Machine Learning and Knowledge Extraction

Name: Machine Learning and Knowledge Extraction | First IFIP TC 5, WG 8.4, 8.9, 12.9 International Cross-Domain Conference, CD-MAKE 2017, Reggio, Italy, August 29 - September 1, 2017, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

First IFIP TC 5, WG 8.4, 8.9, 12.9 International Cross-Domain Conference, CD-MAKE 2017, Reggio, Italy, August 29 - September 1, 2017, Proceedings

Andreas Holzinger Peter Kieseberg A. Min Tjoa Edgar Weippl(Editor)

Springer (Publisher)

Published on 23. August 2017

XV, 376 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-66808-6 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Persons

Content

Intro
Preface
Organization
Contents
MAKE Topology
On Distance Mapping from non-Euclidean Spaces to Euclidean Spaces
1 Introduction
2 Notations
3 Distances over non-Euclidean Spaces
4 Mapping Solution
5 Algorithm of Distance Mapping
5.1 First Case
5.2 Second Case
6 Using ELM to Learn the Functional Distribution
7 Implementation Improvement
8 Experimental Results
9 Conclusion
References
Some Remarks on the Algebraic Properties of Group Invariant Operators in Persistent Homology
1 Introduction
2 Our Mathematical Model
3 Some New Results on Group Invariant Non-expansive Operators
4 Conclusions
References
Decentralized Computation of Homology in Wireless Sensor Networks Using Spanning Trees
1 Introduction
2 Homological Coverage Criteria
3 Decentralized Computation of Homology
3.1 Network Segmentation and Merging
3.2 Computing Betti Numbers
3.3 Merging Within a Spanning Tree
3.4 Merging Multiple Segments
3.5 Partial Merging
4 Results
5 Conclusions
References
Detecting and Ranking API Usage Pattern in Large Source Code Repository: A LFM Based Approach
1 Introduction
2 Related Work
3 LFM-OUPD: An Approach for Proper API Usage Pattern Recommendation
3.1 API Usage Pattern
3.2 Method Call Sequence Graph Constructor
3.3 API Usage Pattern Detector
3.4 Candidate API Usage Recommender
3.5 Candidate Code Examples Recommender
4 Case Study
4.1 Setup
4.2 CacheBuilder Method Case
5 Conclusion
References
MAKE Smart Factor
Towards a Framework for Assistance Systems to Support Work Processes in Smart Factories
Abstract
1 Introduction and Motivation
2 Methodological Considerations
3 Framework
4 Framework Application
4.1 Intelligent Worker Assistance (Büttner et al. 2017)
4.2 TeleAdvisor (Gurevich et al. 2012)
4.3 Smart-Glasses-Based Service Support System (Niemöller et al. 2017)
5 Conclusion and Outlook
References
Managing Complexity: Towards Intelligent Error-Handling Assistance Trough Interactive Alarm Flood Reduction
1 Introduction and Motivation
2 Related Work
2.1 Assistive Systems for Error-Handling
2.2 Alarm Flood Reduction
2.3 Interactive Machine Learning (iML)
3 Method
4 Concept
4.1 Alarm Flood Reduction
4.2 Adaptive and Responsive User Interface
5 Prototype
5.1 Architecture
5.2 Machine Learning Algorithms
5.3 User Interface
6 Discussion, Conclusion and Outlook
References
Online Self-disclosure: From Users' Regrets to Instructional Awareness
1 Introduction
2 Related Work
2.1 Self-disclosure in the Privacy Landscape
2.2 Preventative Technologies
3 Theoretical Background
3.1 Self-disclosure Privacy Concerns
3.2 Regrets in SNSs
3.3 Instructional Awareness
4 Privacy Heuristics Derivation (PHeDer)
4.1 Conceptual Model
4.2 Method
5 Privacy Heuristics Evaluation in IAS
6 Discussion and Future Work
7 Conclusion
References
MAKE Privacy
Decision Tree Rule Induction for Detecting Covert Timing Channels in TCP/IP Traffic
1 Introduction
2 Related Work
3 DAT Detector
4 Implemented Timing Techniques
5 Experiments
6 Results
6.1 Rule Extraction Experiments
6.2 DAT Testing After Generalization
7 Conclusion
References
Practical Estimation of Mutual Information on Non-Euclidean Spaces
1 Introduction
2 A Short Primer on Anonymization Techniques
2.1 k-anonymity
2.2 Differential Privacy
3 Notations
3.1 Distances over Non-Euclidean Spaces
4 Mutual Information for Usability Quantification
4.1 Estimating Mutual Information
5 Experimental Results
5.1 GPS Routes (Timestamped Data)
5.2 Convergence of the MI Estimators
5.3 k-anonymity Effects on the Trajectory Datasets
5.4 Differential Privacy Effects on the Trajectory Datasets
6 Conclusion
References
IntelliAV: Toward the Feasibility of Building Intelligent Anti-malware on Android Devices
1 Introduction
1.1 On-Device Advanced Security
1.2 Contribution
2 System Design
2.1 Feature Extraction
2.2 Model Construction
2.3 On-Device Testing
3 Experimental Analysis
3.1 Experimental Setup
3.2 Results
3.3 IntelliAV Overhead on Device
4 Limitations
5 Related Works
6 Conclusions and Future Work
References
DO NOT DISTURB? Classifier Behavior on Perturbed Datasets
1 Introduction and Related Work
2 K-Anonymity and Information Loss
3 Experiments
3.1 Data
3.2 Anonymization Algorithm
