Pattern Discovery in Time-Ordered Data

CONRAD, GREGORY N. ; BRITANIK, JOHN M. ; DELAND, SHARON M. ; JENKIN, CHRISTINA L.

Sandia National Laboratories

关键词: Pattern Recognition;    Training;    99 General And Miscellaneous//Mathematics, Computing, And Information Science;    Computer Networks;    Robots;   

DOI  :  10.2172/793315
RP-ID  :  SAND2002-0245
RP-ID  :  AC04-94AL85000
RP-ID  :  793315

美国|英语

来源: UNT Digital Library

【 摘 要 】

This report describes the results of a Laboratory-Directed Research and Development project on techniques for pattern discovery in discrete event time series data. In this project, we explored two different aspects of the pattern matching/discovery problem. The first aspect studied was the use of Dynamic Time Warping for pattern matching in continuous data. In essence, DTW is a technique for aligning time series along the time axis to optimize the similarity measure. The second aspect studied was techniques for discovering patterns in discrete event data. We developed a pattern discovery tool based on adaptations of the A-priori and GSP (Generalized Sequential Pattern mining) algorithms. We then used the tool on three different application areas--unattended monitoring system data from a storage magazine, computer network intrusion detection, and analysis of robot training data.