Keogh, E. and Ratanamahatana, A. N. (2004). Exact indexing of dynamic time warping. Knowledge and Information Systems. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Efficient Storage, Retrieval and Indexing of Time Series Data - Chortaras (Correct)
....that the method performs much better than the linear scanning method and as expected its performance increases as the lengths of the sequences increase. Another indexing technique for dynamic time warping, that significantly improves the performance of the previous method, is presented in [16]. Its key feature is that it develops a much tighter lower bound for the time warping distance, thus the index re turns much less false alarms. The experimental comparison of the method with data sets from several application fields demonstrated its superiority over all competitive ap proaches. ....
....the index re turns much less false alarms. The experimental comparison of the method with data sets from several application fields demonstrated its superiority over all competitive ap proaches. In particular, the pruning power of the index is on average 6 times higher that that of the index in [16]. The main limitations of the method are that the sizes of the compared sequences must be the same, and that indexing is possible only if the dynamic time warping algorithm is constrained to work within a limited path. The main difference of these techniques with our application is that we want ....
E. Keogh. Exact indexing of dynamic time warping. In Proceedings of the 28th Confirence, Hong Kong, China, 2002.
Query by Humming: a Time Series Database Approach - Zhu, Shasha (2003) (3 citations) (Correct)
....this technique by allowing transformations, including shifting, scaling and moving average, on the time series before similarity queries. In addition to DFT [2, 26, 35] Discrete Wavelet Transform (DWT) 7, 31, 24] Singular Value Decomposition (SVD) 17] Piecewise Aggregate Approximation (PAA)[32, 14] and Adaptive Piecewise Constant Approximation [15] approaches have also been proposed for similarity searching. Allowing Dynamic Time Warping (DTW) in time series similarity searching is very critical for a query by humming system. A point by point distance measure between time series is very ....
....two techniques to speed up DTW in a pipeline fashion. The rst technique is to use FastMap to index time series with the DTW distance measure. But this technique might result in false negatives. The second is a global lower bounding technique for ltering out unlikely matches. In recentwork, Keogh [14] proposed a technique for the exact indexing of DTW that guarantees no false negatives. 2.1 Our contributions In this paper, weinvestigate the problem of indexing very large music databases, which allows ecient and e ective query byhumming. Our strategy and contributions are as follows. # We ....
[Article contains additional citation context not shown here]
E. J. Keogh. Exact indexing of dynamic time warping. In VLDB 2002.
Indexing Multi-Dimensional Time-Series with.. - Vlachos.. (2003) (3 citations) Self-citation (Keogh) (Correct)
....length of this subsequence [6] In [20] an internal memory index for the LCSS has been proposed. It also demonstrated that while the LCSS presents similar advantages to DTW, it does not share its volatile performance in the presence of outliers. Closest in spirit to our approach, is the work of [10] which, however, only addresses 1D time series. The author uses constrained DTW as the distance function, and surrounds the possible matching regions by a modified version of a Piecewise Approximation, which is later stored as equi length MBRs in an R tree. However, by using DTW, such an approach ....
....a close match to our query, as early as possible. A fast pre filtering step is employed that eliminates the majority of distant matches. Only for some qualified sequences will we execute the costly (but accurate) quadratic time algorithm. This philosophy has also been successfully used in [21, 10]. There are certain preprocessing steps that we follow: 1. The trajectories are segmented into MBRs, which are stored in an Rtree T. 2. Given a query Q, we discover the areas of possible matching by constructing its Minimum Bounding Envelope (MBEQ ) 3. MBEQ is decomposed into MBRs that are ....
[Article contains additional citation context not shown here]
E. Keogh. Exact indexing of dynamic time warping. In Proc. of VLDB, 2002.
Musical Retrieval In P2p Networks Under The - Warping Distance Ioannis (Correct)
No context found.
Keogh, E. and Ratanamahatana, A. N. (2004). Exact indexing of dynamic time warping. Knowledge and Information Systems.
Defending Against Low-rate TCP Attacks: Dynamic Detection and .. - Haibin Sun John (2004) (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In Proc. of the 28th VLDB Conference, China, Aug. 2002.
Simultaneous Localization and Recognition of Dynamic.. - Alon, Athitsos, Yuan.. (2005) (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In International Conference on Very Large Data Bases, pages 406--417, 2002.
Query-Sensitive Embeddings - Athitsos, Hadjieleftheriou, Kollios, .. (2005) (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In VLDB, pages 406--417, 2002.
Simultaneous Localization and Recognition of Dynamic Hand Gestures - Alon, al. (2005) (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In 28th International Conference on Very Large Data Bases, pages 406--417, 2002.
Simultaneous Localization and Recognition of Dynamic Hand Gestures - Alon, al. (2005) (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In 28th International Conference on Very Large Data Bases, pages 406--417, 2002.
Robust Tracking of Human Motion - Buzan (2004) (Correct)
No context found.
Eamonn Keogh. "Exact Indexing of Dynamic Time Warping", in Proceedings of the 28 Very Large Data Bases Conference, pages 406-417, Hong Kong, China, 2002
An Efficient Indexing and Search Technique for Multimedia.. - Clausen, Körner, Kurth (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In 28th International Conference VLDB, Hong Kong, pages 406--417, 2002.
Time Series Representations for Music Information Retrieval - Adams (2004) (Correct)
No context found.
E. Keogh, Exact Indexing of Dynamic Time Warping, Proceedings of the 28th VLDB Conference (2002).
Skyline Index for Time Series Data - Li, Lopez, Moon (2003) (Correct)
No context found.
E. Keogh. Exact Indexing of Dynamic Time Warping. In Proceedings of the 28th VLDB Conference, pages 406--417, Hong Kong, China, August 2002.
Flexible and Efficient Similarity Querying for Time-series.. - Goldin, Millstein, Kutlu (2003) (Correct)
No context found.
Keogh, E. Exact indexing of dynamic time warping. Proc. 28th Int'l Conf. on Very Large Data Bases. Hong Kong. pp 406-417, 2002
A Comparison of Hardware and Software in Sequence Rule Evolution - Hetland, Saetrom (2003) (Correct)
No context found.
E. J. Keogh. Exact indexing of dynamic time warping. In Proc. 28th Int. Conf. on Very Large Data Bases, VLDB, pages 406--417, 2002.
Polyphonic Audio Matching and Alignment for Music Retrieval - Hu, Dannenberg, Tzanetakis (2003) (Correct)
No context found.
Keogh, E. "Exact Indexing of Dynamic Time Warping", Proc. 28th International Conference on Very Large Database (VLDB), VLDB Endowment, 2002.
Primitives for Online Time Series Analysis - December Summary Data (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In In 28th International Conference on Very Large Data Bases, pages 406--417, 2002. 17
Primitives for Online Time Series Analysis - December Summary Data (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In In 28th International Conference on Very Large Data Bases, pages 406--417, 2002.
Primitives for Online Time Series Analysis - December The Vision (Correct)
No context found.
E. Keogh. Exact indexing of dynamic time warping. In In 28th International Conference on Very Large Data Bases, pages 406--417, 2002. 18
Fast Algorithms for Time Series with applications to - Finance Physics Music (Correct)
No context found.
Eamonn Keogh. Exact indexing of dynamic time warping. In VLDB 2002.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC