Multi-disciplinary trends in artificial intelligence : 14th International Conference, MIWAI 2021, virtual event, July 2-3, 2021 : proceedings / / Phatthanaphong Chomphuwiset, Junmo Kim, Pornntiwa Pawara (editors)

• Record Nr.: UNISA996464509903316
• Pubbl/distr/stampa: Cham, Switzerland : , : Springer, , [2021]; ©2021
• ISBN: 3-030-80253-1
• Descrizione fisica: 1 online resource (202 pages)
• Collana: Lecture Notes in Artificial Intelligence ; ; 12832
• Disciplina: 006.3
• Soggetti: Artificial intelligence
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: Intro -- Preface -- Organization -- Bias, Trust, and Doing Good: The Impacts of Digital Technology on Human Ethics, and Vice Versa (Abstract of Keynote Speaker) -- Contents -- 3D Point Cloud Upsampling and Colorization Using GAN -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Data Pre-processing -- 3.2 Network Architecture -- 3.3 Objective -- 3.4 Post-processing -- 4 Experiments -- 4.1 Dataset -- 4.2 Implementation Details -- 4.3 Upsampling and Colorization Results -- 4.4 Only Colorization Results -- 4.5 Ablation Study -- 5 Evaluation -- 5.1 Evaluation Metrics -- 5.2 Evaluation Results -- 6 Conclusion and Discussion -- References -- Learning Behavioral Rules from Multi-Agent Simulations for Optimizing Hospital Processes -- 1 Introduction -- 1.1 Motivation -- 1.2 Related Work -- 2 Mutli-agent Simulation Setting -- 2.1 Scenario Description -- 2.2 Modeling of the Scenario -- 2.3 Simulation Results as Gantt Charts -- 3 Alternative Solution: Learning Behavioral Rules -- 3.1 Preliminaries -- 3.2 An Advanced Algorithm for Learning HKBs from Data -- 3.3 Application in the Hospital Process Multi-agent Simulation Setting -- 4 Demonstration and Basic Evaluation -- 5 Conclusion and Future Work -- References -- An Open-World Novelty Generator for Authoring Reinforcement Learning Environment of Standardized Toolkits -- 1 Introduction -- 2 System Architecture -- 3 Experimental Results -- 3.1 Domain Editor Results -- 3.2 Environment Editor Results -- 4 ; Discussion and Future Work -- References -- Book Cover and Content Similarity Retrieval Using Computer Vision and NLP Techniques -- 1 Introduction -- 2 Literature Review -- 3 Proposed Method -- 3.1 Image Preprocessing -- 3.2 Feature Extraction Using Speed-Up Robust Features (SURF Descriptor) -- 3.3 Word Segmentation -- 3.4 Stop Word Removal -- 3.5 Feature Generation -- 3.6 Similarity Measurements.; 3.7 Performance Evaluation -- 4 Experiment and Result -- 5 Conclusion -- References -- Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers -- 1 Introduction -- 2 Background and Related Works -- 2.1 Recurrent Neural Networks -- 2.2 Echo State Networks and Conceptors -- 3 Classification with Conceptors -- 3.1 Conceptor Algebra -- 3.2 Classification -- 4 Case Studies -- 4.1 Speech Recognition -- 4.2 Car Driving Maneuvers -- 5 Evaluation -- 5.1 Speech Recognition -- 5.2 Car Driving Maneuvers -- 5.3 Identifying Essential Factors -- 6 Conclusions -- References -- Feature Group Importance for Automated Essay Scoring -- 1 Introduction -- 2 Related Work -- 3 Evaluation Methodology -- 3.1 Data Preprocessing -- 3.2 Learning Algorithms -- 3.3 Evaluation Metric for Learning Algorithm -- 3.4 Experimental Setup -- 3.5 Feature Influence -- 3.6 Feature Selection -- 4 Results and Discussion -- 4.1 QWK Scores Result for Comparison -- 4.2 Feature Selection Results -- 5 Conclusion -- References -- Feature Extraction Efficient for Face Verification Based on Residual Network Architecture -- 1 Introduction -- 2 Related Work -- 3 The Proposed Face Verification System -- 3.1 Ace Detection Using MMOD + CNN -- 3.2 Deep Feature Extraction Using ResNet-50 Architecture -- 4 Experiments -- 4.1 Face Databases -- 4.2 Evaluation Metrics -- 4.3 Evaluation -- 4.4 Discussion -- 5 Conclusion -- References -- Acquiring Input Features from Stock Market Summaries: A NLG Perspective -- 1 Introduction -- 2 Related Work -- 3 Dataset and