Embedding-based subsequence matching in time-series databases

• Published in: ACM transactions on database systems Vol. 36; no. 3; pp. 1 - 39
• Main Authors: Papapetrou, Panagiotis, Athitsos, Vassilis, Potamias, Michalis, Kollios, George, Gunopulos, Dimitrios
• Format: Journal Article
• Language: English
• Published: New York, NY Association for Computing Machinery 01.08.2011
• Subjects: Applied sciences; Computer science; control theory; systems; Dynamics; Exact sciences and technology; Information systems. Data bases; Matching; Mathematical analysis; Memory organisation. Data processing; Queries; Software; Vectors (mathematics); Warpage; Warping; Nearest neighbour; Database query; nonmetric spaces; Warping; Theory; Dynamic time warping; Competitiveness; Time series; nearest neighbor retrieval; Algorithms; Query processing; Diagonal matrix; similarity matching; Database; Euclidean space; Embedding methods; Performance; non-Euclidean spaces
• ISSN: 0362-5915; 1557-4644
• DOI: 10.1145/2000824.2000827

We propose an embedding-based framework for subsequence matching in time-series databases that improves the efficiency of processing subsequence matching queries under the Dynamic Time Warping (DTW) distance measure. This framework partially reduces subsequence matching to vector matching, using an embedding that maps each query sequence to a vector and each database time series into a sequence of vectors. The database embedding is computed offline, as a preprocessing step. At runtime, given a query object, an embedding of that object is computed online. Relatively few areas of interest are efficiently identified in the database sequences by comparing the embedding of the query with the database vectors. Those areas of interest are then fully explored using the exact DTW-based subsequence matching algorithm. We apply the proposed framework to define two specific methods. The first method focuses on time-series subsequence matching under unconstrained Dynamic Time Warping. The second method targets subsequence matching under constrained Dynamic Time Warping (cDTW), where warping paths are not allowed to stray too much off the diagonal. In our experiments, good trade-offs between retrieval accuracy and retrieval efficiency are obtained for both methods, and the results are competitive with respect to current state-of-the-art methods.