FSMBO: Fast Time Series Similarity Matching Based on Bit Operation

In many domains, such as meteorology, space physics, geography, multimedia, and economics, there are a lot of time series data. People often use similarity matching to deal with time series data in practical application. DTW (Dynamic Time Warping) can provide the stretch ability along the time axis. Therefore, it becomes one of several popular similarity matching algorithms. But DTW incurs a heavy computation cost. Although several improved methods of DTW have been proposed in some literatures, it still can not meet the actual needs. This paper proposes FSMBO (Fast time series Similarity Matching based on Bit Operation). FSMBO algorithm efficiently prunes a significant number of the matching candidates, which leads to a direct reduction in the matching cost. Experiments reveal that FSMBO is significantly faster than the popular methods.

[1]  Katsushi Ikeuchi,et al.  Automatic modeling of a 3D city map from real-world video , 1999, MULTIMEDIA '99.

[2]  Hiroshi Wakuya,et al.  Time series prediction by a neural network model based on bi-directional computation style: A study on generalization performance with the computer-generated time series "Data Set D" , 2003, Systems and Computers in Japan.

[3]  Christos Faloutsos,et al.  Efficient Similarity Search In Sequence Databases , 1993, FODO.

[4]  Christos Faloutsos,et al.  FTW: fast similarity search under the time warping distance , 2005, PODS.

[5]  Jyh-Shing Roger Jang,et al.  Hierarchical filtering method for content-based music retrieval via acoustic input , 2001, MULTIMEDIA '01.

[6]  Clu-istos Foutsos,et al.  Fast subsequence matching in time-series databases , 1994, SIGMOD '94.

[7]  Eamonn J. Keogh,et al.  Locally adaptive dimensionality reduction for indexing large time series databases , 2001, SIGMOD '01.

[8]  G. W. Hughes,et al.  Minimum Prediction Residual Principle Applied to Speech Recognition , 1975 .

[9]  Donald J. Berndt,et al.  Finding Patterns in Time Series: A Dynamic Programming Approach , 1996, Advances in Knowledge Discovery and Data Mining.

[10]  Kyuseok Shim,et al.  Fast Similarity Search in the Presence of Noise, Scaling, and Translation in Time-Series Databases , 1995, VLDB.

[11]  Satoshi Suzuki,et al.  Memory-Based Forecasting for Weather Image Patterns , 2000, AAAI/IAAI.

[12]  David W. Mount,et al.  Bioinformatics - sequence and genome analysis (2. ed.) , 2004 .

[13]  Jignesh M. Patel,et al.  An efficient and accurate method for evaluating time series similarity , 2007, SIGMOD '07.

[14]  Nguyen Quoc Viet Hung,et al.  Combining SAX and Piecewise Linear Approximation to Improve Similarity Search on Financial Time Series , 2007, 2007 International Symposium on Information Technology Convergence (ISITC 2007).

[15]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[16]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.