Problem Formulation -- 3.1 Preliminary -- 3.2 Market Summaries Preprocessing -- 3.3 Dataset Statistics -- 3.4 Generating Input Features -- 3.5 Linearization -- 4 Experimental Setup -- 4.1 Results -- 4.2 Human Evaluation -- 4.3 Discussion and and Error Analysis -- 5 Conclusion -- References.; A Comparative of a New Hybrid Based on Neural Networks and SARIMA Models for Time Series Forecasting -- 1 Introduction -- 2 Methodology -- 2.1 Decomposition Method -- 2.2 Seasonal Autoregressive Integrated Moving Average (SARIMA) Model -- 2.3 Artificial Neural Network (ANN) -- 2.4 Radial Basis Function (RBF) -- 2.5 Proposed Method -- 3 Data Preparation and Model Evaluation Criteria -- 3.1 Data Descriptions and Data Preparation -- 3.2 Model Evaluation Criteria -- 4 Results and Discussion -- 5 Conclusion and Future Research -- 5.1 Conclusion -- 5.2 Future Research -- References -- Cartpole Problem with PDL and GP Using Multi-objective Fitness Functions Differing in a Priori Knowledge -- 1 Introduction -- 2 Cartpole Problem with Pdl -- 2.1 PDL and Genetic Programming -- 2.2 Experiment &amp -- Fitness Function Design -- 3 Results -- 4 Conclusions and Future Work -- References -- Learning Robot Arm Controls Using Augmented Random Search in Simulated Environments -- 1 Introduction -- 2 Estimating Policy Using Random Search -- 2.1 Policy Space Search Using Augmented Random Search -- 3 Empirical Set up Using Robot Arm Domain -- 3.1 Designing Robot Arm-Reaching Tasks -- 3.2 State Representations -- 3.3 Training a Robot Arm Using ARS -- 4 Empirical Results and Discussion -- 5 Conclusion -- References -- An Analytical Evaluation of a Deep Learning Model to Detect Network Intrusion -- 1 Introduction -- 2 Literature Review -- 3 Dataset Overview -- 4 Research Methodology -- 4.1 Preprocessing -- 4.2 Feature Selection -- ; 4.3 Class Imbalance Handling -- 4.4 Long Short Term Memory (LSTM) -- 4.5 Machine Learning Models -- 5 Results and Discussions -- 6 Conclusion -- References -- Application of Machine Learning Techniques to Predict Breast Cancer Survival -- 1 Introduction -- 2 Material and Method -- 2.1 Machine Learning Techniques -- 2.2 Methods.; 3 Experiment Results -- 3.1 Insight Model Performance -- 3.2 Overall Model Performance -- 4 Discussion and Conclusion -- References -- Thai Handwritten Recognition on BEST2019 Datasets Using Deep Learning -- 1 Introduction -- 2 Related Works -- 2.1 Thai Language Property -- 2.2 Thai Handwritten Recognition -- 3 The Datasets -- 4 Methodology of Thai Handwritten Recognition -- 4.1 Text Localization -- 4.2 Model Generation -- 4.3 Connectionist Temporal Classification (CTC) -- 4.4 Character Error Rate (CER) -- 5 Experiment and Results -- 6 Conclusion -- References -- Comparing of Multi-class Text Classification Methods for Automatic Ratings of Consumer Reviews -- 1 Introduction -- 2 Related Work -- 3 Dataset -- 4 The Method of Multi-class Classifiers Modelling -- 4.1 Pre-processing of Movie Reviews -- 4.2 Feature Selection and Text Representation -- 4.3 Term Weighting -- 4.4 Multi-class Classifiers Modelling -- 5 Experimental Results -- 6 Conclusion -- References -- Improving Safety and Efficiency for Navigation in Multiagent Systems -- 1 Introduction -- 2 Fundamentals -- 2.1 Reciprocal Velocity Obstacles (RVO) -- 2.2 3D Reciprocal Velocity Obstacle (3DRVO) -- 2.3 Three Dimensional Collision Avoidance -- 3 Believe-Desire-Intention Architecture -- 3.1 Planning Strategy with Sub-goal -- 4 K-D Tree Algorithms -- 4.1 3D-Tree Algorithms -- 5 Experiment and Results -- 5.1 The Scenes -- 5.2 Results -- 6 Conclusion and Future Work -- References -- Correction to: Thai Handwritten Recognition on BEST2019 Datasets Using Deep Learning -- Correction to: Chapter "Thai Handwritten Recognition on BEST2019 Datasets Using Deep Learning" in: P. Chomphuwiset et al. (Eds.): Multi-disciplinary Trends in Artificial Intelligence, LNAI 12832, https://doi.org/10.1007/978-3-030-80253-0_14 -- Author Index.

