System and method for learning models from scarce and skewed...

Details System and method for learning models from scarce and skewed... System and method for learning models from scarce and skewed...

2006-08-18

2009-12-08

Holmes, Michael B (Department: 2129)

Data processing: artificial intelligence

Knowledge processing system

Knowledge representation and reasoning technique

Reexamination Certificate

active

07630950

ABSTRACT:
A system and method for learning models from scarce and/or skewed training data includes partitioning a data stream into a sequence of time windows. A most likely current class distribution to classify portions of the data stream is determined based on observing training data in a current time window and based on concept drift probability patterns using historical information.

REFERENCES:
patent: 5727124 (1998-03-01), Lee et al.
patent: 5950158 (1999-09-01), Wang
patent: 5963902 (1999-10-01), Wang
patent: 6735566 (2004-05-01), Brand
patent: 7398268 (2008-07-01), Kim et al.
patent: 7548847 (2009-06-01), Acero et al.
patent: 7558809 (2009-07-01), Radhakrishnan et al.
patent: 7565369 (2009-07-01), Fan et al.
RUSBoost: Improving classification performance when training data is skewed Seiffert, C.; Khoshgoftaar, T.M.; Van Hulse, J.; Napolitano, A.; Pattern Recognition, 2008. ICPR 2008. 19th International Conference on Dec. 8-11, 2008 pp. 1-4 Digital Object Identifier 10.1109/ICPR.2008.4761297.
Hulten et al., “Mining Time-changing Data Streams; in SIGKDD” ACM Press, pp. 97-106, San Francisco, CA 2001.
Wang et al.,“Mining concept-driven data streams using ensemble classifiers”, in SIGKDD, 2003; 10 pages.

Affiliated with

Also associated with

Rating

System and method for learning models from scarce and skewed... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System and method for learning models from scarce and skewed..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for learning models from scarce and skewed... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4121073