Generalizing DTW to the multi-dimensional case requires an adaptive approach
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
In recent years Dynamic Time Warping (DTW) has emerged as the distance measure of choice for virtually all time series data mining applications. For example, virtually all applications that process data from wearable devices use DTW as a core sub-routine. This is the result of significant progress in improving DTW’s efficiency, together with multiple empirical studies showing that DTW-based classifiers at least equal (and generally surpass) the accuracy of all their rivals across dozens of datasets. Thus far, most of the research has considered only the one-dimensional case, with practitioners generalizing to the multi-dimensional case in one of two ways, dependent or independent warping. In general, it appears the community believes either that the two ways are equivalent, or that the choice is irrelevant. In this work, we show that this is not the case. The two most commonly used multi-dimensional DTW methods can produce different classifications, and neither one dominates over the other. This seems to suggest that one should learn the best method for a particular application. However, we will show that this is not necessary; a simple, principled rule can be used on a case-by-case basis to predict which of the two methods we should trust at the time of classification. Our method allows us to ensure that classification results are at least as accurate as the better of the two rival methods, and, in many cases, our method is significantly more accurate. We demonstrate our ideas with the most extensive set of multi-dimensional time series classification experiments ever attempted.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439
Fundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680
A Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662
Time Warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison
Sankoff, D., & Kruskal, J. B. (1983) · Medical Entomology and Zoology · Cited by 1,915
Ding, H., Trajcevski, G., Scheuermann, P., Wang, X., & Keogh, E. (2008) · Proceedings of the VLDB Endowment · doi:10.14778/1454159.1454226 · Cited by 1,354
Self-citationTime series shapelets: a new primitive for data mining
Ye, L., & Keogh, E. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557122 · Cited by 987
Self-citationOn the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration
Keogh, E., & Kasetty, S. (2003) · Data Mining and Knowledge Discovery · doi:10.1023/a:1024988512476 · Cited by 861
Self-citationInduction of decision trees. Machine Learning
Quinlan, J. R. (1986) · Symposium on the Theory of Computing · Cited by 809
Ermes, M., Parkka, J., Mantyjarvi, J., & Korhonen, I. (2008) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2007.899496 · Cited by 707
Twenty Years of Mixture of Experts
Yuksel, S. E., Wilson, J. N., & Gader, P. D. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2200299 · Cited by 606
uWave: Accelerometer-based personalized gesture recognition and its applications
Liu, J., Wang, Z., Zhong, L., Wickramasuriya, J., & Vasudevan, V. (2009) · 2009 IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2009.4912759 · Cited by 559
Aligning gene expression time series with time warping algorithms
Aach, J., & Church, G. M. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.6.495 · Cited by 496
uWave: Accelerometer-based personalized gesture recognition and its applications
Liu, J., Zhong, L., Wickramasuriya, J., & Vasudevan, V. (2009) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2009.07.007 · Cited by 479
Everything you know about Dynamic Time Warping is Wrong
Ratanamahatana, C. A., & Keogh, E. (2004) · Cited by 434
Self-citationSatellite Image Time Series Analysis Under Time Warping
Petitjean, F., Inglada, J., & Gancarski, P. (2012) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2011.2179050 · Cited by 337
Accelerometer-based gesture control for a design environment
Kela, J., Korpipää, P., Mäntyjärvi, J., Kallio, S., Savino, G., Jozzo, L., & Marca, S. D. (2006) · Personal and Ubiquitous Computing · doi:10.1007/s00779-005-0033-8 · Cited by 294
Wearables: has the age of smartwatches finally arrived?
