Partial mutual information based algorithm for input variable selection For time series forecasting

Darudi, Ali; Rezaeifar, Shideh; Bayaz, Mohammd Hossein Javidi Dasht

doi:10.1109/eeeic-2.2013.6737928

Cited by 12 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cooccurrence potential for any given jaguar, in relation to two or more other jaguars, would be the density function of time recordings on the refined time grid where any jaguar is within a set radius (such as 1800 m). The localized mutual information measure could be readily adapted to measure partial mutual information (Darudi et al, 2013 ), where the association between two jaguars is measured while controlling for another jaguar. In both this work and Fontes et al, the interpretations are based solely on observed individuals, and there are still challenges present in interpreting interactions detecting between pairs of jaguars when there are likely other interactions with unobserved individuals.…”

Section: Discussionmentioning

confidence: 99%

Smoothing splines of apex predator movement: Functional modeling strategies for exploring animal behavior and social interactions

Whetten

2021

Ecology and Evolution

View full text Add to dashboard Cite

Technological advancements in remote sensing of animal movement, referred to as animal telemetry, have revolutionized the discipline of movement ecology. Animal movement data provides critical information about ecological processes, and it can be a vital asset to conservation efforts of species and ecosystems. The increased feasibility of tracking and collecting animal movement information has yielded large reservoirs of fine-scale spatio-temporal data, and the challenges of meaningfully modeling animal behavior have resulted in the expansion of holistic machine learning methodology that appropriately considers animal psychology and cognition (Buderman

show abstract

Section: Discussionmentioning

confidence: 99%

Smoothing splines of apex predator movement: Functional modeling strategies for exploring animal behavior and social interactions

Whetten

2021

Ecology and Evolution

View full text Add to dashboard Cite

show abstract

“…On the contrary, inefficient or redundant lags may result in poor or complex models. Many optimal lag selection methods fail to perform properly owing to the inherent hypothesis of linearity or intense redundancy between the lags (Darudi et al 2013). In previous studies, autocorrelation analysis of the streamflow series has been commonly employed to identify the optimum lags (e.g., Rezaie-Balf et al 2019).…”

Section: Average Mutual Information (Ami)mentioning

confidence: 99%

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

Mehr

Ghadimi

Marttila

et al. 2022

Theor Appl Climatol

View full text Add to dashboard Cite

Genetic programming (GP) is an evolutionary regression method that has received considerable interest to model hydro-environmental phenomena recently. Considering the sparseness of hydro-meteorological stations on northern areas, this study investigates the benefits and downfalls of univariate streamflow modeling at high latitudes using GP and seasonal autoregressive integrated moving average (SARIMA). Furthermore, a new evolutionary time series model, called GP-SARIMA, is introduced to enhance streamflow forecasting accuracy at long-term horizons in a lake-river system. The paper includes testing the new model for one-step-ahead forecasts of daily mean, weekly mean, and monthly mean streamflow in the headwaters of the Oulujoki River, Finland. The results showed that a combination of correlogram and average mutual information (AMI) analysis might yield in the selection of the optimum lags that are needed to be used as the predictors of streamflow models. With Nash-Sutcliffe efficiency values of more than 99%, both GP and SARIMA models exhibited good performance for daily streamflow prediction. However, they were not able to precisely model the intramonthly snow water equivalent in the long-term forecast. The proposed ensemble model, which integrates the best GP and SARIMA models with the most efficient predictor, may eliminate one-fourth of root mean squared errors of standalone models. The GP-SARIMA also showed up to three times improvement in the accuracy of the standalone models based on the Nash-Sutcliff efficiency measure.

show abstract

“…The unnecessary and redundant features not only use extra memory storage but also raise overfitting problems, wasting computing power, and all the time required for the purpose of training the models. With the use of the partial mutual information (PMI) algorithm [23], redundancy between some features, that look mathematically similar, can be identified. The PMI algorithm calculates only that information between input feature and target output which has not been accounted for the calculation of information between previously selected feature set and output .…”

Section: E Feature Selectionmentioning

confidence: 99%

Mass Flow Rate Measurement of Pneumatically Conveyed Solids Through Multimodal Sensing and Data-Driven Modeling

Abbas

Yan

Lijuan

2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

Partial mutual information based algorithm for input variable selection For time series forecasting

Cited by 12 publications

References 15 publications

Smoothing splines of apex predator movement: Functional modeling strategies for exploring animal behavior and social interactions

Smoothing splines of apex predator movement: Functional modeling strategies for exploring animal behavior and social interactions

A new evolutionary time series model for streamflow forecasting in boreal lake-river systems

Mass Flow Rate Measurement of Pneumatically Conveyed Solids Through Multimodal Sensing and Data-Driven Modeling

Contact Info

Product

Resources

About