Similarity searching for multi-attribute sequences

T. Kahveci1, A. Singh1, A. Gurel2
1Department of Computer Science, University of California, Santa Barbara, CA, USA
2Department of Mathematics, University of California, Santa Barbara, CA, USA

Tóm tắt

We investigate the problem of searching similar multiattribute time sequences. Such sequences arise naturally in a number of medical, financial, video, weather forecast, and stock market databases where more than one attribute is of interest at a time instant. We first solve the simple case in which the distance is defined as the Euclidean distance. Later we extend it to shift and scale invariance. We formulate a new symmetric scale and shift invariant notion of distance for such sequences. We also propose a new index structure that transforms the data sequences and clusters them according to their shiftings and scalings. This clustering improves the efficiency considerably. According to our experiments with real and synthetic datasets, the index structure's performance is 5 to 45 times better than competing techniques, the exact speedup based on other optimizations such as caching and replication.

Từ khóa

#Weather forecasting #Databases #Discrete Fourier transforms #Stock markets #Economic forecasting #Euclidean distance #Wavelet transforms #Computer science #Mathematics #Indexes

Tài liệu tham khảo

kahveci, 2001, An efficient index structure for string databases, VLDB, 351 10.1109/ICDE.2001.914838 kahveci, 2001, Technical Report lee, 2000, Similarity search for multidimensional data sequences, ICDE 10.1109/ICDE.2000.839385 10.1109/ICDE.1999.754957 10.1145/253260.253264 rafiei, 1998, Efficient retrieval of similar time sequences using DFT, FODO seeger, 1993, Reading a set of disk pages, VLDB, 592 shahabi, 2000, TSA-tree: A wavelet-based approach to improve the efficieny of multi-level surprise and trend queries, SSDBM chan, 1999, Efficient time series matching by wavelets, ICDE 10.1145/93597.98741 das, 1997, Finding similar time series, PKDD, 88 10.1145/303976.304000 goldin, 1995, On similarity queries for time-series data: Constraint specification and implementation, CP, 137 10.1145/191839.191925 agrawal, 1995, Fast similarity search in the presence of noise, scaling, and translation in time-series databases, VLDB agrawal, 1993, Efficient similarity search in sequence databases, FODO 10.1145/971697.602266 10.1109/ICDE.2002.994784 white, 1996, Similarity indexing: Algorithms and performance, SPIE Storage and Retrieval for Image and Video Databases, 10.1117/12.234810