
Research and Development in Intelligent Systems XXXII
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The papers in this volume are the refereed papers presented at AI-2015, the Thirty-fifth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, held in Cambridge in December 2015 in both the technical and the application streams.
They present new and innovative developments and applications, divided into technical stream sections on Knowledge Discovery and Data Mining, Machine Learning and Knowledge Acquisition, and AI in Action, followed by application stream sections on Applications of Genetic Algorithms, Applications of Intelligent Agents and Evolutionary Techniques, and AI Applications. The volume also includes the text of short papers presented as posters at the conference.
This is the thirty-second volume in the
Research and Development in Intelligent Systems
series, which also incorporates the twenty-third volume in the
Applications and Innovations in Intelligent Systems
series. These series are essential reading for those who wish to keep up to date with developments in this important field.
More details
Other editions
Additional editions

Persons
Content
- Intro
- Programme Chairs' Introduction
- Acknowledgements/Committees
- AI-2015 Conference Committee
- Technical Executive Programme Committee
- Applications Executive Programme Committee
- Technical Programme Committee
- Application Programme Committee
- Contents
- Research and Development in Intelligent Systems XXXII
- Best Technical Paper
- Sparse Covariance Matrix Adaptation Techniques for Evolution Strategies
- 1 Introduction
- 2 Evolution Strategies
- 2.1 Covariance Matrix Adaptation: The Population Covariance
- 2.2 Step-Size Adaptation
- 3 A Sparse Covariance Matrix Adaptation
- 3.1 Space Transformation
- 3.2 Sparse Covariance Matrix Estimation
- 4 Experiments
- 4.1 Test Suite Und Performance Measure
- 4.2 Results and Discussion
- 5 Conclusions and Outlook
- References
- Knowledge Discovery and Data Mining
- A Replicator Dynamics Approach to Collective Feature Engineering in Random Forests
- 1 Introduction
- 2 Diversified Random Forests: An Overview
- 3 Replicator Dynamics
- 4 Applying Replicator Dynamics to an DRF
- 5 Experimental Study
- 6 Related Work
- 7 Conclusion and Future Work
- References
- A Directed Acyclic Graph Based Approach to Multi-Class Ensemble Classification
- 1 Introduction
- 2 Literature Review
- 3 Directed Acyclic Graph (DAG) Classification Model Framework
- 3.1 DAG Generation
- 3.2 DAG Operation
- 4 Experiments and Evaluation
- 4.1 Comparison Between DAG Approaches
- 4.2 Comparison Between Stand-Alone Classification, Bagging, Binary Tree, OVO SVM and DAG Ensemble Classification
- 4.3 Note on Efficiency
- 5 Conclusion
- References
- CLUB-DRF: A Clustering Approach to Extreme Pruning of Random Forests
- 1 Introduction
- 2 Related Work
- 2.1 Diversity Creation Methods
- 2.2 Diversity Measures
- 3 Proposed Extension: CLUB-DRF
- 3.1 Clustering-Based Diverse Random Forest (CLUB-DRF)
- 3.2 Diversity Measure
- 4 Experimental Study
- 4.1 Results
- 4.2 Analysis
- 4.3 Pruning Level
- 4.4 Performance Comparison with Pruned Neural Network Ensemble
- 5 Conclusion and Future Directions
- References
- Machine Learning and Knowledge Acquisition
- Fast Handwritten Digit Recognition with Multilayer Ensemble Extreme Learning Machine
- 1 Introduction
- 2 Problem Definition
- 3 Related Work
- 3.1 Single Hidden Layer Feedforward Neural Networks
- 3.2 Multiple Hidden Layer Feedforward Neural Networks
- 3.3 Convolutional Neural Networks
- 3.4 Other Approaches
