Advances in artificial intelligence and applied cognitive computing : proceedings from ICAI'20 and ACC'20 / / edited by Hamid R. Arabnia [and five others]

• Pubblicazione: Cham, Switzerland : , : Springer, , [2021]; ©2021
• Descrizione fisica: 1 online resource (1152 pages)
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence; Soft computing
• Persona (resp. second.): ArabniaHamid
• Note generali: Includes index.
• Nota di contenuto: Intro -- Preface -- Artificial Intelligence: ICAI 2020 - Program Committee -- Applied Cognitive Computing: ACC 2020 - Program Committee -- Contents -- Part I Deep Learning, Generative Adversarial Network, CNN, and Applications -- Fine Tuning a Generative Adversarial Network's Discriminator for Student Attrition Prediction -- 1 Introduction -- 2 Background and Other Work -- 3 Methodology -- 3.1 Discriminator -- 3.2 Generator -- 4 Experiments and Results -- 4.1 Experiment 1 -- 4.2 Experiment 2 -- 4.3 Experiment 3 -- 4.4 Results -- 5 Conclusions -- References -- Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning -- 1 Introduction -- 2 Definition and Related Work -- 2.1 Image/Video Captioning -- 2.2 Text Summarization -- 3 Methodology -- 3.1 Video to Document Process -- 3.2 Document to Title Process -- 4 Experiments -- 5 Conclusion -- References -- White Blood Cell Classification Using Genetic Algorithm-Enhanced Deep Convolutional Neural Networks -- 1 Introduction -- 2 White Blood Cells -- 3 Deep Convolutional Network Model and Kaggle Data Set -- 3.1 Genetic Algorithm -- 3.2 Chromosome Representation of CNN Optimization Using GA -- 3.3 Data Preprocessing -- 3.4 Genetic Algorithm -- 3.5 Convolutional Neural Network Model -- 3.6 Kaggle Data Set -- 4 GA-Enhanced D-CNN Model and Results -- 5 Conclusions -- References -- Deep Learning-Based Constituency Parsing for Arabic Language -- 1 Introduction -- 2 Survey of Related Work -- 3 Dense Input Representation -- 4 Parse Tree Generator Model -- 5 Workflow -- 5.1 Workflow -- 5.2 Dataset -- 6 Experiments -- 6.1 Short Sentences with Minimum Split Points -- 6.2 Short Sentences with Maximum Split Points -- 6.3 Long Sentences with Minimum Split Points -- 6.4 Long Sentences with Maximum Split Points -- 7 Conclusion -- References. ; Deep Embedded Knowledge Graph Representationsfor Tactic Discovery -- 1 Introduction -- 1.1 Exploration Domain: NFL Football -- 2 Methodology -- 2.1 Naive Vectorization -- 2.2 Knowledge Graph Construction -- 2.2.1 Domain-Specific Semantic Graph -- 2.2.2 Specification Graph -- 2.3 Embedding Techniques -- 2.4 Testing Protocol -- 2.4.1 Supervised Classification Task -- 2.4.2 Unsupervised Discovery Task -- 3 Results -- 3.1 Supervised Classification Task -- 3.2 Unsupervised Discovery Task -- 4 Conclusions -- References -- Pathways to Artificial General Intelligence: A Brief Overview of Developments and Ethical Issues via Artificial Intelligence, Machine Learning, Deep Learning, and Data Science -- 1 Introduction -- 2 Artificial Intelligence -- 3 Data Science -- 4 Machine Learning (ML) -- 5 Artificial Neural Network -- 6 Deep Learning (DL) -- 7 Discussion -- 8 Ethics -- References -- Brain Tumor Segmentation Using Deep Neural Networks and Survival Prediction -- 1 Introduction -- 2 Materials and Methods -- 2.1 Data Acquisition -- 2.2 Data Preprocessing -- 2.3 3D Deep Learning Algorithms -- 3 Results -- 3.1 