Significant motifs in time series

Castro, Nuno Constantino; Azevedo, Paulo J.

doi:10.1002/sam.11134

Cited by 21 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A normalized time series has interesting properties that allow us to quickly compute length 3 time series motifs. [2], ···} is equal to one less the number of observations in the normalized time series. In other words, ∑…”

Section: Motif Discoverymentioning

confidence: 99%

See 2 more Smart Citations

Efficient Mining of Lag Patterns in Evolving Time Series

Patel

Hsu²,

Lee³

2013

Transactions on Large-Scale Data- And Knowledge-Centered Systems XI

View full text Add to dashboard Cite

Abstract. Time series motifs are sets of similar subsequences. Lag patterns, or the invariant ordering among time series motifs, depict localized repeated associative relationships across multiple real valued time series. Lag patterns are of special interest in many real world applications, such as constructing stock portfolio in financial domain, extracting regulator-target relationship in bioinformatics domain, etc. However, mining lag patterns is computationally intensive, particularly in evolving time series data. In this paper, we present an efficient algorithm called LPMiner * that iteratively discovers motifs and generates lag patterns of increasing length. We also design an incremental algorithm called incLPMiner to mine lag patterns in the presence of frequent database updates. Experimental analysis on real world time series datasets demonstrate the efficiency and scalability of our proposed algorithms.

show abstract

Section: Motif Discoverymentioning

confidence: 99%

“…Given a time series T = {v [1], v [2], ···}, its normalized time series is T = { v [1], v [2], ··· } where…”

Section: Motif Discoverymentioning

confidence: 99%

See 1 more Smart Citation

Efficient Mining of Lag Patterns in Evolving Time Series

Patel

Hsu²,

Lee³

2013

Transactions on Large-Scale Data- And Knowledge-Centered Systems XI

View full text Add to dashboard Cite

show abstract

“…(1) The original fMRI data is processed via time correction, spatial registration, normalization, and smoothing, etc. (12). The whole brain time series data are obtained by filtering high-frequency physiological noise and low frequency signals.…”

Section: Fmri Data Processingmentioning

confidence: 99%

Directed connectivity of brain default networks in resting state using GCA and motif

Jiao

Wang

et al. 2017

Front Biosci

View full text Add to dashboard Cite

Nowadays, there is a lot of interest in assessing functional interactions between key brain regions. In this paper, Granger causality analysis (GCA) and motif structure are adopted to study directed connectivity of brain default mode networks (DMNs) in resting state. Firstly, the time series of functional magnetic resonance imaging (fMRI) data in resting state were extracted, and the causal relationship values of the nodes representing related brain regions are analyzed in time domain to construct a default network. Then, the network structures were searched from the default networks of controls and patients to determine the fixed connection mode in the networks. The important degree of motif structures in directed connectivity of default networks was judged according to p-value and Z-score. Both node degree and average distance were used to analyze the effect degree an information transfer rate of brain regions in motifs and default networks, and efficiency of the network. Finally, activity and functional connectivity strength of the default brain regions are researched according to the change of energy distributions between the normals and the patients' brain regions. Experimental results demonstrate that, both normal subjects and stroke patients have some corresponding fixed connection mode of three nodes, and the efficiency and power spectrum of the patient's default network is somewhat lower than that of the normal person. In particular, the Right Posterior Cingulate Gyrus (PCG.R) has a larger change in functional connectivity and its activity. The research results verify the feasibility of the application of GCA and motif structure to study the functional connectivity of default networks in resting state.

show abstract

“…The purposes of motifs and histories are very different, though. Data mining seeks, as a matter of unsupervised learning, to extract motifs [36] and, for example, evaluate their significance [37]. Flow field forecasting, by contrast, is performing supervised learning to interpolate a new change for a current history based on a set of past observed associations between history and change.…”

Section: Closing Remarksmentioning

confidence: 99%

Flow field forecasting for univariate time series

Frey

Caudle

2013

Statistical Analysis

View full text Add to dashboard Cite

A statistical learning methodology, called ﬂow ﬁeld forecasting, is presented for predicting the future of a univariate time series. Flow ﬁeld forecasting draws information from an interpolated ﬂow ﬁeld of the observed time series to incrementally build a forecast. The time series need not have uniformly spaced observations. Included in the presentation are measures of assessment, a procedure for forecast updating as new data arrive and a performance comparison of ﬂow ﬁeld forecasting with other major forecasting techniques. © 2013 Wiley Periodicals, Inc. Statistical Analysis and Data Mining, 2013

show abstract

Significant motifs in time series

Cited by 21 publications

References 43 publications

Efficient Mining of Lag Patterns in Evolving Time Series

Efficient Mining of Lag Patterns in Evolving Time Series

Directed connectivity of brain default networks in resting state using GCA and motif

Flow field forecasting for univariate time series

Contact Info

Product

Resources

About