Classification of Multi-dimensional Streaming Time Series by Weighting Each Classifier's Track Record

Hu, Bing; Chen, Yanping; Zakaria, Jesin; Ulanova, Liudmila; Keogh, Eamonn

doi:10.1109/icdm.2013.33

Cited by 26 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, adding more dimensions does not guarantee improved accuracy. In [4] the authors outline a strategy for choosing which dimensions to add to an MDT. Note, however, that this issue is completely orthogonal to our contributions; Table 4 suggests that whatever set of dimensions you choose, you are better off with DTWA than any other method.…”

Section: Recognition Of Cricket Umpire Signalsmentioning

confidence: 99%

“…While there are hundreds of research efforts that use DTW in a multi-dimensional setting [3][5] [7][9] [11][16], we are not aware of any work that discusses the relative merits of DTWI and DTWD, or even explicitly notes that they are alternatives. The ubiquity of multi-dimensional time series, especially given the recent explosion of interest in wearable devices, has produced significant research in speeding up DTW [14], choosing which subset of dimensions to use [4], choosing a setting for the warping window constraint [2], etc. However, all such work is orthogonal to (and compatible with) our contributions.…”

Section: Conclusion and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On the Non-Trivial Generalization of Dynamic Time Warping to the Multi-Dimensional Case

Shokoohi-Yekta

Wang

Keogh

2015

Proceedings of the 2015 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

In the last decade, Dynamic Time Warping (DTW) has emerged as the distance measure of choice for virtually all time series data mining applications. This is the result of significant progress in improving DTW's efficiency, and multiple empirical studies showing that DTW-based classifiers at least equal 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. 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 multidimensional 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 give credence to. 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 strictly more accurate. We demonstrate our ideas with the most extensive set of multi-dimensional time series classification experiments ever attempted.

show abstract

Section: Recognition Of Cricket Umpire Signalsmentioning

confidence: 99%

Section: Conclusion and Related Workmentioning

confidence: 99%

On the Non-Trivial Generalization of Dynamic Time Warping to the Multi-Dimensional Case

Shokoohi-Yekta

Wang

Keogh

2015

Proceedings of the 2015 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, [7] proposed a voting framework for multi-dimensional time series classification by weighting the class prediction from each time series stream. [6] used an ensemble of models for mining data streams with concept-drifting and skewed distributions.…”

Section: Related Workmentioning

confidence: 99%

“…Given a network of time series R, the dimension of latent factors l, and the weight of contextual information λ, the algorithm aims to tune model parameters and approximate the values of the latent factors. It first randomly initializes the model parameters θ (including U) (step 1); and then iteratively infers the expectations of Z, V (step [3][4][5][6][7][8][9][10][11], and updates the model parameters θ (step 13) until convergence. The missing values can be inferred from the reconstructed time seriesX (step 16).…”

Section: The Overall Algorithmmentioning

confidence: 99%

“…Time Series Mining There has been a large amount of research work in time series mining [9], including representation [18,16], classification [21,6,7], outlier detection [11] and etc. For instance, [7] proposed a voting framework for multi-dimensional time series classification by weighting the class prediction from each time series stream.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Fast Mining of a Network of Coevolving Time Series

Cai¹,

Tong²,

Fan³

et al. 2015

Proceedings of the 2015 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Coevolving multiple time series are ubiquitous and naturally appear in a variety of high-impact applications, ranging from environmental monitoring, computer network traffic monitoring, motion capture, to physiological signal in health care and many more. In many scenarios, the multiple time series data is often accompanied by some contextual information in the form of networks. In this paper, we refer to such multiple time series, together with its embedded network as a network of coevolving time series. In order to unveil the underlying patterns of a network of coevolving time series, we propose DCMF, a dynamic contextual matrix factorization algorithm. The key idea is to find the latent factor representation of the input time series and that of its embedded network simultaneously. Our experimental results on several real datasets demonstrate that our method (1) outperforms its competitors, especially when there are lots of missing values; and (2) enjoys a linear scalability w.r.t. the length of time series.

show abstract