- 4 Extreme Learning Machines
- 4.1 Review of Extreme Learning Machine
- 4.2 Ensemble ELM
- 4.3 Multilayer ELM
- 4.4 Multilayer Ensemble ELM
- 5 Experimental Setup and Evaluation
- 6 Conclusion
- References
- Stylochronometry: Timeline Prediction in Stylometric Analysis
- 1 Introduction
- 2 Previous Work
- 3 Data and Methods
- 3.1 Corpora
- 3.2 Timeline Compression and Analysis
- 4 Experiments
- 4.1 Data Preparation
- 4.2 Variable Selection and Model Evaluation
- 4.3 Results
- 5 Discussion
- 6 Conclusion
- References
- 7 Semantic Analysis for Document Similarity and Search Queries
- Abstract
- 1 Introduction
- 2 Previous Research
- 3 Dream Interpretations
- 4 Semantic Analysis of Search Queries
- 5 Results
- 6 Conclusion and Further Work
- References
- Social Trust in a Familiar Community
- 1 Introduction
- 2 Literature Review
- 2.1 Trust, Experience and Familiarity
- 2.2 Evaluation of Familiarity and Experience
- 3 Modelling Trust from a Community
- 3.1 Familiarity-Experience Based Social Trust
- 3.2 Collection of Data
- 3.3 Analysis with Data
- 4 Conclusion
- References
- AI in Action
- Surface Reconstruction from Point Clouds Using a Novel Variational Model
- 1 Introduction
- 2 Preprocessing
- 2.1 Distance Function for Point Cloud Using Fast Sweeping
- 2.2 The Volume Enclosed by Point Cloud Using the Distance Function
- 3 The Proposed Variational Model for Optimising Reconstruction
- 4 Discretisation
- 5 Experiments
- 6 Conclusion
- References
- 3D Spatial Reasoning Using the Clock Model
- 1 Introduction
- 2 Clock-Based 3D Qualitative Spatial Relations
- 3 Experiments and Discussion
- 4 Conclusions
- References
- Scheduling with Structured Preferences
- 1 Introduction
- 2 Background
- 2.1 DTPs and VDTPs
- 2.2 Utility Difference Networks
- 3 Motivating Example
- 4 Generalizing VDTPs to CDI-VDTPs
- 5 Solving CDI-VDTPs
- 6 Experimental Results
- 7 Related Work
- 8 Conclusions
- References
- 12 An Optimisation Algorithm Inspired by Dendritic Cells
- Abstract
- 1 Introduction
- 2 Dendritic Cells and the Optimization Framework
- 2.1 Human Dendritic Cells
- 2.2 The DC-Mediated Framework
- 2.2.1 Threat Quantification
- 2.2.2 Signal Cascading Network and Effector Control
- 3 Experimental Studies
- 3.1 Quality of Solutions
- 3.2 Diversity of Solutions
- 4 Conclusions
- References
- Short Papers
- Graph-Based Multi-Document Summarization: An Initial Investigation
- 1 Introduction
- 2 Related Work
- 3 The Proposed Model
- 3.1 Pre-processing
- 3.2 Building the Intermediate Representation
- 3.3 Computing the Content and the Coherence Scores
- 3.4 Selecting and Ordering Summary Sentences
- 4 Conclusion
- References
- Towards Expressive Rule Induction on IP Network Event Streams
- 1 Introduction
- 2 Online Generalised Rule Induction Framework
- 2.1 OGRI Framework
- 2.2 Online Generalised Rule Induction
- 3 Conclusions
- References
- A Hybrid Ensemble for Classifying and Repurposing Financial Entities
- 1 Introduction
- 2 Related Work
- 3 Experimentation
- 3.1 Rule Base
- 3.2 Machine Learning Base
- 4 Results
- 5 Discussion
- 6 Future Work
- References
- 16 Data Mining and Knowledge Discovery Approach for Manufacturing in Process Data Optimization
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Co-linearity Index (CLI)
- 2.2 Scores Projected Space to Predict the Optimal Variables Range and Variables Recommendation
- 3 Conclusion
- References
- Applications and Innovations in Intelligent Systems XXIII
- Best Technical Paper
- 17 Development of Temporal Logic-Based Fuzzy Decision Support System for Diagnosis of Acute Rheumatic Fever/Rheumatic Heart Disease
