Knowledge Science, Engineering and Management

Name: Knowledge Science, Engineering and Management | 10th International Conference, KSEM 2017, Melbourne, VIC, Australia, August 19-20, 2017, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

10th International Conference, KSEM 2017, Melbourne, VIC, Australia, August 19-20, 2017, Proceedings

Gang Li Yong Ge Zili Zhang Zhi Jin Michael Blumenstein(Editor)

Springer (Publisher)

Published on 10. August 2017

XVII, 563 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-63558-3 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Learning from Non-stationary Distributions (Invited Speech)
Contents
Text Mining and Document Analysis
Learning Sparse Overcomplete Word Vectors Without Intermediate Dense Representations
1 Introduction
2 Related Work
3 Our Model
3.1 Parameter Estimation
3.2 Optimization Algorithm
4 Evaluation
4.1 Experimental Settings
4.2 Word Analogy
4.3 Word Similarity
4.4 Interpretability
5 Conclusion
References
A Study of Distributed Semantic Representations for Automated Essay Scoring
1 Introduction
2 Common Text Features
3 Semantic Representations for AES
3.1 Methods for Vector Representations
3.2 Semantic Features
4 Experimental Settings
4.1 Dataset
4.2 Evaluation Metrics and Learning Algorithms
5 Evaluation Design and Results
5.1 Evaluation Design
5.2 Evaluation Results
6 Conclusions and Future Work
References
Weakly Supervised Feature Compression Based Topic Model for Sentiment Classification
1 Introduction
2 Related Work
3 Hidden Topic Analysis Model
4 Weakly Supervised Feature Compression Based ELDA
5 Experiment Results
5.1 Data Preparation
5.2 Performance Evaluation
5.3 Results with Different Topics
5.4 Results with Different Gibbs Sampling Iterations
6 Conclusion
References
An Effective Gated and Attention-Based Neural Network Model for Fine-Grained Financial Target-Dependent Sentiment Analysis
1 Introduction
2 Related Work
3 The Proposed Neural Network Model GABi-LSTM
3.1 Motivation
3.2 The Overview of Model Architecture
3.3 Word Representation with Gated Char- and Word- Embedding
3.4 Sentence Representation with Attention-Based Bi-LSTM
3.5 Linear Regression
3.6 Parameter Learning
4 Experiments
4.1 Datasets
4.2 Evaluation Measure
4.3 Experimental Results
4.4 Comparison with the State-of-the-Art Systems
4.5 Qualitative Visualization Analysis
5 Concluding Remarks
References
A Hidden Astroturfing Detection Approach Base on Emotion Analysis
1 Introduction
2 Related Work
3 Hidden Astroturfing Detection Method
3.1 Data Preparation
3.2 Pre-processing Operations
3.3 Bag-of-Word Module Construction
3.4 Emotion Mining and Analysis
3.5 Matching
3.6 Summary
4 Experiment and Evaluation
4.1 Experiment Setup
4.2 Evaluation Result
5 Conclusion
References
Leveraging Term Co-occurrence Distance and Strong Classification Features for Short Text Feature Selection
Abstract
1 Introduction
2 Problem Preliminaries
2.1 Correlation of Two Terms in a Text
2.2 Expected Cross Entropy
3 The Proposed Approach
3.1 Terming Weighting Method Based on Co-occurrence Distance
3.2 Feature Dictionary Construction
4 Experiments and Results Analysis
4.1 Data Sets and Evaluation Metrics
4.2 Experimental Results and Analysis
4.2.1 Comparison of Feature Dictionaries
4.2.2 Effect of Variation of Dictionary Size for Short Text Classification
4.2.3 Classification Performance of Different Feature Selection Methods
5 Conclusions and Future Work
Acknowledgement
References
Formal Semantics and Fuzzy Logic
A Fuzzy Logic Based Policy Negotiation Model
1 Introduction
2 Preliminaries
3 Model Definition
4 Fuzzy Rules
5 Experiment
6 Related Work
7 Conclusions
References
f-ALC(D)-LTL: A Fuzzy Spatio-Temporal Description Logic
1 Introduction
2 Spatial Fuzzy Description Logic
3 Fuzzy Spatio-Temporal Description Logic f-ALC(D)-LTL
3.1 Syntax
3.2 Models
4 Hintikka Structures for f-ALC(D)-LTL
