Ellis / Allen / Tuson Applications and Innovations in Intelligent Systems XIV

Proceedings of AI-2006, the Twenty-sixth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence
1. Auflage 2010
ISBN: 978-1-84628-666-7
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Wasserzeichen (»Systemvoraussetzungen)

E-Book, Englisch, 243 Seiten

The papers in this volume are the refereed application papers presented at AI-2006, the Twenty-sixth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, held in Cambridge in December 2006. The papers present new and innovative developments in the field. The series serves as a key reference as to how AI technology has enabled organisations to solve complex problems and gain significant business benefit.

Autoren/Hrsg.

Ellis, Richard

Allen, Tony

Tuson, Andrew

Inhaltsverzeichnis

1;APPLICATION PROGRAMME CHAIR'S INTRODUCTION;5
2;ACKNOWLEDGEMENTS;6
3;APPLICATION EXECUTIVE PROGRAMME COMMITTEE;6
4;APPLICATION PROGRAMME COMMITTEE;7
5;Table of contents
;8
6;BEST APPLICATION PAPER;11
6.1;Managing Restaurant Tables using Constraints;13
6.1.1;1. Introduction;13
6.1.2;2. Restaurant Table Management;14
6.1.3;3. Constraint Programming;15
6.1.4;4. Modelling the static table management problem;16
6.1.5;5. Flexibility and Optimisation;18
6.1.6;6. Minimising Disruption;20
6.1.7;7. The Integrated Table Management Adviser;20
6.1.8;8. Conclusions and Future Work;25
6.1.9;Acknowledgements;26
6.1.10;References;26
7;SESSION 1: DATA MINING AND BAYESIAN NETWORKS
;28
7.1;Use of Data Mining Techniques to Model Crime Scene Investigator Performance
;29
7.1.1;1. Introduction;29
7.1.2;2. Current CSI Activity and Assessment
;30
7.1.3;3. Methodology;31
7.1.3.1;3.1 CRISP-OM;32
7.1.4;4. Data Manipulation;34
7.1.5;5. Results;36
7.1.5.1;5.1 CSI Personal Predictions;39
7.1.6;6. Conclusion;40
7.1.7;References;41
7.2;Analyzing Collaborative Problem Solving with Bayesian Networks
;43
7.2.1;1 Introduction;43
7.2.2;2 Bayesian networks in teaching and learning;44
7.2.3;3 Collaborative problem solving in DomoSim-TPC;45
7.2.4;4 A Bayesian network to model collaborative work;48
7.2.5;5 Data analysis;49
7.2.6;6 Conclusions;52
7.2.7;Acknowledgments;52
7.2.8;References;53
7.3;The Integration of Heterogeneous Biological Data using Bayesian Networks
;54
7.3.1;1 Introduction;54
7.3.2;2 Bayesian Networks Models;56
7.3.2.1;2.1 Modification of Bayesian Network through Informative Prior Knowledge
;58
7.3.2.2;2.2 Related Work on Bayesian Networks;59
7.3.3;3 Integrating Heterogenous Sources of Data;59
7.3.3.1;3.1 Genomic Data (Microarray Data);60
7.3.3.2;3.2 Proteomic data (2DE Gels);61
7.3.3.3;3.3 Expert opinion and diabetes domain knowledge;61
7.3.4;4 Experimental Procedure;62
7.3.4.1;4.1 Data preprocessing;62
7.3.4.2;4.2 Results;63
7.3.5;5 Conclusions;66
7.3.6;6 Acknowledgements;66
7.3.7;References;66
7.4;Automatic Species Identification of Live Moths;68
7.4.1;1. Introduction;68
7.4.2;2. Recent Work on Automatic Species Identification;69
7.4.3;3. The Macrolepidoptera Image Collection;71
7.4.4;4. Extracting Features from the Images;71
7.4.5;5. Results;74
7.4.6;6. Conclusion;79
7.4.7;Acknowledgements;81
7.4.8;References;81
8;SESSION 2: GENETIC ALGORITHMS ANDOPTIMISATION TECHNIQUES
;82
8.1;Estimating Photometric Redshifts Using Genetic Algorithms
;83
8.1.1;1. INTRODUCTION;83
8.1.1.1;1.1 Spectroscopy & Photometry;83
8.1.1.2;1.2 Contribution;84
8.1.2;2. Extragalactic Astronomy;84
8.1.2.1;2.1 What is redshift?;84
8.1.2.2;2.2 Finding high-redshift objects;84
8.1.2.3;2.3 Photometric Redshift;85
8.1.2.4;2.4 Deep Field Surveys;86
8.1.3;3. Preparation of the data to be mined;86
8.1.4;4. A Genetic Algorithm for estimating redshifts;87