DeepMedic Base Model -- 3.1.1 3D U-Net Neural Network Model -- 3.1.2 Survival Prediction -- 4 Discussion -- 5 Conclusion -- References -- Combination of Variational Autoencoders and Generative Adversarial Network into an Unsupervised Generative Model -- 1 Introduction -- 2 Related Work -- 3 Agent Model -- 4 VAE (V) Model -- 5 MDN-RNN (M) Model -- 6 Controller Model (C) -- 7 GAN/Discriminator -- 8 C. MDN-RNN (M) Model -- 9 D. Controller Model© -- 10 Experimental Results of Car Racing: Feature Extraction -- 11 Evolutional Strategies and Doom RNN -- 12 Conclusion -- References -- Long Short-Term Memory in Chemistry Dynamics Simulation -- 1 Introduction -- 2 Methodology -- 2.1 Prediction-Correction Algorithm -- 2.2 Long Short-Term Memory -- 2.3 Model. ; 3 Experimental Results -- 4 Conclusion and Future WORK -- References -- When Entity Resolution Meets Deep Learning, Is Similarity Measure Necessary? -- 1 Introduction -- 2 Problem Statement and Related Work -- 3 The Design of the Deep Learning Method -- 3.1 Difference with the Traditional Method -- 3.2 Record Pair Representation -- 3.3 Deep Learning Classifier -- 4 Experiments and Results -- 4.1 Convolutional Neural Network -- 4.2 Long Short-Term Memory -- 4.3 Embedding Combining MLP -- 4.4 Count Combining MLP -- 4.5 TF-IDF Combining MLP -- 4.6 Validation on Real-World Cora Data -- 5 Conclusion and Future Work -- References -- Generic Object Recognition Using Both Illustration Images and Real-Object Images by CNN -- 1 AlexNet [1] -- 2 An Experiment on Object Recognition Using AlexNet -- 3 Generation of Illustration Images -- 4 Evaluations -- 5 Conclusion -- References -- A Deep Learning Approach to Diagnose Skin Cancer Using Image Processing -- 1 Introduction -- 2 Dataset -- 3 Methodology -- 3.1 Image Preprocessing -- 3.2 CNN -- 3.3 VGG-Net -- 4 Results -- 5 Conclusions -- References -- Part II Learning Strategies, Data Science, and Applications -- Effects of Domain Randomization on Simulation-to-Reality Transfer of Reinforcement Learning Policies for Industrial Robots -- 1 Introduction -- 2 Related Work -- 2.1 Reinforcement Learning -- 2.2 Simulation-to-Reality Transfer Learning -- 2.3 Attention Maps -- 3 Experimental Setup -- 3.1 Learning Environment -- 3.2 Agent Architecture -- 3.3 Design of Experiments -- 4 Results -- 4.1 Training in Simulation -- 4.2 Transfer to Real World -- 4.3 Attention Maps -- 4.4 Summary and Outlook -- References -- Human Motion Recognition Using Zero-Shot Learning -- 1 Introduction -- 2 Related Work -- 2.1 Supervised Learning -- 2.2 Unsupervised Learning -- 2.3 Auto-Encoder -- 3 Proposed Method -- 3.1 Preliminary. ; 3.2 Semantic Auto-Encoder Adaptation on Human Motion Recognition -- 3.3 Tuning Projection Functions for Semantic Auto-Encoder -- 4 Experimental Result -- 4.1 Dataset -- 4.2 Supervised Learning Results -- 4.3 Unsupervised Learning -- 5 Discussion and Conclusion -- References -- The Effectiveness of Data Mining Techniques at Estimating Future Population Levels for Isolated Moose Populations -- 1 Introduction -- 2 Methods -- 2.1 Data Wrangling -- 2.2 Multiple Regression -- 2.2.1 First Maximal Model -- 2.2.2 Reduced Parameter Maximal Model -- 2.3 Regression Trees -- 2.4 Neural Networks -- 2.5 K-Nearest Neighbors (KNN) Regression -- 2.6 Simulation (After Knadler [6]) -- 2.6.1 System Analysis and Data Collection -- 2.6.2 