5 Reasoning in f-ALC(D)-LTL
5.1 Tableau Rules
5.2 Tableau Construction
5.3 Tableau Elimination
5.4 Correctness
6 Conclusion and Future Work
References
R-Calculus for the Primitive Statements in Description Logic ALC
1 Introduction
2 Description Logic ALC
3 R-Calculus for Subset-Minimal Change
3.1 SDL: R-Calculus for a Statement
3.2 SDL: R-Calculus for a Set of Statements
4 Conclusions and Further Works
References
A Multi-objective Attribute Reduction Method in Decision-Theoretic Rough Set Model
1 Introduction
2 Preliminaries
2.1 Decision-Theoretic Rough Set Model
2.2 Three Kinds of Criteria in Decision-Theoretic Rough Set Model
3 Multi-objective Attribute Reduction in Decision-Theoretic Rough Set Model
3.1 Multi-objective Attribute Reduct
3.2 Multi-objective Attribute Reduction Algorithm
4 Experiments
4.1 Dataset
4.2 Experimental Setting
4.3 Experimental Results
5 Conclusion
References
A Behavior-Based Method for Distinction of Flooding DDoS and Flash Crowds
1 Introduction
2 Proposed Method
3 Experiments
4 Conclusion
References
Knowledge Management
Analyzing Customer's Product Preference Using Wireless Signals
1 Introduction
2 Channel State Information
3 Analyzing Customer's Product Preference Using CSI
3.1 CSI Preprocessing
3.2 Feature Extraction
3.3 Classification
4 Performance Evaluation
4.1 Experimental Methodology
4.2 Feasibility of Customer's Product Preference Analysis
5 Related Work
5.1 Device-Based Activity Sensing
5.2 Device-Free Activity Sensing Using WiFi
6 Conclusion
References
Improved Knowledge Base Completion by the Path-Augmented TransR Model
1 Introduction
2 Our Approach
2.1 Base Model: TransR
2.2 Path-Augmented TransR: PTransR
2.3 Training Details
3 Evaluation
3.1 Dataset
3.2 Experimental Settings
3.3 Overall Performance
3.4 In-Depth Analysis and Discussion
4 Related Work
5 Conclusion
References
Balancing Between Cognitive and Semantic Acceptability of Arguments
1 Introduction
2 Preliminaries
3 Equilibrium-Based Resolutions
3.1 Semantic and Cognitive Acceptabilities
3.2 Satisfiability Resolution
3.3 Entailment Resolution
3.4 Semantic Equivalence Resolution
4 Generality and Applicability
4.1 Characterising Existence of Resolutions
4.2 Application Illustration in Online Forum
5 Conclusions and Discussion
A Proofs
References
Discovery of Jump Breaks in Joint Volatility for Volume and Price of High-Frequency Trading Data in China
Abstract
1 Introduction
2 Bivariate Normal Distribution
3 Realized Trading Volatility of Price and Volume
3.1 Price Volatility
3.2 Volume Volatility
3.3 Volatility Rate of Price and Volume of Realized Trading
4 The Jump Point Model for High-Frequency Trading Volatility Break
5 The Algorithm of Point-by-Point Test for Jump Critical Points
6 The Empirical Analysis of Jump Critical Points
7 Conclusion
Acknowledgments
References
Device-Free Intruder Sensing Leveraging Fine-Grained Physical Layer Signatures
1 Introduction
2 Related Work
2.1 Gait Based Human Identification
2.2 WiFi Based Activity Recognition
3 System Design
3.1 Channel State Information Extration
3.2 Data Prepocessing
3.3 Step Analysis
3.4 Device-Free Intruder Sensing
4 Experimentation Evaluation
4.1 Equipment
4.2 Experimental Results
5 Conclusion
References
Understanding Knowledge Management in Agile Software Development Practice
Abstract
1 Introduction
2 Background and Related Work
2.1 Knowledge Classifications
2.2 Prior Reviews on Knowledge Management in ASD
3 Review Method
3.1 Planning the Review and Identifying Relevant Literature
3.2 Publication Selection
3.3 Data Extraction and Synthesis
4 Results
4.1 Agile Practices Supporting Knowledge Management
4.2 Knowledge Involved in Agile Practices
5 Discussion
5.1 Implications
5.2 Limitations
6 Conclusion
Acknowledgement
References
Knowledge Integration
Multi-view Unit Intact Space Learning
1 Introduction
2 The Proposed Model
2.1 Background
