Feature-Based Time-Series Analysis

Fulcher, Ben D.

doi:10.1201/9781315181080-4

Cited by 89 publications

(81 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results above demonstrate that Fourier spectral properties of rs-fMRI are strongly correlated with connectivity strength, s. But the time-series analysis literature is vast and interdisciplinary [59]; could other statistical summaries of BOLD dynamics exhibit stronger relationships to s? To investigated this possibility, we used the hctsa toolbox [46,47] to perform a comprehensive data-driven comparison of the performance of 6062 different time-series features.…”

Section: Diverse Properties Of Bold Dynamics Are Informative Of Nodmentioning

confidence: 84%

“…Generating summaries of activity dynamics at individual brain areas also yields spatial maps that can be related to other datasets, such as macroscale maps of microstructural variation [36,68] straightforwardly. While univariate analysis of the BOLD signal is promising, a common problem in analyzing univariate time series is selecting an appropriate analysis method or summary statistic to compute [59]. The neuroimaging literature has most commonly focused on linear autocorrelation properties, either measured directly from the autocorrelation function or via the Fourier power spectrum.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Timescales of spontaneous fMRI fluctuations relate to structural connectivity in the brain

Fallon

Ward

Parkes

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

2 FALLON ET AL. motifs. Our findings demonstrate a conserved property of mouse and human brain organization, in which a brain region's spontaneous activity fluctuations are closely related to their surrounding structural scaffold. K E Y W O R D S structure-function relationship, time-series analysis, structural connectivity, resting-state fMRI, interspecies comparison 1 | INTRODUCTION The brain's complex spatiotemporal dynamics unfold on an intricate web of axonal connections: the connectome [1, 2]. These pathways facilitate information transfer between brain regions, manifesting in a complex relationship between connectome structure and neural dynamics. Reflecting the pairwise nature of structural connectivity (regionregion), existing studies have overwhelmingly compared pairwise measurements of anatomical connectivity to pairwise statistical relationships between neural activity time series, or functional connectivity, often using simulations of network dynamics to better understand how the observed relationships may arise [3-18]. Structural connectivity is highly informative of functional connectivity, consistent with the connectome as a physical substrate constraining inter-regional communication dynamics.Our understanding of pairwise structure-function relationships in the brain remains disconnected from our understanding of how a brain area's structural connectivity properties shape its activity dynamics. Indeed, the structural connectivity profile of a region's incoming and outgoing axonal connections is thought to define its function [19]. Furthermore, the activity dynamics of brain areas follow a functional hierarchy, with rapid dynamics in 'lower' sensory regions, and slower fluctuations in 'higher' regions associated with integrative processes [20][21][22][23][24]. The spatial variation of intrinsic timescales has been measured using ECOG [21], MEG [25,26], TMS-EEG [27], and fMRI [24,[28][29][30][31][32][33], and may a function variation in temporal receptive windows: timescales over which new information can be actively integrated with recently received information [20,33,34]. Spatial variation in intrinsic activity fluctuations may form a key basis for the brain's functional hierarchical organization, shaped by structural variation in the brain's microcircuitry [35][36][37]. This organization is thought to be important for behavior and cognition [20,[38][39][40], and its disruption has clinical implications: e.g., differences in intrinsic timescales are associated with symptom severity in autism [33]. While much is known about the structure-function relationship at the level of brain-region pairs, and how structural and functional connectivity architecture shape cognitive function and are affected in disease [41][42][43][44], relatively little is known about how it affects the information processing dynamics of individual brain areas. In particular, we do not yet understand the role structural connections play in the cortical organization of intrinsic timescales.Recent work has provided statistical e...

show abstract

Section: Diverse Properties Of Bold Dynamics Are Informative Of Nodmentioning

confidence: 84%

Section: Discussionmentioning

confidence: 99%

Timescales of spontaneous fMRI fluctuations relate to structural connectivity in the brain

Fallon

Ward

Parkes

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is an overall high correlation in performance across datasets, with a range of average performance (unbalanced classification rate on the given train-test partition a ub tot ): catch22 (69%), Euclidean 1-NN (71%), and DTW 1-NN (74%). The most interesting datasets are those for which one of the two approaches (shape-based or feature-based) markedly outperforms the other, as in these cases there is a clear advantage to tailoring your classification method to the structure of the data [12]; selected examples are annotated in Fig. 6B).…”

Section: Performance Comparisonmentioning

confidence: 99%

“…There is no single representation that is best for all time-series datasets, but rather, the optimal representation depends on the structure of the dataset and the questions being asked of it [12]. In this section we characterize the properties of selected datasets that show a strong preference for either featurebased or shape-based classification, as highlighted in Fig.…”

Section: Characteristics Of Datasets That Favor Feature-or Shape-basementioning

confidence: 99%

“…This approach does not scale well, often quadratic in both number of time series and series length [2], due to the necessity to compute distances (often using expensive elastic metrics) between all pairs of objects. An alternative approach involves defining timeseries similarity in terms of extracted features that are the output of time-series analysis algorithms [13,12]. This approach yields an interpretable summary of the dynamical characteristics of each time series that can then be used as the basis of efficient classification and clustering in a feature space using conventional machine-learning methods.…”

mentioning

confidence: 99%

See 1 more Smart Citation

catch22: CAnonical Time-series CHaracteristics selected through highly comparative time-series analysis

Lubba

Sethi²,

Knaute³

et al. 2019

Preprint

View full text Add to dashboard Cite

Capturing the dynamical properties of time series concisely as interpretable feature vectors can enable efficient clustering and classification for time-series applications across science and industry. Selecting an appropriate feature-based representation of time series for a given application can be achieved through systematic comparison across a comprehensive time-series feature library, such as those in the hctsa toolbox. However, this approach is computationally expensive and involves evaluating many similar features, limiting the widespread adoption of feature-based representations of time series for real-world applications. In this work, we introduce a method to infer small sets of time-series features that (i) exhibit strong classification performance across a given collection of time-series problems, and (ii) are minimally redundant. Applying our method to a set of 93 time-series classification datasets

show abstract

Classification of stochastic processes with topological data analysis

Güzel

Kaygun

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryIn this study, we demonstrate that engineered topological features can distinguish time series sampled from different stochastic processes with different noise characteristics, in both balanced and unbalanced sampling schemes. We compare our classification results against the results of the same classification on features coming from descriptive statistics and the wavelet transform. We conclude that machine learning models built on engineered topological features alone perform consistently better than those built on the standard statistical and wavelet features for time series classification tasks. We also apply dimension reduction techniques to our engineered features and compare the result of our classification models before and after dimensionality reduction. Finally, we also show that in our calculations of the engineered topological features, employing parallel computing methods does yield significant improvements in run time and memory footprint.

show abstract

Feature-Based Time-Series Analysis

Cited by 89 publications

References 74 publications

Timescales of spontaneous fMRI fluctuations relate to structural connectivity in the brain

Timescales of spontaneous fMRI fluctuations relate to structural connectivity in the brain

catch22: CAnonical Time-series CHaracteristics selected through highly comparative time-series analysis

Classification of stochastic processes with topological data analysis

Contact Info

Product

Resources

About