Simulation Habitat -- 2.6.3 Wolf Characterization -- 2.6.4 Moose Characterization -- 2.6.5 Simulation Initialization -- 3 Results -- 3.1 Overview -- 3.2 Constant Population Assumption -- 3.3 Multiple Regression -- 3.4 Regression Tree -- 3.5 Neural Network -- 3.6 KNN1 -- 3.7 KNN2 -- 3.8 KNN3 -- 3.9 KNN4 -- 4 Conclusions -- References -- Unsupervised Classification of Cell-Imaging Data Using the Quantization Error in a Self-Organizing Map -- 1 Introduction -- 2 Materials and Methods -- 2.1 Images -- 2.2 SOM Prototype and Quantization Error (QE) -- 2.3 SOM Training and Data Analysis -- 3 Results -- 4 Conclusions -- References -- Event-Based Keyframing: Transforming Observation Data into Compact and Meaningful Form -- 1 Introduction -- 2 Systems Requirements for Adaptive Learning -- 3 Insights from Past Experiences -- 4 Event-Based Keyframing -- 4.1 Event Representation and Event Recognition -- 4.2 Keyframes and Keyframing -- 4.3 Elaboration and Repair -- References -- An Incremental Learning Scheme with Adaptive Earlystopping for AMI Datastream Processing -- 1 Introduction -- 2 Problem Description -- 3 Proposed System. ; 3.1 Architecture Overview -- 3.2 Proposed Incremental Learning Scheme -- 4 Experiment Results -- 4.1 Experimental Environment -- 4.2 Effects of Concept Drift Threshold -- 4.3 Performance Comparison with Other Incremental Learning Algorithms -- 5 Conclusions -- References -- Traceability Analysis of Patterns Using Clustering Techniques -- 1 Introduction -- 2 Literature Review About Approaches for Traceability -- 3 Analyzed Techniques -- 4 Experiments -- 4.1 Metrics -- 4.2 Results -- 4.2.1 General Results -- 4.2.2 Analysis of the Results -- 4.3 Example of Analysis of the Traceability of the Patterns -- 5 Conclusions -- References -- An Approach to Interactive Analysis of StarCraft: BroodWar Replay Data -- 1 Introduction -- 2 Logic Programming -- 2.1 Encoding Domain Knowledge in Datalog -- 2.2 Datalog Queries -- 3 Knowledge Representation -- 3.1 StarCraft Domain Knowledge -- 4 Replay Knowledge Representation -- 5 Example Data Analyses -- 5.1 Build Order Identification -- 5.2 State Estimation -- 5.3 Future Work -- 6 Concluding Remarks -- References -- Merging Deep Learning and Data Analytics for Inferring Coronavirus Human Adaptive Transmutability and Transmissibility -- 1 Introduction and Approaches -- 2 Methods -- 2.1 Develop Deep Learning-Based Methods for Interacting Host-Cell Identification -- 2.2 Stacked Autoencoders for Dimension Reduction -- 2.3 Nonmetric Similarity Measurement -- 2.4 Hybrid Unsupervised Clustering -- 2.5 Build a Hybrid Statistical Model to Construct the Temporal Order of Host-Cell-Adaptive Process -- 2.6 Identifying Adjacency Relationships between Clusters and Reconstructing Interacting Host-Cell Lineage -- 2.7 Constructing Pseudo-temporal Ordering of Individual Interaction -- 2.8 Reconstruct Host-Cell-Specific Regulatory Networks by Integrating Profiles and Pseudo-Temporal Information -- 2.9 Building Target Interaction Modules. ; 2.10 Establish Differential Interaction Modules.
• Titolo autorizzato: Advances in artificial intelligence and applied cognitive computing
• ISBN: 3-030-70296-0
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910502594303321
• Lo trovi qui: Univ. Federico II
• Serie: Transactions on Computational Science and Computational Intelligence