The UCR Time Series Archive

Dau, Son Hoang; Bagnall, Anthony; Kamgar, Kaveh; Yeh, Chin‐Chia Michael; Zhu, Yan; Gharghabi, Shaghayegh; Ratanamahatana, Chotirat Ann; Keogh, Eamonn

doi:10.48550/arxiv.1810.07758

Cited by 18 publications

(27 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These 46 datasets are used in (Mori et al, 2017) who, fortunately, also report classification accuracy and earliness of compared approaches. They are made available on the UCR repository (Dau et al, 2018;Chen et al, 2015) and cover a wide range of data modalities, ranging from motion capture through audio to Electrocardiography (ECG) sensor data. The competitors considered here are the best method from (Mori et al, 2017) (denoted SR2-CF2), the pioneering work of (Xing et al, 2012) (ECTS), as well as EDSC (Xing et al, 2011), and RELCLASS (Parrish et al, 2013) methods.…”

Section: Resultsmentioning

confidence: 99%

End-to-end Learning for Early Classification of Time Series

Rußwurm¹,

Lefèvre²,

Courty³

et al. 2019

Preprint

View full text Add to dashboard Cite

Classification of time series is a topical issue in machine learning. While accuracy stands for the most important evaluation criterion, some applications require decisions to be made as early as possible. Optimization should then target a compromise between earliness, i.e., a capacity of providing a decision early in the sequence, and accuracy. In this work, we propose a generic, end-toend trainable framework for early classification of time series. This framework embeds a learnable decision mechanism that can be plugged into a wide range of already existing models. We present results obtained with deep neural networks on a diverse set of time series classification problems. Our approach compares well to state-of-the-art competitors while being easily adaptable by any existing neural network topology that evaluates a hidden state at each time step.

show abstract

Section: Resultsmentioning

confidence: 99%

End-to-end Learning for Early Classification of Time Series

Rußwurm¹,

Lefèvre²,

Courty³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to its clearly defined objective evaluation measures, we evaluate ADTW against other distances on a classification benchmark, using the UCR archive [23] in its 128 dataset versions. We retained 112 datasets after filtering out those with series of variable length, containing missing data, or having only one training exemplar per class (leading to spurious results under LOOCV).…”

Section: Methodsmentioning

confidence: 99%

“…One of the issues that must be addressed in any application of CDTW is how to select an appropriate value for w. A method deployed when the UCR benchmark archive was first established has become the defacto default method for time series classification [23]. This method applies leave-one-out cross validation to nearest neighbor classification over the training data D for all w ∈ {0, 0.01 , 0.02 , .…”

Section: Constrained Dtwmentioning

confidence: 99%

Amercing: An Intuitive, Elegant and Effective Constraint for Dynamic Time Warping

Herrmann¹,

Webb²

2021

Preprint

View full text Add to dashboard Cite

Dynamic Time Warping (DTW), and its constrained (CDTW) and weighted (WDTW) variants, are time series distances with a wide range of applications.They minimize the cost of non-linear alignments between series. CDTW and WDTW have been introduced because DTW is too permissive in its alignments.However, CDTW uses a crude step function, allowing unconstrained flexibility within the window, and none beyond it. WDTW's multiplicative weight is relative to the distances between aligned points along a warped path, rather than being a direct function of the amount of warping that is introduced. In this paper, we introduce Amerced Dynamic Time Warping (ADTW), a new, intuitive, DTW variant that penalizes the act of warping by a fixed additive cost. Like CDTW and WDTW, ADTW constrains the amount of warping.However, it avoids both abrupt discontinuities in the amount of warping allowed and the limitations of a multiplicative penalty. We formally introduce ADTW, prove some of its properties, and discuss its parameterization. We show on a simple example how it can be parameterized to achieve an intuitive outcome, and demonstrate its usefulness on a standard time series classification benchmark.We provide a demonstration application in C++ [1].

show abstract

“…Example 2: Crop image This example comprises crop image data obtained from the UCR Time Series Classification Archive (Dau et al, 2019). Each observation is a time series associated with a pixel from a satellite image, where the images at different times are corrected so that a given pixel corresponds to the same spatial region in all images.…”

Section: Datasetsmentioning

confidence: 99%

Bayesian clustering using random effects models and predictive projections

Mao,

Nott

2021

Preprint

View full text Add to dashboard Cite

Linear mixed models are widely used for analyzing hierarchically structured data involving missingness and unbalanced study designs. We consider a Bayesian clustering method that combines linear mixed models and predictive projections. For each observation, we consider a predictive replicate in which only a subset of the random effects is shared between the observation and its replicate, with the remainder being integrated out using the conditional prior. Predictive projections are then defined in which the number of distinct values taken by the shared random effects is finite, in order to obtain different clusters. Integrating out some of the random effects acts as a noise filter, allowing the clustering to be focused on only certain chosen features of the data. The method is inspired by methods for Bayesian model checking, in which simulated data replicates from a fitted model are used for model criticism by examining their similarity to the observed data in relevant ways. Here the predictive replicates are used to define similarity between observations in relevant ways for clustering. To illustrate the way our method reveals aspects of the data at different scales, we consider fitting temporal trends in longitudinal data using Fourier cosine bases with a random effect for each basis function, and different clusterings defined by shared random effects for replicates of low or high frequency terms. The method is demonstrated in a series of real examples.

show abstract

The UCR Time Series Archive

Cited by 18 publications

References 0 publications

End-to-end Learning for Early Classification of Time Series

End-to-end Learning for Early Classification of Time Series

Amercing: An Intuitive, Elegant and Effective Constraint for Dynamic Time Warping

Bayesian clustering using random effects models and predictive projections

Contact Info

Product

Resources

About