References -- A Semi-automatic Data Generator for Query Answering -- 1 Introduction -- 2 Proposed Method -- 3 Experiments -- 3.1 Quantitative Analysis -- 3.2 A Better Estimation for QA Model Performances. ; 4 Conclusion -- References -- Explainability -- XAI to Explore Robustness of Features in Adversarial Training for Cybersecurity -- 1 Introduction -- 2 Related Work -- 3 Proposed Methodology -- 4 Empirical Evaluation -- 4.1 Dataset Description -- 4.2 Implementation Details -- 4.3 Results -- 5 Conclusion -- References -- Impact of Feedback Type on Explanatory Interactive Learning -- 1 Introduction -- 2 Related Work -- 2.1 Model Training -- 2.2 Model Explanation -- 2.3 Feedback Collection -- 3 Methods -- 3.1 Dataset for XIL -- 3.2 Experimental Setup -- 3.3 Model Training -- 4 Results -- 4.1 Random Decoy Fashion MNIST -- 4.2 Class-wise Decoy Fashion MNIST -- 5 Conclusion -- References -- Learning and Explanation of Extreme Multi-label Deep Classification Models for Media Content -- 1 Introduction -- 2 Related Work -- 3 Framework -- 3.1 Hierarchical Deep Multi-label Classification -- 3.2 From Prediction to Explanation -- 4 Experimental Results -- 4.1 Numerical Results -- 4.2 Explanation Prototypes -- 5 Conclusions and Future Work -- References -- An Interpretable Machine Learning Approach to Prioritizing Factors Contributing to Clinician Burnout -- 1 Introduction -- 2 Methods -- 2.1 Data Collection and Study Measures -- 2.2 Dataset Preparation -- 2.3 Feature Selection -- 2.4 Classification -- 2.5 Feature Importance -- 3 Results -- 3.1 Feature Selection -- 3.2 Classification -- 3.3 Feature Importance -- 4 Discussion -- 5 Conclusion -- References -- A General-Purpose Method for Applying Explainable AI for Anomaly Detection -- 1 Anomaly Detection and Interpretability -- 2 Conventions and Basic Definitions -- 3 Explainability vs. Interpretability -- 3.1 Explainability -- 3.2 Interpretablity -- 4 An Approach for Interpreting Anomalies -- 4.1 Choose an Exemplar Baseline Set -- 4.2 Choose a Measure of Dissimilarity -- 4.3 Select a Baseline Point. ; 4.4 Choose a Path from the Anomaly to the Baseline -- 4.5 Apply an Explanation Function with the Baseline -- 5 Experiments -- 6 Discussion and Future Work -- References -- More Sanity Checks for Saliency Maps -- 1 Introduction -- 2 Related Work -- 3 Comparing Human's Saliency Maps to XAI's -- 4 Dispersion for Saliency Maps -- 5 Conclusion -- References -- Intelligent Systems -- Deep Reinforcement Learning for Automated Stock Trading: Inclusion of Short Selling -- 1 Introduction -- 2 Related Works -- 3 Background -- 3.1 Deep Reinforcement Learning Algorithms -- 3.2 Technical Indicators -- 4 Deep Reinforcement Learning Approach to Automated Stock Trading -- 4.1 Stock Trading Problem Formulation -- 4.2 Dataset -- 4.3 Trading Objectives -- 4.4 Financial Markets' Constraints -- 4.5 Shorting Thresholding -- 4.6 Turbulence as a Safety Switch -- 5 Results and Discussion -- 5.1 Performance Metrics -- 5.2 Performance Evaluation of Modified DRL Agents -- 6 Conclusion -- References -- Scaling Posterior Distributions over Differently-Curated Datasets: A Bayesian-Neural-Networks Methodology -- 1 Introduction -- 2 Case Study: Stock Quotation Prediction -- 3 Related Work -- 4 Innovative Sampling Methods -- 5 Conclusions and Future Work -- References -- Ensembling Sparse Autoencoders for Network Covert Channel Detection in IoT Ecosystems -- 1 Introduction -- 2 Attack Scenario and Threat Modelling -- 2.1 Attack Scenario -- 2.2 Dataset for Modelling the Covert Channel -- 3 Deep Ensemble Learning Scheme -- 3.1 Detection Through a Single Autoencoder -- 3.2 Learning and Combining Different Detectors -- 4 Performance Evaluation -- 4.1 Pre-processing, Parameters and Evaluation Metrics -- 4.2 Numerical Results -- 5 Conclusions and Future Work -- References -- Towards Automation of Pollen Monitoring: Image-Based Tree Pollen Recognition -- 1 Introduction -- 1.1 Background. ; 2 Biological Data -- 3 Methods -- 3.1 Object Detection -- 3.2 Quality Measures for Model Evaluation -- 3.3 Training Process -- 3.4 Statistical Analysis -- 4 Results -- 5 Summary and Conclusions -- References -- Rough Sets for Intelligence on Embedded Systems -- 1 Introduction -- 1.1 Embedded Systems -- 2 Algorithm Preliminaries -- 2.1 KNN -- 2.2 FRNN -- 2.3 FROVOCO -- 3 Experiments -- 3.1 Model Training -- 3.2 Model Testing -- 4 Future Research -- 5 Conclusion -- References -- Context as a Distance Function in ConSQL -- 1 Introduction -- 2 Context as a First-Class Citizen for Query Answering -- 2.1 The Concept of Context in a Conversation -- 2.2 Cumulative and Disjunctive Context Switch -- 3 Contextual Query Language ConSQL -- 3.1 Syntax of ConSQL -- 3.2 Semantics of ConSQL -- 4 Conclusions -- References -- Classification and Clustering -- Detecting Anomalies with LatentOut: Novel Scores, Architectures, and Settings -- 1 Introduction -- 2 Preliminaries and Method -- 2.1 Definition of LatentOut -- 2.2 Extension to GAAL Architectures -- 2.3 LatentOut for Semi-supervised Outlier Detection -- 3 Experimental Results -- 4 Conclusion -- References -- Richness Fallacy -- 1 Introduction -- 2 Richness and Learnability -- 3 Richness Problems in Euclidean Space -- 4 Disturbing Effects of Consistency Axiom on Richness Axiom -- 5 Super-Ball Separation -- 6 Final Remarks -- References -- Adapting Loss Functions to Learning Progress Improves Accuracy of Classification in Neural Networks -- 1 Introduction -- 2 Models and Methods -- 2.1 Neural Network Models and Data Sets -- 2.2 Power Error Loss Function (PEL) -- 2.3 Hyperparameter Optimization -- 3 Results -- 4 Summary and Conclusions -- References -- Multiscale and Multivariate Time Series Clustering: A New Approach -- 1 Introduction -- 2 Notations and Definitions. ; 3 Multiscale and Multivariate Time Series Clustering.
• Titolo autorizzato: Foundations of Intelligent Systems
• ISBN: 3-031-16564-0
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996490355003316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science Ser.