Rawassizadeh, R., Price, B. A., & Petre, M. (2015) · Communications of the ACM · doi:10.1145/2629633 · Cited by 267
Rakthanmanon, T., Campana, B., Mueen, A., Batista, G., Westover, B., Zhu, Q., Zakaria, J., & Keogh, E. (2013) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2500489 · Cited by 246
Self-citationKeogh, E., Li, W., Xi, X., Lee, S., & Vlachos, M. (2006) · doi:10.5555/1182635.1164203 · Cited by 197
Self-citationTime Series Classification under More Realistic Assumptions
Hu, B., Chen, Y., & Keogh, E. (2013) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972832.64 · Cited by 151
Self-citationOn the Non-Trivial Generalization of Dynamic Time Warping to the Multi-Dimensional Case
Shokoohi-Yekta, M., Wang, J., & Keogh, E. (2015) · Proceedings of the 2015 SIAM International Conference on Data Mining · doi:10.1137/1.9781611974010.33 · Cited by 144
Self-citationAkl, A., & Valaee, S. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495895 · Cited by 116
Accuracy Assessment for AG500, Electromagnetic Articulograph
Yunusova, Y., Green, J. R., & Mefferd, A. S. (2008) · Journal of Speech Language and Hearing Research · doi:10.1044/1092-4388(2008/07-0218 · Cited by 108
iSAX: disk-aware mining and indexing of massive time series datasets
Shieh, J., & Keogh, E. (2009) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-009-0125-6 · Cited by 88
Self-citationDiscovery of Meaningful Rules in Time Series
Shokoohi-Yekta, M., Chen, Y., Campana, B., Hu, B., Zakaria, J., & Keogh, E. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783306 · Cited by 82
Self-citationEmbedding-based subsequence matching in time-series databases
Papapetrou, P., Athitsos, V., Potamias, M., Kollios, G., & Gunopulos, D. (2011) · ACM Transactions on Database Systems · doi:10.1145/2000824.2000827 · Cited by 76
Online Context Recognition in Multisensor Systems using Dynamic Time Warping
Ko, M. H., West, G., Venkatesh, S., & Kumar, M. (2005) · 2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing · doi:10.1109/issnip.2005.1595593 · Cited by 54
Recognition Of Multivariate Temporal Musical Gestures Using N-Dimensional Dynamic Time Warping
Gillian, N. E., Knapp, B., & O’Modhrain, S. (2011) · doi:10.5281/zenodo.1178028 · Cited by 53
Wang, J., Balasubramanian, A., de la Vega, L. G. M., Green, J. R., Samal, A. K., & Prabhakaran, B. (2013) · Lincoln (University of Nebraska) · Cited by 52
Self-citationWang, J., Samal, A. K., & Green, J. R. (2014) · Workshop on Speech and Language Processing for Assistive Technologies · doi:10.3115/v1/w14-1906 · Cited by 43
Self-citationBashir, M., & Kempf, J. (2008) · doi:10.5281/zenodo.1081500 · Cited by 41
Kale, N., Lee, J., Lotfian, R., & Jafari, R. (2012) · Wireless Health · doi:10.1145/2448096.2448103 · Cited by 39
Hu, B., Chen, Y., Zakaria, J., Ulanova, L., & Keogh, E. (2013) · Proceedings · doi:10.1109/icdm.2013.33 · Cited by 36
Self-citationUsing multi-dimensional dynamic time warping for TUG test instrumentation with inertial sensors
Al-Jawad, A., Adame, M. R., Romanovas, M., Hobert, M. A., Maetzler, W., Traechtler, M., Möeller, K., & Manoli, Y. (2012) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2012.6343011 · Cited by 27
An Ensemble Dynamic Time Warping Classifier with Application to Activity Recognition
McGlynn, D., & Madden, M. G. (2010) · Springer eBooks · doi:10.1007/978-0-85729-130-1_26 · Cited by 26
Multi-Dimensional Dynamic Time Warping for Image Texture Similarity
de Mello, R. F., & Gondra, I. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88190-2_8 · Cited by 21
Parameter-Free Audio Motif Discovery in Large Data Archives
Hao, Y., Shokoohi-Yekta, M., Papageorgiou, G., & Keogh, E. (2013) · Proceedings · doi:10.1109/icdm.2013.30 · Cited by 15
Self-citationMother Fugger: Mining Historical Manuscripts with Local Color Patches
Zhu, Q., & Keogh, E. (2010) · Proceedings · doi:10.1109/icdm.2010.11 · Cited by 12
Self-citation
Cited by
Ruiz, A. P., Flynn, M., Large, J., Middlehurst, M., & Bagnall, A. (2021) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-020-00727-3 · Cited by 476
HIVE-COTE 2.0: a new meta ensemble for time series classification
Middlehurst, M., Large, J., Flynn, M., Lines, J., Bostrom, A., & Bagnall, A. (2021) · Machine Learning · doi:10.1007/s10994-021-06057-9 · Cited by 321
The UEA multivariate time series classification archive, 2018
Bagnall, A., Dau, H. A., Lines, J., Flynn, M., Large, J., Bostrom, A., Southam, P., & Keogh, E. (2018) · arXiv · doi:10.48550/arxiv.1811.00075 · Cited by 87
“Cricket was first formatted for MTSC in [4].”
MethodInfluentialSelf-citationTSGBench: Time Series Generation Benchmark
Ang, Y., Huang, Q., Bao, Y., Tung, A. K. H., & Huang, Z. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3632093.3632097 · Cited by 38
Hachaj, T., & Piekarczyk, M. (2019) · Sensors · doi:10.3390/s19245408 · Cited by 30
“Especially popular is DTW time series classification algorithm which utilizes the similarity function to determine the similarity of the time series pairs [10,11].”
Method
Metadata
- Authors
- Shokoohi-Yekta, M., Hu, B., Jin, H., Wang, J., & Keogh, E.
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2016-02-15
- Volume
- 31
- Issue
- 1
- Pages
- 1-31
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W2283896980
- Cited by
- 320
- References
- 38
- FWCI
- 22.15
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.