2.2 Multi-view Unit Intact Space Learning
3 Optimization
3.1 Update Latent Feature Vectors in Unit Intact Space
3.2 Update View Generation Matrices
3.3 Convergence Analysis
3.4 Complexity Analysis
4 Experiments
4.1 Datasets and Evaluation Measures
4.2 Parameter Analysis
4.3 Comparison Results
5 Conclusion
References
A Novel Blemish Detection Algorithm for Camera Quality Testing
Abstract
1 Introduction
2 Related Works
2.1 Traditional Methods Based on Image Filtering
2.2 Image Size Reduction by Scaling
2.3 Median Filtering
2.4 Image Subtraction
2.5 Thresholding
3 Novel Filtering Method
3.1 Influences of Image Noises
3.2 Proposed Multi-directional Median Filter
3.3 Adaptive Threshold with Bias
4 Results and Discussion
4.1 Low Noise Samples
4.2 High Noise Samples
5 Conclusion
Acknowledgments
References
Learning to Infer API Mappings from API Documents
1 Introduction
2 Related Work
3 Approach
3.1 Overview
3.2 Understanding API Documents
3.3 Computing Similarity Between APIs
4 Evaluation
4.1 Dataset
4.2 Experimental Settings
4.3 Results
5 Conclusion
References
Super-Resolution for Images with Barrel Lens Distortions
Abstract
1 Introduction
2 Related Work
3 Proposed Method
3.1 Pretreatment Process
3.2 Training Stage
3.3 Testing Stage
4 Experiments
4.1 Experiment Settings
4.2 Experimental Results
5 Conclusion
Acknowledgments
References
Knowledge Retrieval
Mining Schema Knowledge from Linked Data on the Web
1 Introduction
2 Related Work
3 Background
3.1 The RDF/S Data Models
3.2 DBpedia
3.3 Formal Concept Analysis
4 Schema Extraction
4.1 Mining Conceptual Knowledge from LD
4.2 Translating the Concept Lattice into RDFS
4.3 Naming RDFS Classes
5 Experimental Study
5.1 Dataset
5.2 Experimental Results
5.3 Evaluation
5.4 Discussion
6 Conclusion
References
Inferring User Profiles in Online Social Networks Based on Convolutional Neural Network
Abstract
1 Introduction
2 Related Work
3 Problem Definition
4 Proposed Architecture
4.1 User Profiling in Social Network
4.2 User Profiling in Ego-Network
5 Experiment
5.1 Dataset
5.2 Experiment Result
6 Conclusion
Acknowledgement
References
Co-saliency Detection Based on Superpixel Clustering
Abstract
1 Introduction
2 Related Works
3 Proposed Method
3.1 Build Superpixel Pyramid
3.2 Content-Sensitive Based Multi-scale Saliency (CSMS) Detection
3.3 Superpixel Clustering
3.4 WCS (Weak Co-saliency) Computation
3.5 Integration
4 Experimental Results
4.1 Evaluation of CSMS Method
4.2 Evaluation of SCCD Method
5 Conclusion
Acknowledgment
References
ARMICA-Improved: A New Approach for Association Rule Mining
Abstract
1 Introduction
2 Literature Review
3 Proposed Method
4 Example
5 Evaluation
6 Discussion
7 Conclusion
References
Recommendation Algorithms and Systems
Collaborative Filtering via Different Preference Structures
1 Introduction
2 Preliminaries and Related Work
2.1 Heterogeneous Sources
2.2 Preference Relation
3 Preference Relation-Based Conditional Random Fields
3.1 Problem Statement
3.2 Preference Relation-Based Matrix Factorization
3.3 Conditional Random Fields
3.4 PrefCRF: Unifying PrefNMF and CRF
4 Experiment and Analysis
4.1 Experimental Settings
4.2 Results and Analysis
5 Conclusions and Future Works
References
A Multifaceted Model for Cross Domain Recommendation Systems
1 Introduction
2 Content-Boosted CF for Cross Domain RS
3 The Multifaceted Model
4 Experiments
4.1 Baselines and Evaluation Metrics
4.2 Results
5 Related Works
6 Conclusion
References
Cross Domain Collaborative Filtering by Integrating User Latent Vectors of Auxiliary Domains
Abstract
1 Introduction
2 Related Works
3 Our Model
3.1 Convert the Recommendation Problem into a Classification Problem
3.2 Feature Vector Expansion
3.3 Classification Problem Solving and the Proposed Algorithm
4 Experiments
4.1 Data Sets
4.2 The Setting of the Compared Methods
4.3 Evaluation Protocol
4.4 Results
5 Conclusion
Acknowledgments
References