- Abstract
- 1 Introduction
- 2 ARF Symptoms and Diagnosis Process
- 2.1 Signs and Symptoms of ARF
- 2.2 Diagnosis Process of ARF
- 2.3 Purposed Model for Diagnosis of ARF
- 2.4 Signs and Symptoms for Different Level of the Severity
- 3 Methodology
- 3.1 Knowledge-Base and Rules to Diagnose of ARF
- 3.1.1 Search and Match Stage (SMS)
- 3.1.2 Rule Pattern Matching (RPM)
- 3.1.3 New Rule Formation (NRF)
- 3.1.4 Rule Selection Mechanism (RSM)
- 3.2 Temporal Logic and Temporal Rule (TR)
- 3.2.1 Relation Between Arthritis and Other Symptoms: Absolutely Positive Case
- 3.2.2 Temporal Reasoning (TR) and Temporal Guideline (TG)
- 3.3 Fuzzy Logic
- 3.3.1 Fuzzy Inferences
- 4 System Development
- 4.1 User Interface for Diagnosis of ARF Application
- 5 System Testing and Conclusion
- References
- Applications of Genetic Algorithms
- 18 Optimising Skill Matching in the Service Industry for Large Multi-skilled Workforces
- Abstract
- 1 Introduction
- 2 Skill Matching Problem
- 2.1 Problem Description
- 3 Solution Methods
- 3.1 GA
- 3.1.1 Solution Representation
- 3.1.2 Operators
- 3.1.3 Fitness Function
- 3.1.4 Pseudo Code
- 3.1.5 GA Implementation
- 3.2 Simple Planner Heuristic
- 3.3 Linear Program
- 4 Experiments
- 4.1 Motivation
- 4.2 Experimental Method
- 5 Results
- 5.1 Solution Cost
- 5.2 Skill Variances
- 5.3 Analysis
- 6 Conclusions
- References
- Hybrid Optimization Approach for Multi-Layer FTTH Network Design
- 1 Introduction
- 2 Related Work
- 3 Problem Statement
- 4 Hybrid Optimization Approach
- 4.1 Finding JB Locations
- 4.2 Generating the Duct Layer
- 4.3 Creating the Cable Layer
- 5 Results
- 5.1 Locations of Joint Boxes
- 5.2 Creation of Duct Layer
- 5.3 Generation of Cable Layer
- 6 Conclusion
- References
- 20 A Genetic Algorithm Based Approach for Workforce Upskilling
- Abstract
- 1 Introduction
- 2 Overview of the Skill Optimisation Problem
- 2.1 Overview of Multi-skilled Engineers
- 2.2 Objective and Constraints
- 3 Overview of Genetic Algorithms
- 4 The Proposed GA Based Skill Optimisation System
- 5 Experiments and Results
- 6 Conclusions and Future Work
- References
- Applications of Intelligent Agents and Evolutionary Techniques
- Multi Agent Based Simulation Using Movement Patterns Mined from Video Data
- 1 Introduction
- 2 Previous Work
- 3 Video Data Set
- 4 Pattern Mining Framework
- 4.1 Grid Representation
- 4.2 Movement Patterns
- 5 Simulation Framework
- 6 Evaluation
- 7 Case Study
- 8 Conclusion
- References
- 22 Assembly of Neural Networks Within a Federation of Rational Agents for the Diagnosis of Acute Coronary Syndromes
- Abstract
- 1 Introduction
- 2 Methodology
- 2.1 Analysis and Design of the Multi-agent System
- 2.2 Description of the Cooperation Model
- 2.3 Selection of Assembly Model
- 2.3.1 Description of the Database
- 2.3.2 Training and Neural Network Tests
- 2.3.3 Tests with the Assembly Models
- 3 Results
- 4 Discussion
- 5 Conclusions
- Acknowledgments
- References
- Cluster Analysis of Face Images and Literature Data by Evolutionary Distance Metric Learning
- 1 Introduction
- 2 Evolutionary Distance Metric Learning
- 2.1 Global Distance Metric Learning
- 2.2 Neighborhood Smoothing of Clustering Index
- 2.3 Self-organizing Map
- 2.4 K-Means Clustering with K-Nearest Neighbor Centroids Graph
- 2.5 Evolutionary Distance Metric Learning Framework
- 2.6 DE with Self-Adapting Control Parameters and Generalized Opposition-Based Learning: GOjDE
- 3 Application to Face Recognition
- 3.1 Experimental Settings
- 3.2 Results
- 4 Application to Literature Data
