Meaningful Subsequence Matching under Time Warping Distance for Data Stream

Authors:
Vit Niennattrakul;Chotirat Ann Ratanamahatana
Affiliations:
Department of Computer Engineering, Chulalongkorn University, Bangkok, Thailand 10330;Department of Computer Engineering, Chulalongkorn University, Bangkok, Thailand 10330
Venue:
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Year:
2009

Citing 5
Cited 1

Data mining: concepts and techniques

Data mining: concepts and techniques
Exact indexing of dynamic time warping

Knowledge and Information Systems
Detecting time series motifs under uniform scaling

Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Approximate embedding-based subsequence matching of time series

Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Scaling and time warping in time series querying

The VLDB Journal — The International Journal on Very Large Data Bases

Similar subsequence search in time series databases

DEXA'11 Proceedings of the 22nd international conference on Database and expert systems applications - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Since the era of data explosion, research on mining data stream has become more and more active, particularly focusing on improving time and space complexity in similarity subsequence matching problems for data stream. Recently, SPRING algorithm and its variance have been proposed to solve the subsequence matching problem under time warping distance. Unfortunately, these algorithms produce meaningless results since no normalization is taken into account before distance calculation. In this work, we propose a novel subsequence matching algorithm which fully supports global constraint, uniform scaling, and normalization called MSM (Meaningful Subsequence Matching). As expected, our MSM algorithm is much faster and much more accurate than the current existing algorithms in terms of computational cost and accuracy by a very large margin.