Collaborative Filtering Based on Pairwise User-Item Blocking Structure (PBCF): A General Framework and Its Implementation
1 Introduction
2 Related Work
3 The Framework of Pairwise User-Item Blocking
4 Implementation of Pairwise User-Item Block Learning
4.1 Unified Feature Extraction
4.2 Users Align Base on Items
4.3 Compute Item Similarity by MinHashing
4.4 Improved Spectral Clustering Based on Items
5 Prediction Based on the Block Structure
5.1 Global Feature Learning
5.2 Local Block Feature Learing
6 Simulation
6.1 Experiment Setup and Evaluation Methodology
6.2 Experiments Comparisons
7 Conclusions
References
Beyond the Aggregation of Its Members---A Novel Group Recommender System from the Perspective of Preference Distribution
1 Introduction
2 Related Work
3 Mathematic Modeling of Group Recommendation Mechanism
3.1 Framework
3.2 Modeling of Prediction of Group Profile
3.3 Decision of Recommendation Results
4 Experiments and Analysis
4.1 Experimental Setup
4.2 Metrics and Baselines
4.3 Results and Analysis
5 Conclusion
References
Exploring Latent Bundles from Social Behaviors for Personalized Ranking
1 Introduction
2 Problem Formulation
3 The Framework
3.1 Modeling Markov Chains Incorporating Social Roles
3.2 Latent Bundle Relationships
3.3 Model Learning
4 Experiments
4.1 Dataset and Evaluation Metric
4.2 Baselines
4.3 Performance and Quantitative Analysis
5 Conclusion
References
Trust-Aware Recommendation in Social Networks
Abstract
1 Introduction
2 Related Work
3 Preliminary
4 The Trust-Aware Recommendation Approach
4.1 Social Trust Matrix
4.2 The Trust-Aware Recommendation Approach
5 Experimental Evaluation
6 Conclusion
Acknowledgment
References
Connecting Factorization and Distance Metric Learning for Social Recommendations
1 Introduction
2 Social Recommender Connecting Factorization and Distance Metric Learning
2.1 Problem Definition
2.2 Distance Metric Learning
2.3 The SocialFD Model
3 Experimental Results
3.1 Experimental Setup
3.2 Performance for Predicting Missing Ratings
3.3 Change of the Distance
4 Related Work
5 Conclusion
References
Knowledge Engineering
Relevant Fact Selection for QA via Sequence Labeling
1 Introduction
2 Related Work
3 Methodology
3.1 Fact Reordering
3.2 Fact to Vector
3.3 Fact Selection
4 Experiments
5 Conclusions
References
Community Outlier Based Fraudster Detection
1 Introduction
2 Related Work
3 Preliminaries
4 Community Outlier Based Fraudster Detection Approach
4.1 Network Construct
4.2 Community Detection
4.3 Community Outlier Based Fraudster Detection
5 Experiments
5.1 Experimental Settings
5.2 Results and Analysis
6 Conclusion
References
An Efficient Three-Dimensional Reconstruction Approach for Pose-Invariant Face Recognition Based on a Single View
Abstract
1 Introduction
2 An Improved Dense Correspondence Method Based on Planar Template Resampling with Geometric Information
2.1 Definition of Planar Template
2.2 Resampling of Original 3D Faces
3 3D Face Reconstruction Based on Sparse Morphable Model
3.1 Construction of 3D Morphable Model
3.2 Face Shape Reconstruction Based on Sparse Morphable Model
4 Experiments and Analysis
4.1 3D Face Database and the Segmentation Performance
4.2 Dense Correspondence Performance of the Proposed Method
4.3 3D Reconstruction Results of the Proposed Method
4.4 Recognition Results of the Proposed Method
5 Conclusions and Discussions
Acknowledgments
References
MIAC: A Mobility Intention Auto-Completion Model for Location Prediction
1 Introduction
2 Related Work
2.1 Mobility Regularity Characterization
2.2 Prediction Algorithm
3 MIAC Model
3.1 Problem Statement
3.2 Mobility Intention Extraction and Transformation
3.3 Mobility Intention Prediction
3.4 Location Prediction
4 Experiment and Analysis
4.1 Data Set and Settings
4.2 Performance Comparison on the Next Location Prediction
4.3 Performance Comparison on the Future Location Prediction
