AI 2002: Advances in Artificial Intelligence

AI 2002 is the 15th in the series of annual conferences on arti?cial intelligence held in Australia. This conference is the major forum for the presentation of arti?cial intelligence research in Australia, encompassing all aspects of that broad ?eld. It has traditionally attracted signi?cant international participation, as was again the case in 2002. The current volume is based on the proceedings of AI 2002. Full length ver- ons of all submitted papers were refereed by an international program committee, each paper receiving at least two independent reviews. As a result, 62 papers were selected for oral presentation in the conference, and 12 more for poster presentation, out of 117 submissions. One-page abstracts of the posters are - blished in this volume, along with the full papers selected for oral presentation. In addition to the scienti?c track represented here, the conference featured a program of tutorials and workshops, and plenary talks by ?ve invited sp- kers: Peter van Beek (University of Waterloo, Canada), Eric Bonabeau (I- system Corporation, USA), Ming Li (University of California at Santa Barbara), Bernhard Nebel (Albert-Ludwigs-Universit¨ at Freiburg, Germany) and Zoltan Somogyi (University of Melbourne, Australia). It was colocated with a number of related events: an AI Applications Symposium, the 6th Australia-Japan Joint Workshop on Intelligent and Evolutionary Systems, the Australasian Workshop on Computational Logic (AWCL), and the annual conference of the Australasian Association for Logic (AAL).

Natural Language and Information Retrieval.- A Controlled Language to Assist Conversion of Use Case Descriptions into Concept Lattices.- Preferred Document Classification for a Highly Inflectional/Derivational Language.- Experiments in Query Paraphrasing for Information Retrieval.- Knowledge Representation and Reasoning.- Dynamic Decision-Making in Logic Programming and Game Theory.- On a Linear Representation Theory for Quantitative Belief Change.- Trust in Secure Communication Systems - The Concept, Representations, and Reasoning Techniques.- Foundations for a Formalism of Nearness.- Deduction.- Semantic Selection for Resolution in Clause Graphs.- Machine-Checking the Timed Interval Calculus.- Modeling Programs with Unstructured Control Flow for Debugging.- Learning Theory I.- Message Length Formulation of Support Vector Machines for Binary Classification A Preliminary Scheme.- MML Inference of Decision Graphs with Multi-way Joins.- MML Clustering of Continuous-Valued Data Using Gaussian and t Distributions.- Optimizing Kernel-Based Nonlinear Subspace Methods Using Prototype Reduction Schemes.- Agents.- Intention and Rationality for PRS-Like Agents.- Modeling and Simulation for Detecting a Distributed Denial of Service Attack.- Knowledge-Driven Processes Can Be Managed.- Adaptive Multi-agent Decision Making Using Analytical Hierarchy Process.- Intelligent Systems.- Autonomous Planning and Scheduling on the TechSat 21 Mission.- Omni-drive Robot Motion on Curved Paths: The Fastest Path between Two Points Is Not a Straight-Line.- Indexing of Image Databases Using Untrained 4D Holographic Memory Model.- The Flux-Oriented Control of an Induction Machine Utilizing an Online Controller Parameter Adaptation Scheme.- Bayesian Reasoning and Classification.- Modelling the Acquisition of Colour Words.- Bayesian Information Reward.- Prediction of User Preference in Recommendation System Using Associative User Clustering and Bayesian Estimated Value.- Argument Interpretation Using Minimum Message Length.- Evolutionary Algorithms.- Genetic Programming for Classification: An Analysis of Convergence Behaviour.- Lineage and Induction in the Development of Evolved Genotypes for Non-uniform 2D CAs.- Evolution in the Orange Box — A New Approach to the Sphere-Packing Problem in CMAC-Based Neural Networks.- Finding Worst-Case Instances of, and Lower Bounds for, Online Algorithms Using Genetic Algorithms.- Neural Networks I.- An Adaptive Activation Function for Higher Order Neural Networks.- An Adaptive Learning Algorithm Aimed at Improving RBF Network Generalization Ability.- A Neural Network Online Training Algorithm Based on Compound Gradient Vector.- Applications of Wavelet Transform and Artificial Neural Networks to Pattern Recognition for Environmental Monitoring.- Reinforcement Learning.- Adapting Kernels by Variational Approach in SVM.- Learning to Reach the Pareto Optimal Nash Equilibrium as a Team.- Computational Models of the Amygdala and the Orbitofrontal Cortex: A Hierarchical Reinforcement Learning System for Robotic Control.- Constraints and Scheduling.- A General Approach for Building Constraint Languages.- Metric SCSPs: Partial Constraint Satisfaction via Semiring CSPs Augmented with Metrics.- A Hybrid Genetic Algorithm for School Timetabling.- Genetic Scheduling on Minimal Processing Elements in the Grid.- Neural Net Applications I.- Protein Sequences Classification Using Modular RBF Neural Networks.- Feature Extraction and Selection in Tool Condition Monitoring System.- A Robust Meaning Extraction Methodology Using Supervised Neural Networks.- Solving Regression Problems Using Competitive Ensemble Models.- Learning Theory II.- Learning of Finite Unions of Tree Patterns with Internal Structured Variables from Queries.- TreeITL-Mine: Mining Frequent Itemsets Using Pattern Growth, Tid Intersection, and Prefix Tree.- Convergency of Learning Process.- Structured Features from Concept Lattices for Unsupervised Learning and Classification.- Satisfiability Reasoning.- Towards Fewer Parameters for SAT Clause Weighting Algorithms.- An Investigation of Variable Relationships in 3-SAT Problems.- Modelling More Realistic SAT Problems.- A Two Level Local Search for MAX-SAT Problems with Hard and Soft Constraints.- Neural Net Applications II.- Strong Pseudorandom Bit Sequence Generators Using Neural Network Techniques and Their Evaluation for Secure Communications.- Surface Feature Recognition of Wear Debris.- Improved Defect Detection Using Novel Wavelet Feature Extraction Involving Principal Component Analysis and Neural Network Techniques..- Effectiveness for Machine Translation Method Using Inductive Learning on Number Representation.- Effectiveness for Machine Translation Method Using Inductive Learning on Number Representation.- Estimating Episodes of Care Using Linked Medical Claims Data.- Estimating Episodes of Care Using Linked Medical Claims Data.- Fuzzy Reasoning.- Adaptation of a Mamdani Fuzzy Inference System Using Neuro-genetic Approach for Tactical Air Combat Decision Support System.- Optimization of Recurrent NN by GA with Variable Length Genotype.- Neural Networks II and CBR.- Theoretical Foundation for Nonlinear Edge-Preserving Regularized Learning Image Restoration.- The Application of Case Based Reasoning on Q&A System.- Abstracts of Posters.- Development of an Intelligent Tutoring System on Design of Liquid Retaining Structures.- Real-Time Prediction of Water Stage with Artificial Neural Network Approach.- On the Design of Mathematical Concepts.- Consistency of Trust Theories.- An Artificially Intelligent Sports Tipper.- Selecting Semantics for Use with Semantic Pruning of Linear Deductions.- Calibration of Flow and Water Quality Modeling Using Genetic Algorithm.- A Comparison of Machine Learning Approaches for the Automated Classification of Dementia.- A Defeasible Logic of Policy-Based Intention (Extended Abstract).- A Self-Organizing Territorial Approach to Multi-robot Search and Surveillance.- Knowledge-Based Techniques for Constraints Satisfaction in Resource Allocation Problems.- Effective SAT Planning by Speculative Computation.