- 4.1 Preprocessing and Settings
- 4.2 Results
- 4.3 Discussion
- 5 Conclusion and Future Work
- References
- AI Applications
- 24 A Novel K-Means Voice Activity Detection Algorithm Using Linear Cross Correlation on the Standard Deviation of Linear Predictive Coding
- Abstract
- 1 Introduction
- 2 Voice Activity Detection (VAD)
- 3 Linear Predictive Coding (LPC)
- 4 Proposed System
- 4.1 Linear Cross Correlation (LCC) Stage
- 4.2 K-Means Clustering Stage
- 4.2.1 Modifications to K--Means
- 5 Methodology
- 6 Experimental Data
- 7 Results
- 8 Conclusion
- 9 Future Work
- Acknowledgements
- References
- Opinionated Explanations for Recommendation Systems
- 1 Introduction
- 2 Opinionated Recommendation
- 2.1 Review Feature Extraction
- 2.2 Sentiment Analysis
- 2.3 Item Feature Mapping
- 2.4 Case Generation: Constructing Item Cases
- 2.5 Case Generation: Constructing User Profiles
- 3 From Opinions to Compelling Explanations
- 3.1 Generating a Basic Explanation Structure
- 3.2 Filtering Compelling Explanations
- 3.3 From Explanations to Ranking
- 4 The Explanation Interface
- 5 Evaluation
- 5.1 Offline Evaluation
- 5.2 Live-User Study
- 6 Conclusions
- References
- The Influence of Virtual Reality on the Perception of Artificial Intelligence Characters in Games
- 1 Motivation
- 2 Background
- 3 Method
- 3.1 Ethical Considerations
- 4 Test-Bed Games
- 4.1 Racing Game
- 4.2 First Person Shooter
- 4.3 Headset and Input Device
- 5 Results
- 6 Conclusion and Future Work
- References
- Short Papers
- 27 Eugene: A Generic Interactive Genetic Algorithm Controller
- Abstract
- 1 Introduction
- 2 Genetic Algorithms
- 3 Interactive Genetic Algorithms
- 4 Eugene
- 5 Evaluation
- 6 Discussion
- 7 Conclusion
- References
- Automatically Geotagging Articles in the Welsh Newspapers Online Collection
- 1 Introduction
- 2 Metadata and Geotagging
- 3 Methods
- 4 Results
- 5 Conclusions
- References
- Contextual Sequential Pattern Mining in Games: Rock, Paper, Scissors, Lizard, Spock
- 1 Introduction
- 2 The Game Interface
- 3 Formal Background
- 4 Discussion
- 4.1 Preliminary Results
- 4.2 Related Work
- References
- On the Way Towards Automated Planning and Budgeting: Combining Fuzzy Planning with CBR Learning Systems
- 1 Issues and Challenges of Planning and Budgeting
- 2 Recent Research
- 2.1 FULPAL---A Fuzzy P&B Approach
- 2.2 CBR Learning Systems
- 3 Combing FULPAL with CBR
- 4 Evaluation and Ongoing Work
- 5 Conclusions and Future Work
- References
- A Comparative Analysis of Ranking Methods in a Hybrid Filter-Wrapper Model for Feature Selection in DNA Microarrays
- 1 Introduction
- 2 Filter Methods for Variable Ranking
- 2.1 Univariate Method: Mutual Information
- 2.2 Multivariate Method: Recursive Feature Elimination
- 3 Wrapper Method: Genetic Algorithm and SVM
- 4 Expermiments and Results
- 5 Conclusion
- References
- 32 A New Content-Based Recommendation Algorithm for Job Recruiting
- Abstract
- 1 Introduction
- 2 The Proposed Algorithm
- 3 Experimental Evaluation
- 4 Conclusion and Future Work
- References
- Mining Fuzzy Time-Interval Patterns in Clinical Databases
- 1 Introduction
- 2 Sequential Patterns Mining with Fuzzy Time-Intervals
- 3 Case Study in Clinical Databases
- 3.1 Breast Cancer Data System
- 3.2 Mining Results
- 3.3 Evaluation
- 4 Conclusion
- References
- A Sense-Think-Act Architecture for Low-Cost Mobile Robotics
- 1 Background and Motivation
- 2 Prototype Robot Platform
- 2.1 Hardware
- 2.2 Implementation
- 3 Testing
- 4 Conclusions and Future Work
- References
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.