3.3 Dataset Creation
4 Results and Discussion
4.1 Perturbed Datasets - Selective Deletion
4.2 Anonymized Datasets
4.3 ``Outliers'' Removed
4.4 Anonymization on Outliers Removed
5 Open Problems/Future Challenges
6 Conclusion
References
A Short-Term Forecast Approach of Public Buildings' Power Demands upon Multi-source Data
Abstract
1 Introduction
2 Related Work
3 Methodology
3.1 Grey Correlation Analysis
3.2 Probability Graph Model
4 Case Study and Result
4.1 Data Preparation
4.2 Influence Factors
4.2.1 Scatter Diagram
4.2.2 Remove Noisy Factors
4.3 Prediction
5 Error Analysis and Discussion
6 Conclusion
Acknowledgements
References
MAKE VIS
On the Challenges and Opportunities in Visualization for Machine Learning and Knowledge Extraction: A Research Agenda
1 Introduction
2 A Few Examples of Visualization and Machine Learning Integration
3 Challenges and Opportunities for Research
4 A Potential Road-Map for Bridging the Communities
5 Conclusion
References
Quantitative Externalization of Visual Data Analysis Results Using Local Regression Models
1 Introduction
2 Related Work
3 Data Description and Problem Statement
4 Interactive Regression Modeling
4.1 Linear Regression Models
4.2 Interactive Modeling
5 Case Study
6 Discussion, Conclusion, and Future Work
References
Analysis of Online User Behaviour for Art and Culture Events
1 Introduction
1.1 Context
1.2 Problem Statement
1.3 Proposed Solution
1.4 Structure of the Paper
2 Related Work
3 Approach
3.1 Data Extraction
3.2 Data Preprocessing
3.3 Data Analysis Overview
3.4 Topic Modeling
3.5 Clustering
3.6 Prediction of User Interest
4 Implementation
5 Case Study
6 Results and Discussion
6.1 User Clustering
6.2 Applying Topic Modeling
6.3 Cluster Hierarchy
6.4 Cluster Labeling/User Profiling
6.5 Demographic Analysis - Language
6.6 Demographic Analysis - Gender
6.7 Prediction of Interests of New Users
7 Conclusion and Future Work
References
On Joint Representation Learning of Network Structure and Document Content
1 Introduction
2 Background
2.1 Word Embeddings
2.2 Document Embeddings
2.3 Graph Embeddings
3 Combining Link and Text Information
3.1 Paragraph Vector on Graphs
3.2 Fusing Link and Text Information
4 Related Work
4.1 Paper2Vec
4.2 TADW
5 Evaluation
6 Summary and Future Work
References
MAKE AAL
Ambient Assisted Living Technologies from the Perspectives of Older People and Professionals
1 Introduction
2 Methodology
2.1 Planning
2.2 Focus Group and Sampling
2.3 Data Collection
2.4 Ethics
2.5 Data Analysis
3 Findings and Discussions
3.1 Daily Living
3.2 Social Engagement and Physical Activities
3.3 Technology
3.4 Suggestions/Recommendations
4 Conclusion
References
Human Activity Recognition Using Recurrent Neural Networks
1 Introduction
2 Related Work
3 LSTM Model
4 Experiments
4.1 Dataset
4.2 Results
5 Discussion
6 Future Work
References
Modeling Golf Player Skill Using Machine Learning
Abstract
1 Introduction
2 Background
3 Related Work
4 Method
4.1 Data Collection
4.2 Preprocessing
4.3 Experiments
4.4 Model Interpretation
5 Results
5.1 Basic Statistics
5.2 Predictive Performance
5.3 Interpretation of Models
6 Discussion and Conclusions
References
Predicting Chronic Heart Failure Using Diagnoses Graphs
1 Introduction
2 Data Description
3 Building a Representational Predictive Model
4 Predicting Heart Failure for an Unseen Patient
5 Results
6 Discussion
7 Conclusion
References
MAKE Semantics
A Declarative Semantics for P2P Systems
1 Introduction
2 Background
3 P2P Systems: Syntax and Semantics
3.1 Syntax
3.2 Semantics
4 A More General Framework
5 Query Answers and Complexity
6 Related Work
7 Conclusion
References
Improving Language-Dependent Named Entity Detection
Abstract
1 Introduction
2 State of the Art in Entity Detection (Spotting)
3 TOMO Approach to Optimize Spotter for the German Language
4 Evaluation Measures and Datasets
4.1 Measures and Benchmarking
4.2 Dataset
5 Experiments and Results
6 Conclusions and Future Work
Acknowledgements
References
Towards the Automatic Detection of Nutritional Incompatibilities Based on Recipe Titles
1 Introduction
2 State of the Art
3 Experimental Setup
3.1 Problem Statement
3.2 Nutritional Incompatibility Representation
3.3 Corpus
3.4 Knowledge Resource
4 Method
4.1 Pre-processing
4.2 From Text to Graph
4.3 From Graph to Associations
4.4 Evaluation and Discussion
4.5 Discussion
5 Conclusion
References
The More the Merrier - Federated Learning from Local Sphere Recommendations
1 Introduction and Motivation
2 Theoretical Building Blocks
2.1 Client-Side Machine Learning
2.2 Privacy and Security
2.3 Interactive Machine Learning (iML)
2.4 Distributed Bagging
3 Proposed Workflow
4 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Machine Learning and Knowledge Extraction

Description

More details

Other editions

Additional editions

Persons

Content

System requirements