| | |
Summary: Towards Faster Activity Search Using Embeddingbased
Subsequence Matching
Panagiotis Papapetrou 1 , Paul Doliotis 2 , and Vassilis Athitsos 2
1 Computer Science Department, Boston University, USA
2 Computer Science and Engineering Department, University of Texas at Arlington, USA
ABSTRACT
Event search is the problem of identifying events or activity of in
terest in a large database storing long sequences of activity. In this
paper, our topic is the problem of identifying activities of interest
in databases where such activities are represented as time series. In
the typical setup, the user presents a query that represents an activ
ity of interest, and the system needs to retrieve the most similar ac
tivities stored in the database. We focus on the case where the best
database matches are not segmented a priori: the database contains
representations of long, continuous activity, that occurs throughout
relatively extensive periods of time, and, given a query, there are
no constraints as to when exactly a database match starts and ends
within the longer activity pattern where it is contained. Using the
popular DTW measure, the best database matches can be found us
ing dynamic programming. However, retrieval time is linear to the
|