8.1.4.1;4.1 Individual Representation;87
8.1.4.2;4.2 SequentialCovering;88
8.1.4.3;4.3 Fitness Function;89
8.1.4.4;4.4 Genetic Operators (Crossover and Mutation);90
8.1.4.4.1;4.4.1 Crossover;90
8.1.4.5;4.5 Selection Method;91
8.1.5;5. Computational Results;91
8.1.6;6. Conclusion and Future Research;93
8.1.7;7. References;93
8.2;Non-linear Total Energy Optimisation of a Fleet of Power Plants
;96
8.2.1;1. Introduction;96
8.2.2;2. Approaches to Mixed Integer Optimisation;97
8.2.3;3. Fast Simulation of Power Plants;98
8.2.4;4. Simulated Annealing;99
8.2.5;5. Power Plant Optimisation: A Case Study;100
8.2.6;6. Conclusion;103
8.2.7;References;104
8.3;Optimal Transceivers Placement in an Optical Communication Broadband Network Using Genetic Algorithms
;105
8.3.1;1. Introduction;105
8.3.2;2. Problem Description;106
8.3.3;3. Method Proposed;107
8.3.4;4. Description of the Genetic Algorithm.;108
8.3.5;5. Simulations and Results;110
8.3.6;5. Conclusions;112
8.3.7;Acknowledgment;114
8.3.8;References;114
8.4;SASS APPLIED TO OPTIMUM WORK ROLL PROFILE SELECTION IN THE HOT ROLLING OF WIDE STEEL
;115
8.4.1;1. Introduction;115
8.4.2;2. Hot RoIling of Wide Strip;116
8.4.2.1;2.1 Mill Train;116
8.4.2.2;2.2 Strip Quality;117
8.4.2.3;2.3 Initially Ground Work Roll Profiles;119
8.4.2.4;2.4 Roll Profile Specification;120
8.4.3;3. Optimisation of profiles;120
8.4.3.1;3.1 The Fitness Function;121
8.4.3.2;3.2 Self-Adaptive Stepsize Search;121
8.4.4;4. Experimental Results;123
8.4.5;5. Conclusion;124
8.4.6;References;125
9;SESSION 3: AGENTS AND SEMANTIC WEB
;126
9.1;Agents in Safety Related Systems Including Ubiquitous Networks
;127
9.1.1;1. Introduction;127
9.1.2;2. Overview;129
9.1.3;3. Handling Safety;133
9.1.4;4. Intelligence;135
9.1.5;5. Matching lEe 61508 and ADM;136
9.1.6;6. Demonstrator;138
9.1.7;7. Conclusions;139
9.1.8;References;140
9.2;Using Semantic Web technologies to bridge the Language Gap between Academia and Industry in the Construction Sector
;141
9.2.1;1. Introduction;141
9.2.2;2. Motivation and initial requirements;142
9.2.3;3. A Web portal with a keyword-based search engine;143
9.2.4;4. A SW portal with an ontology-based search engine;147
9.2.5;5. Empirical results: comparing both search engines;152
9.2.6;6. Conclusions;153
9.2.7;References;154
9.2.8;Acknowledgements;154
9.3;Ontology based CBR with jCOLIBRI;155
9.3.1;1 Introduction;155
9.3.2;2 The jCOLIBRI Architecture;156
9.3.3;3 Ontology based CBR;157
9.3.3.1;3.1 Ontologies as the CBR system vocabulary;158
9.3.3.2;3.2 Case Retrieval using Ontologies;159
9.3.3.3;3.3 Case Adaptation based on Ontologies;161
9.3.4;4 KI Case Representation and Retrieval in jCOLIBRI
;162
9.3.5;5 Ontology-based Adaptation in jCOLIBRI;165
9.3.6;6 Conclusions;167
9.3.7;References;168
9.4;Domain Dependent Distributed Models for Railway Scheduling;169
9.4.1;1 Introduction.;169
9.4.2;2 Distributed CSPs.;171
9.4.2.1;2.1 Definitions.;171
9.4.2.2;2.2 The Distributed Model.;172
9.4.3;3 Railway Scheduling Problem.;173
9.4.3.1;3.1 Constraints in the Railway Scheduling Problem;174
9.4.4;4 Partition Proposals;177
9.4.4.1;4.1 Domain Independent: Partition Proposall.;177
9.4.4.2;4.2 Domain Dependent: Partition Proposal 2.;177
9.4.4.3;4.3 Domain Dependent: Partition Proposal 3.;178
9.4.5;5 Evaluation.;179
9.4.5.1;Random problems.;179
9.4.5.2;Benchmark problems.;179
9.4.6;6 Conclusions.;180
9.4.7;References;182
10;SESSION 5: NATURAL LANGUAGE
;184
10.1;Bringing Chatbots into Education: Towards Natural Language Negotiation of Open Learner Models
;185
10.1.1;1 Background;185
10.1.1.1;1.1 Chatbots;185
10.1.1.2;1.2 Intelligent Tutoring Systems;187
