|
Published Articles >> Table of Contents >> Abstract
International Workshop on Ubiquitous Data Management
pp. 97-104
Finding Periodic Outliers over a Monogenetic Event Stream
Kimio Kuramitsu, Yokohama National University 79-1 Tokiwadai, Hodogayaku, Yokohama 240-8501 JAPAN
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/UDM.2005.9
Send link to a friend
| Abstract |
|
Sensors are active everywhere. Enormous volumes of sensed events are sent over the data streams, while most of applications want to focus on events that would be curious. We propose a technique for mining periodicities and predicting its outliers from the stream. The key to our technique is a simple periodic pattern {\Delta x}t, derived from delta-time mining, or SUP(t, t+{\Delta x}t). We provide efficient algorithms for finding the highest support {\Delta x}t on a small and resource-limited sensor device. Our experiments will compare memory efficiency and accuracy, on a variety of event patterns, monogenesis, polygenesis, and semi-random.
|
 Additional Information
|
Citation:
Kimio Kuramitsu,
"Finding Periodic Outliers over a Monogenetic Event Stream,"
udm,
pp. 97-104,
International Workshop on Ubiquitous Data Management,
2005
|
|
