Predicting the Future: AI Approaches to Time-Series Problems
Papers from the AAAI Workshop
Andrea Danyluk, Program Chair
Technical Report WS-98-07 published by The AAAI Press, Menlo Park, California
This technical report is also available in book and CD format.
Please Note: Abstracts are linked to individual titles, and will appear in a separate browser window. Full-text versions of the papers are linked to the abstract text. Access to full text may be restricted to AAAI members. PDF file sizes may be large!
Contents
Preface / 1
Andrea Danyluk, Tom Fawcett, and Foster Provost
Modeling Periodic Functions for Time Series Analysis / 1
Anish Biswas (University of Tulsa)
Predicting Sequences of User Actions / 5
Brian D. Davison and Haym Hirsh (Rutgers University)
Automated Design of User Profiling Systems for Fraud Detection / 13
Tom Fawcett and Foster Provost (Bell Atlantic Science and Technology)
Early Prediction of Electric Power System Blackouts by Temporal Machine Learning / 21
P. Geurts and L. Wehenkel (University of Liege)
Learning in Time Ordered Domains with Hidden Changes in Context / 29
Michael Harries (University of NSW), Kim Horn (RMB Australia), and Claude Sammut (University of NSW)
Heterogeneous Time Series Learning for Crisis Monitoring / 34
William Hsu, Nathan D. Gettings, Victoria E. Lease, Yu Pan, and
David C. Wilkins (University of Illinois at Urbana-Champaign)
A New Mixture Model for Concept Learning from Time Series / 42
William H. Hsu and Sylvian R. Ray (University of Illinois at Urbana-Champaign)
An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification, Clustering and Relevance Feedback / 44
Eamonn J. Keogh and Michael J. Pazzani (University of California, Irvine)
A Probabilistic Approach to Fast Pattern Matching in Time Series Databases / 52
Eamonn Keogh and Padhraic Smyth (University of California, Irvine)
Filtering Techniques for Rapid User Classification / 58
Terran Lane (Purdue University)
Approaches to Online Learning and Concept Drift for
User Identification in Computer Security / 64
Terran Lane and Carla Brodley (Purdue University)
Predicting Resource Usages with Incomplete Information / 71
Jung-Jin Lee and Robert McCartney (University of Connecticut)
Discovering Rules for Clustering and Predicting Asynchronous Events / 73
Tim Oates, David Jensen, and Paul R. Cohen (University of Massachusetts at Amherst)
Pattern Discovery in Temporal Databases: Some Recent Results / 80
Alexander Tuzhilin (New York University)
Learning to Predict Rare Events in Categorical Time-Series Data / 83
Gary M. Weiss and Haym Hirsh (Rutgers University)
A General Paradigm for Applying Machine Learning in
Automated Manufacturing Processes / 91
Wei Zhang and Rod Tjoelker (The Boeing Company)
AAAI Digital Library
AAAI relies on your generous support through membership and donations. If you find these resources useful, we would be grateful for your support.