Further processing options
available via online resource

Knowledge Management and Acquisition for Intelligent Systems: 15th Pacific Rim Knowledge Acquisition Workshop, PKAW 2018, Nanjing, China, August 28-29, 2018, Proceedings.

Saved in:

Authors and Corporations: Yoshida, Kenichi., Lee, Maria.
Other Authors: Lee, Maria. []
Edition: 1st ed.
Type of Resource: E-Book
Language: English
published:
Cham : Springer International Publishing AG, 2018.
©2018.
Series: Lecture Notes in Computer Science Series
Subjects:
Source: Ebook Central
ISBN: 9783319972893
Table of Contents:
  • Intro
  • Preface
  • Organization
  • Contents
  • Building a Commonsense Knowledge Base for a Collaborative Storytelling Agent
  • Abstract
  • 1 Introduction
  • 2 Related Works
  • 3 Extracting Knowledge from ConceptNet
  • 4 Expanding the Commonsense Ontology
  • 5 Filtering the Concepts
  • 6 Discussion
  • 6.1 Processing User Input
  • 6.2 Generating Responses
  • 7 Conclusion and Further Work
  • References
  • A Knowledge Acquisition Method for Event Extraction and Coding Based on Deep Patterns
  • 1 Introduction
  • 2 Event Extraction and Coding Framework
  • 2.1 AfPak Ontology
  • 2.2 Event Definition and Structure
  • 2.3 Pattern Creation and Generalisation
  • 2.4 Pattern Based Event Extraction
  • 3 Event Coding Assistant
  • 4 Evaluation
  • 4.1 Evaluation of Event Coding
  • 4.2 Evaluation of Pattern Generalisation
  • 5 Related Work
  • 6 Conclusions and Future Research
  • References
  • Incremental Acquisition of Values to Deal with Cybersecurity Ethical Dilemmas
  • Abstract
  • 1 Introduction
  • 2 Background and Theoretical Foundations
  • 2.1 Schwartz's Values Theory
  • 2.2 AORTA
  • 2.3 Adding Values to BDI Agents
  • 2.4 Ripple Down Rules
  • 3 Proposed Approach
  • 4 Example
  • 5 Discussion
  • 6 Conclusion
  • References
  • Towards Realtime Adaptation: Uncovering User Models from Experimental Data
  • Abstract
  • 1 Introduction
  • 2 Identifying Data for Building User Models
  • 3 Methodology
  • 3.1 Intelligent Virtual Agents for Reducing Study Stress
  • 3.2 Educational Virtual World for Science Inquiry
  • 3.3 Data Processing and Analysis
  • 4 Results
  • 4.1 Reducing Study Stress Results
  • 4.2 Educational Virtual World Results
  • 5 Discussion
  • 6 Conclusions and Future Directions
  • Acknowledgements
  • References
  • Supporting Relevance Feedback with Concept Learning for Semantic Information Retrieval in Large OWL Knowledge Base
  • Abstract
  • 1 Introduction.
  • 2 Related Work
  • 3 Concept Learning Problem in OWL Knowledge Base
  • 3.1 Concept Learning Problem
  • 3.2 The General Procedure of CLDL Based Interactive Search
  • 4 Improving CLDL Search Performance by Reducing the Scale of OWL Knowledge Base
  • 4.1 Reducing the Scale of CLDL Problem
  • 4.2 Clustering Based Partition by Analyzing the Structure of Knowledge Base
  • 4.2.1 Analyzing the Cluster Structure of OWL Knowledge Base
  • 4.2.2 Partitioning OWL Knowledge Base by Clustering
  • 5 Experiment
  • 5.1 Dataset and Evaluation Criteria
  • 5.2 Experiment Results
  • 5.2.1 The CLDL Based Search on the Complete Knowledge Base
  • 5.2.2 The Search Based on Partitioned Knowledge Base
  • 6 Conclusion and Further Work
  • Acknowledgement
  • References
  • Combining Concept Learning and Probabilistic Information Retrieval Model to Understand User's Searching Intent in OWL Knowledge Base
  • Abstract
  • 1 Introduction
  • 2 Related Work
  • 3 Concept Learning and Probabilistic Information Retrieval
  • 4 Probabilistic IR in OWL KB Using Concept Learning
  • 5 Experiment
  • 5.1 Describing User's Intent
  • 5.2 Efficiency of Uncertain Inference in OWL KB for Probabilistic IR
  • 5.3 Overall Performance of the IR Prototype Designed
  • 6 Conclusion
  • Acknowledgement
  • References
  • Diabetic Retinopathy Classification Using C4.5
  • Abstract
  • 1 Introduction
  • 2 Material
  • 3 Methods
  • 3.1 Preprocessing
  • 3.2 Segmentation of MA Candidates
  • 3.3 Feature Space
  • 3.4 Generation of Classification Rules
  • 4 Results
  • 5 Conclusions
  • References
  • Stock Price Movement Prediction from Financial News with Deep Learning and Knowledge Graph Embedding
  • Abstract
  • 1 Introduction
  • 2 Related Work
  • 2.1 Deep Learning in Stock Market Prediction
  • 2.2 Knowledge Graph Embedding
  • 2.3 Representation Learning Based on Text and Knowledge
  • 3 Task Description.
