Closest History Flow Field Forecasting for IEEE CSCI-ISCS

Caudle, Kyle; Fleming, Patrick S.

doi:10.1109/csci.2016.0227

Cited by 2 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because different history structures (ℋ) have a different numbers of predictors, the distances are computed in spaces with different dimensions. In (Caudle and Fleming (2016)), we show that the Manhattan distance computed in different dimensional spaces have different distributions and different quantiles. So, direct comparison of distances is not appropriate.…”

Section: Bivariate Ff Forecastingmentioning

confidence: 87%

“…For bivariate data, we start with a set of candidate predictors (

scriptP

). We then search over all history structures (ℋ) obtained from all the power sets of

scriptP

(Caudle & Fleming, 2016). Although this is computationally expensive, for bivariate data, it does not overload the computing resources on standard desktop computers.…”

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

“…By choosing different structures

scriptS

and

scriptS'

, the same sequence s k of observations yields different histories

h_{k} = scriptS ((), s_{k})

and

boldh'_{k} = scriptS' ((), s_{k})

with perhaps different dimensions. For a concrete example of structures, histories, and predictor variables, the reader is referred to (Caudle and Fleming (2016)).…”

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

“…Determining “closesness” is a challenge because history structures are of different dimensions. One of the contributions of (Caudle and Fleming (2016)) is distance comparison between spaces whose dimensions differ.…”

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

“…In this review, we will provide the history of FF forecasting and explain the FF forecasting methodology. For more detailed and comparison studies, we refer the reader to the published work on this subject (Caudle, Fleming, Pyeatt, & Hoover, 2019; Caudle & Fleming, 2016; M. Frey & Caudle, 2011; Frey & Caudle, 2013).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A review of flow field forecasting: A high‐dimensional forecasting procedure

Caudle

Fleming

Hoover

2020

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

Forecasting, especially high-dimensional forecasting, is becoming more and more sought after, particularly as computing resources increase in both size and speed. Flow field forecasting is a general purpose regression-based forecasting method that has recently been expanded to high-dimensional settings. In this article, we provide an overview of the flow field forecasting methodology, with a particular emphasis on environments where the number of candidate predictor variables is large, potentially larger than the number of observations.

show abstract

Section: Bivariate Ff Forecastingmentioning

confidence: 87%

“…For bivariate data, we start with a set of candidate predictors (

scriptP

). We then search over all history structures (ℋ) obtained from all the power sets of

scriptP

(Caudle & Fleming, 2016). Although this is computationally expensive, for bivariate data, it does not overload the computing resources on standard desktop computers.…”

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

“…By choosing different structures

scriptS

and

scriptS'

, the same sequence s k of observations yields different histories

h_{k} = scriptS ((), s_{k})

and

boldh'_{k} = scriptS' ((), s_{k})

with perhaps different dimensions. For a concrete example of structures, histories, and predictor variables, the reader is referred to (Caudle and Fleming (2016)).…”

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

Section: Bivariate Ff Forecastingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A review of flow field forecasting: A high‐dimensional forecasting procedure

Caudle

Fleming

Hoover

2020

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

show abstract

Forecasting Multilinear Data via Transform-Based Tensor Autoregression

Cates¹,

Hoover²,

Caudle³

et al. 2022

Preprint

View full text Add to dashboard Cite

In the era of big data, there is an increasing demand for new methods for analyzing and forecasting 2-dimensional data. The current research aims to accomplish these goals through the combination of time-series modeling and multilinear algebraic systems. We expand previous autoregressive techniques to forecast multilinear data, aptly named the L-Transform Tensor autoregressive (L-TAR for short). Tensor decompositions and multilinear tensor products have allowed for this approach to be a feasible method of forecasting. We achieve statistical independence between the columns of the observations through invertible discrete linear transforms, enabling a divide and conquer approach. We present an experimental validation of the proposed methods on datasets containing image collections, video sequences, sea surface temperature measurements, stock prices, and networks.

show abstract

Closest History Flow Field Forecasting for IEEE CSCI-ISCS

Cited by 2 publications

References 15 publications

A review of flow field forecasting: A high‐dimensional forecasting procedure

A review of flow field forecasting: A high‐dimensional forecasting procedure

Forecasting Multilinear Data via Transform-Based Tensor Autoregression

Contact Info

Product

Resources

About