Advances in Artificial Intelligence: 21st Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2008, Windsor, Canada, May 28-30, 2008. ProceedingsThis book constitutes the refereed proceedings of the 21st Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2008, held in Windsor, Canada, in May 2008. The 30 revised full papers presented together with 5 revised short papers were carefully reviewed and selected from 75 submissions. The papers present original high-quality research in all areas of Artificial Intelligence and apply historical AI techniques to modern problem domains as well as recent techniques to historical problem settings. |
Contents
Local Decision Bagging of Binary Neural Classifiers | 1 |
Assessing the Impact of Changing Environments on Classifier Performance | 13 |
Polarizing Movie Blogs | 25 |
Some Simplified Forms of Reasoning with DistanceBased Entailments | 36 |
A BeliefTheoretic Reputation Estimation Model for Multicontext Communities | 48 |
A Frequency MiningBased Algorithm for Reranking Web Search Engine Retrievals | 60 |
Multiagent Framework for a Virtual Enterprise of DemandResponsive Transportation | 66 |
Use of Fuzzy Histograms to Model the Spatial Distribution of Objects in CaseBased Reasoning | 72 |
Selective Sampling for Classification | 191 |
Full Border Identification for Reduction of Training Sets | 203 |
Choosing Best Algorithm Combinations for Speech Processing Tasks in Machine Learning Using MARF | 216 |
Predicting User Preferences Via SimilarityBased Clustering | 222 |
Mathematically Clinching a Playoff Spot in the NHL and the Effect of Scoring Systems | 234 |
An Intelligent Automatic Face Contour Prediction System | 246 |
Word Clustering with Validity Indices | 259 |
The Role of Nominalizations in Prepositional Phrase Attachment in GENIA | 271 |
Aspects of Inconsistency Resolution in Modular Ontologies | 84 |
Fast Markov Blanket Discovery Algorithm Via Local Learning within Single Pass | 96 |
Finding Topics in Email Using Formal Concept Analysis and Fuzzy Membership Functions | 108 |
Recognizing Biomedical Named Entities in Chinese Research Abstracts | 114 |
PointBased Planning for Predictive State Representations | 126 |
Comparison of Pleomorphic and Structural Features Used for Breast Cancer Malignancy Classification | 138 |
Towards a Faster Inference Algorithm in Multiply Sectioned Bayesian Networks | 150 |
Using Dependence Diagrams to Summarize Decision Rule Sets | 163 |
A Fast Computation of Interclass Overlap Measures Using Prototype Reduction Schemes | 173 |
A Case Study in Child Vehicle Safety Simulation | 185 |
A Statistical Model for Topic Segmentation and Clustering | 283 |
Inductive Transfer between Multiple Tasks Having Multiple Outputs | 296 |
Using Unsupervised Learning for Network Alert Correlation | 308 |
Verb Categories in Learning Polarity and Strength of Opinions | 320 |
A Stochastic PointBased Algorithm for POMDPs | 332 |
Semisupervised Selftraining for Sentence Subjectivity Classification | 344 |
A Novel Approach for Social Behavior Analysis of the Blogosphere | 356 |
Seller Bidding in a TrustBased Incentive Mechanism for Dynamic EMarketplaces | 368 |
380 | |
Other editions - View all
Common terms and phrases
accuracy agent alerts analysis approach Artificial Intelligence assigned attributes bagging Bayesian network Berlin Heidelberg 2008 biometric blog border buyers Canadian AI 2008 clustering complexity Computer concept consider constraint constraint programming context corpus correlation csMTL data points data set decision tree defined denoted dependence diagram description logic distance distribution domain emails error rate evaluation external messages extracted feature extraction fuzzy heuristics identified images inductive transfer input interface IPC-MB iteration label learning algorithms linkage LNAI machine learning Markov Markov blanket measure method metric modular ontology module MSBN named entity recognition neural networks node ontology optimal output parameters patterns performance point-based POMDP prediction vectors preferences problem Proceedings proposed query represent representation reputation sample Section segmentation selection self-training sellers semantic sentences similar subnets supervised learning Table task topic training set underlying classifier unlabeled variables verb words