  • 3.1 Research Architecture
  • 3.2 Dataset Description
  • 3.3 Data Pre-Processing
  • 4 Methodology
  • 4.1 Feature Selection by the Model of Joint Learning
  • 4.1.1 Feature Extraction from the News Title Using CNN Model
  • 4.1.2 Feature Extraction from the Event Tuple Using TransE Model
  • 4.1.3 Combined Loss Function for Feature Extraction
  • 4.2 Stock Market Prediction Model
  • 4.2.1 Long Short-Term Memory Networks
  • 4.2.2 Output Layer
  • 5 Experiment and Results
  • 5.1 Experiment Settings
  • 5.2 Results and Discussion
  • 6 Conclusions and Future Works
  • Acknowledgments
  • References
  • Sample Dropout for Audio Scene Classification Using Multi-scale Dense Connected Convolutional Neural Network
  • 1 Introduction
  • 2 Related Work
  • 3 Audio Scene Classification Datasets and Experimental Setup
  • 4 Multi-scale DenseNet
  • 5 Culling Training Samples for Convolutional Neural Network
  • 6 Experimental Results
  • 7 Conclusion
  • References
  • LOUGA: Learning Planning Operators Using Genetic Algorithms
  • 1 Introduction
  • 2 Background and Problem Specification
  • 3 LOUGA
  • 3.1 Genome Model
  • 3.2 Pre-processing
  • 3.3 Fitness Function
  • 3.4 The Genetic Algorithm
  • 3.5 Learning Effects Predicate by Predicate
  • 3.6 Learning Preconditions
  • 4 Results of Experiments
  • 4.1 Efficiency of Predicate by Predicate Approach
  • 4.2 Comparison of GA and Hill Climbing
  • 4.3 Efficiency of Using Types
  • 4.4 Comparison to ARMS
  • 5 Conclusions
  • References
  • k-NN Based Forecast of Short-Term Foreign Exchange Rates
  • 1 Introduction
  • 2 Forecasting Exchange Rates Using k-NN
  • 3 Proposed Method
  • 4 Experimental Settings
  • 4.1 Datasets
  • 4.2 Baseline Methods
  • 4.3 Evaluation Metrics
  • 4.4 Experimental Method for Exchange Rate Forecast
  • 4.5 Experimental Method for Pseudo-Trading
  • 5 Experimental Results
  • 5.1 Evaluation in Forecasting Exchange Rates.