Bioetica e pluralismo dei valori : tolleranza, principi, ideali morali / / Roberta Sala

• Record Nr.: UNINA9910141737403321
• Autore: Sala Roberta <1964->
• Pubbl/distr/stampa: Liguori Editore
• Descrizione fisica: 1 online resource (ix, 384 p.)
• Soggetti: Bioethics; Medical ethics; Toleration; Pluralism; Ethics
• Lingua di pubblicazione: Italiano
• Formato: Materiale a stampa
• Livello bibliografico: Monografia

Source Modeling Techniques for Quality Enhancement in Statistical Parametric Speech Synthesis / / by K. Sreenivasa Rao, N. P. Narendra

• Record Nr.: UNINA9910337649203321
• Autore: Rao K. Sreenivasa (Krothapalli Sreenivasa)
• Pubbl/distr/stampa: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2019
• ISBN: 3-030-02759-7
• Edizione: [1st ed. 2019.]
• Descrizione fisica: 1 online resource (145 pages)
• Collana: SpringerBriefs in Speech Technology, Studies in Speech Signal Processing, Natural Language Understanding, and Machine Learning, , 2191-737X
• Disciplina: 006.54
• Soggetti: Signal processing; Image processing; Speech processing systems; Natural language processing (Computer science); Computational linguistics; Signal, Image and Speech Processing; Natural Language Processing (NLP); Computational Linguistics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Chapter 1. Introduction -- Chapter 2. Background and literature review -- Chapter 3. Robust voicing detection and F0 estimation method -- Chapter 4. Parametric approach of modeling the source signal -- Chapter 5. Hybrid approach of modeling the source signal -- Chapter 6. Generation of creaky voice -- Chapter 7. Summary and conclusions.
• Sommario/riassunto: This book presents a statistical parametric speech synthesis (SPSS) framework for developing a speech synthesis system where the desired speech is generated from the parameters of vocal tract and excitation source. Throughout the book, the authors discuss novel source modeling techniques to enhance the naturalness and overall intelligibility of the SPSS system. This book provides several important methods and models for generating the excitation source parameters for enhancing the overall quality of synthesized speech. The contents ; of the book are useful for both researchers and system developers. For researchers, the book is useful for knowing the current state-of-the-art excitation source models for SPSS and further refining the source models to incorporate the realistic semantics present in the text. For system developers, the book is useful to integrate the sophisticated excitation source models mentioned to the latest models of mobile/smart phones. Presents the efficient excitation source modeling techniques for generating high quality speech; Includes a combination of both waveform and parametric methods to enhance the quality of synthesis; Features and methods that need less memory and computational requirements than others, allowing them to be integrated to smart phones and smaller devices.