10.1.1.3;1.3 Learner Modelling and Open Learner Modelling;187
10.1.1.4;1.4 Intelligent Tutoring Systems that use Natural Language;188
10.1.2;2 Using a Chathot for Negotiated Learner Modelling
;189
10.1.2.1;2.1 The Choice of Chatbot;189
10.1.3;3 Wizard-of-Oz study;190
10.1.3.1;3.1 The Wizard-of-Oz Paradigm;190
10.1.3.2;3.2 The Learner Modelling System;190
10.1.3.3;3.3 Experimental setup;191
10.1.3.4;3.4 Outcomes;193
10.1.4;4 Lessons for implementation;194
10.1.4.1;4.1 System Requirements;194
10.1.4.2;4.2 Areas for Further Research;195
10.1.5;5 Conclusion;196
10.1.6;Acknowledgements;196
10.1.7;References;196
10.2;Adding question answering to an e-tutor for programming languages
;199
10.2.1;1. Introduction;199
10.2.2;2. Related Work;200
10.2.3;3. IVC Architecture
;203
10.2.3.1;3.1 Challenges in teaching Verilog;203
10.2.3.2;3.2 Constructingthe ontology;203
10.2.3.3;3.3 Cross-linkingthe different ontologies;203
10.2.3.4;3.4 Shallow question answering;204
10.2.3.5;3.5 User Concept Model;204
10.2.3.6;3.6 User interface;205
10.2.4;4. Results;206
10.2.4.1;4.1 Research Questions;206
10.2.4.2;4.2 Methodology;207
10.2.4.3;4.3 Question Answering Opportunities;207
10.2.4.4;4.4 Average Activity Index Results;209
10.2.4.5;4.5 Tracking User Activity;209
10.2.4.6;4.6 Results from student revision;210
10.2.5;5. Conclusions;211
10.2.6;References;212
10.3;Speech-Enabled Interfaces for Travel Information Systems with Large Grammars
;213
10.3.1;1. Introduction;213
10.3.2;2. Large grammar issues in a London bus travel application
;214
10.3.3;3. First letter based grammar reduction system;215
10.3.3.1;3.1 Dividing a large grammar file into many small files;216
10.3.3.2;3.2 Confusion matrix for first letter recognition;216
10.3.3.3;3.3 Large & first letter grammar system comparison;219
10.3.3.4;3.4 Automatic first phoneme recognition system;220
10.3.4;4. Last word based recognition system;221
10.3.4.1;4.1 The system design;222
10.3.4.2;4.2 The experimental results;223
10.3.5;5. Conclusion and discussion;225
10.3.6;References;226
11;SHORT PAPERS;228
11.1;Adoption of New Technologies in a Highly Uncertain Environment: The Case of Egyptian Public Banks;229
11.1.1;1. Introduction;229
11.1.2;2. Current Dominant Technology Adoption Models;230
11.1.3;3. Case: Technology Adoption in Egyptian Banks;230
11.1.4;4. Discussion and Conclusion;232
11.1.5;5. References;232
11.2;RoboCup 3D Soccer Simulation Server: A Progressing Testbed for AI Researchers
;234
11.2.1;1. Introduction;234
11.2.2;2. Characteristics of RoboCup 3D Soccer Server;235
11.2.3;3. Inside of RoboCup 3D Soccer Server;235
11.2.3.1;3.1 World and Object Representation;235
11.2.3.2;3.2 Scene Graph;236
11.2.4;4. SPADES;236
11.2.4.1;4.1 Component Organization;237
11.2.4.2;4.2 Sense-Think-Act;237
11.2.5;5. Putting All Together: A Complete Simulation;237
11.2.6;6. Conclusion;238
11.2.7;References;238
11.3;Review of Current Crime Prediction Techniques;239
11.3.1;1. Introduction;239
11.3.2;2. Crime Facts;240
11.3.2.1;2.1 Crime Recording Process;240
11.3.2.2;2.2 Environmental Criminology;240
11.3.3;3. Current Crime and Offending Prediction Techniques;240
11.3.3.1;3.1 Statistical Methods;240
11.3.3.2;3.2 Miscellaneous Methods;241
11.3.3.3;3.3 Geographical Information System Methods;241
11.3.4;4. Discussion;242
11.3.5;References;242
11.4;Data Assimilation of a Biological Model Using Genetic Algorithms
;244
11.4.1;1. Introduction;244
11.4.2;2. Mathematical Model of the Problem;245
11.4.3;3. Experimental Setup;246
11.4.4;4. Numerical Results and Discussions;247
11.4.5;5. Conclusions and Future Scope;247
11.4.6;6. Acknowledgements;248
11.4.7;References;248
12;AUTHOR INDEX;249