  • 5.2 Evaluation via Pseudo-Trading
  • 6 Conclusion
  • References
  • Multi-dimensional Banded Pattern Mining
  • 1 Introduction
  • 2 Related Work
  • 3 BPM Formalism
  • 4 Calculation of Banding Scores
  • 5 Banded Pattern Mining
  • 5.1 Generation of the Set Max
  • 6 Evaluation
  • 6.1 Comparison of BPM Algorithms (ABPM and EBPM)
  • 6.2 Comparison with Previous Work (BC and MBA)
  • 7 Conclusion
  • References
  • Automated Business Process Discovery and Analysis for the International Higher Education Industry
  • Abstract
  • 1 Introduction
  • 2 Background
  • 3 Process Mining Overview
  • 3.1 Business Process Management
  • 3.2 Process Mining
  • 3.3 Event Logs
  • 3.4 Types of Process Mining
  • 3.5 Process Mining Methodology Framework
  • 4 Process Mining Knowledge Generation
  • 4.1 Event Log Extraction
  • 4.2 Event Log Preparation
  • 4.3 Automated Business Process Discovery
  • 5 Discussion
  • 6 Conclusion
  • References
  • An Analysis of Interaction Between Users and Open Government Data Portals in Data Acquisition Process
  • Abstract
  • 1 Introduction
  • 2 Theoretical Foundation
  • 2.1 Open Government Data Portal
  • 2.2 Users of Open Government Data Portal
  • 2.3 Technology Acceptance Model
  • 3 Research Design and Methods
  • 4 Results
  • 4.1 Users' Data Acquisition Method
  • 4.2 Users' Need of Data Quality
  • 4.3 Helping Functions
  • 5 Discussion
  • 6 Conclusion
  • References
  • Blockchain: Trends and Future
  • 1 Introduction
  • 2 Blockchain Basics
  • 3 Trends in Blockchain Type Data Structure
  • 4 Trends in Consensus Algorithms
  • 5 Trends in Blockchain Systems
  • 6 Blockchain-Based Internet and Its Challenges
  • 7 Conclusion
  • References
  • Selective Comprehension for Referring Expression by Prebuilt Entity Dictionary with Modular Networks
  • 1 Introduction
  • 2 Related Work
  • 3 Our Model
  • 3.1 Expression Filtering Model
  • 3.2 Expression Parsing Module.
  • 3.3 Localization Module
  • 4 Experiments
  • 4.1 Add Error Expression
  • 4.2 The Evaluation on Google-Ref Dataset
  • 4.3 The Evaluation on Visual-7W
  • 5 Conclusion
  • References
  • Pose Specification Based Online Person Identification
  • 1 Introduction
  • 2 Related Work
  • 3 Our Method
  • 3.1 Pose Prediction and Recognition System
  • 3.2 PSM and LSTM
  • 3.3 Face, Character and Clothes Recognition
  • 4 Experiment
  • 4.1 Soccer Dataset
  • 4.2 Results and Analysis
  • 5 Conclusion
  • References
  • Get the Whole Action Event by Action Stage Classification
  • 1 Introduction
  • 2 Related Work
  • 2.1 Off-line Methods
  • 2.2 On-line Methods
  • 3 Our Model
  • 3.1 Online Action Tube Generation
  • 3.2 Classifying the Action Stage
  • 3.3 Link Conditions of Two Action Tubes
  • 4 Implementation
  • 5 Experiments
  • 5.1 Dataset:UCF-24
  • 5.2 Implementation Details
  • 5.3 Validation of Action Stage Classification
  • 5.4 Complete Action Tube Generation Performance
  • 5.5 Comparison with the Existing Methods
  • 6 Conclusion and Future Works
  • References
  • Clothing Attribute Extraction Using Convolutional Neural Networks
  • Abstract
  • 1 Introduction
  • 2 Related Work
  • 2.1 Semantic Annotation of Images
  • 2.2 Clothing Attributes Extraction from Images
  • 2.3 Clothing Attribute Extraction by CNN
  • 3 Method
  • 3.1 Feature Extraction
  • 3.2 SIFT
  • 3.3 Texture Description
  • 3.4 Color Description
  • 3.5 Skin Probability
  • 3.6 Convolution Layer
  • 3.7 Clothing Attribute Classifier
  • 4 Experiments
  • 5 Results
  • 6 Conclusion
  • References
  • Research Paper Recommender Systems on Big Scholarly Data
  • Abstract
  • 1 Introduction
  • 2 Current Status of Research Paper Recommender Systems
  • 2.1 Research Paper Recommender Systems Related Studies
  • 2.2 Research Paper Recommender Systems from the Perspective of Big Scholarly Data.
  • 2.3 Public Available Big Scholarly Datasets.