4.4 Performance Comparison on Mobility Intention and QAC-Based Predicting Algorithms
5 Conclusions
References
Automatically Difficulty Grading Method Based on Knowledge Tree
1 Introduction
2 Related Work
3 Methodology
3.1 Algorithm Architecture
3.2 Knowledge Tree Model
3.3 Attributes Box
4 Evaluation
4.1 Question Bank Data Preprocessing
4.2 ``Instruction System'' Ontology Knowledge Tree Building
4.3 Outcome of Classification Accuracy
5 Conclusion and Future Work
References
A Weighted Non-monotonic Averaging Image Reduction Algorithm
1 Introduction
2 Preliminaries
2.1 Aggregation Function and Averaging Aggregation Function
2.2 Non-monotone Averaging Aggregation Function and Penalty Function
3 Sigmoid Function Based Weighted Image Reduction Algorithm
4 Experiments and Evaluation
5 Conclusion
References
Knowledge Representation and Reasoning
Learning Deep and Shallow Features for Human Activity Recognition
1 Introduction
2 Related Work on HAR
3 Feature Representation
3.1 Hand-Crafted Features
3.2 Frequency Transform Features
3.3 Deep Features
4 Evaluation
4.1 Experiment Design
4.2 Results
5 Conclusion
References
Transfer Learning with Manifold Regularized Convolutional Neural Network
1 Introduction
2 Preliminary Knowledge
2.1 Convolutional Neural Network
2.2 Fine-Tuning
2.3 Manifold Regularization
3 MRCNN Model
4 Experiments
4.1 Data Sets and Data Processing
4.2 Baseline Methods
4.3 Implementation Details
4.4 Results
4.5 Analysis and Discussion
4.6 Parameter Sensitivity
5 Related Work
6 Conclusion
References
Learning Path Generation Method Based on Migration Between Concepts
Abstract
1 Introduction
2 Related Work
2.1 Approaches to Learning Path Generation
2.2 Word Similarity
3 Generating a Learning Path
3.1 Definition of Learning Path
3.2 Data Preprocessing
3.3 Extraction of Relevant Concepts
3.4 The Generation Method
4 Test
4.1 Test Data
4.2 Evaluation
4.3 Results
5 Conclusions
References
Representation Learning of Multiword Expressions with Compositionality Constraint
1 Introduction
2 Related Works
3 Our Proposed Model
3.1 Skip-Gram with Negative Sampling (SGNS)
3.2 Composition Model
3.3 The Hybrid Model
4 Experiment and Analysis
4.1 Evaluation Tasks
4.2 Baselines and Experiment Settings
4.3 Performance Evaluation and Analysis
5 Conclusion and Future Work
References
Linear Algebraic Characterization of Logic Programs
1 Introduction
2 Preliminaries
3 Tensor Logic Programming
3.1 Horn Logic Programs
3.2 Disjunctive Logic Programs
3.3 Normal Logic Programs
4 Discussion
5 Conclusion
References
Representation Learning with Entity Topics for Knowledge Graphs
1 Introduction
2 Related Works
3 Methodology
3.1 Notations and Definitions
3.2 Topic Representation of Entities
3.3 Joint Representation Learning of Triples and Topics
3.4 Loss Optimization and Training
4 Experiments
4.1 Datasets and Experiment Settings
4.2 Knowledge Graph Completion
5 Conclusion and Future Work
References
Robust Mapping Learning for Multi-view Multi-label Classification with Missing Labels
1 Introduction
2 The RLM-MCML Approach
2.1 Global Structure of Label Correlations
2.2 The Local Smoothness of Label Structure
2.3 Problem Formulation
3 Experiments
3.1 Datasets
3.2 Evaluation Criteria and Algorithms
3.3 Classification Results
3.4 Impact of Missing Labels
4 Conclusions
References
Fast Subsumption Between Rooted Labeled Trees
1 Introduction
2 Trees, Subsumption and Homomorphism
2.1 Concrete Trees
2.2 Abstract Syntax
2.3 Rooted Labeled Tree Homomorphism
3 Tour Language of a Tree
3.1 Automata Induced by a Tree
3.2 Tour Languages, Containment and Homomorphism
4 Search Data Structures
4.1 Complete Determinization
4.2 Trade Off Between Space and Time
5 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Knowledge Science, Engineering and Management

Description

More details

Other editions

Additional editions

Content

System requirements