Control with GP Models

Kocijan, Juš

doi:10.1007/978-3-319-21021-6_4

Search citation statements

Order By: Relevance

Paper Sections

Select...

System Identification1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sequential dynamic structure of RNNs is also suitable for being employed as a NARX [148]. Recently, NARX based on dynamic GP [149] and polynomial chaos expansions (PCE) [150] were developed with the advantage of providing confidence intervals [147].…”

Section: System Identificationmentioning

confidence: 99%

A review of machine learning methods applied to structural dynamics and vibroacoustic

Cunha

Droz

Zine

et al. 2023

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Section: System Identificationmentioning

confidence: 99%

A review of machine learning methods applied to structural dynamics and vibroacoustic

Cunha

Droz

Zine

et al. 2023

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Assessment of a probabilistic supervised machine learning method to estimate biomass expansion and conversion factors: a case study on cedar and pine trees

Diamantopoulou,

Kurnaz,

Kalkanlı Genç

et al. 2024

Can. J. For. Res.

View full text Add to dashboard Cite

Quantifying tree and forest biomass is crucial for formulating effective forest policy and management, given its role in human resource use and carbon storage. Forest biomass significantly contributes to environmental quality by absorbing carbon dioxide. Current research focuses on determining biomass factors for various tree species. This study employed both standard non-linear regression (NLR) and Gaussian process regression (GPR), a machine learning method using artificial intelligence, to estimate and predict biomass expansion and conversion factors accurately. The case study included plantation and naturally occurring cedar and pine trees in Türkiye's Western Anatolian Region and Göller Region. Non-linear regression used Levenberg-Marquardt optimization method, while Gaussian process regression employed radial basis function kernel. This dual approach allowed for assessing prediction uncertainties. The models constructed using GPR show superior performance compared to NLR models for both biomass factors and species within the datasets used. According to Furnival evaluation metric values, accuracy of the NLR models was 1.05 to 1.34 times lower than that of corresponding GPR models. Overall findings highlight the significant potential of Gaussian process regression for accurately estimating and predicting biomass factors with high variances. This emphasizes its utility in modeling scenarios that require high flexibility, such as tree biomass prediction.

show abstract

Control with GP Models

Cited by 2 publications

References 83 publications

A review of machine learning methods applied to structural dynamics and vibroacoustic

A review of machine learning methods applied to structural dynamics and vibroacoustic

Assessment of a probabilistic supervised machine learning method to estimate biomass expansion and conversion factors: a case study on cedar and pine trees

Contact Info

Product

Resources

About