Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model

Najiya Omar; Hamed Aly; Timothy Little

doi:10.1109/ACCESS.2022.3171230

Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model

Najiya Omar, Hamed Aly, Timothy Little

Institutional Research Division

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Original language	English
Pages (from-to)	48643-48659
Number of pages	17
Journal	IEEE Access
Volume	10
DOIs	https://doi.org/10.1109/ACCESS.2022.3171230
Publication status	Published - 2022

ASJC Scopus Subject Areas

General Engineering
General Materials Science
General Computer Science

Keywords

Feature importance
GHI forecasting
data perturbation
exogenous and endogenous variables
long short-term memory
random forest regression
recursive feature elimination
redundancy and relevancy measures
variance reduction

Access to Document

10.1109/ACCESS.2022.3171230

Cite this

Omar, N., Aly, H., & Little, T. (2022). Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model. IEEE Access, 10, 48643-48659. https://doi.org/10.1109/ACCESS.2022.3171230

@article{ef0089f1d28e46a5a0776ea7cb1a8ccb,

title = "Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model",

keywords = "Feature importance, GHI forecasting, data perturbation, exogenous and endogenous variables, long short-term memory, random forest regression, recursive feature elimination, redundancy and relevancy measures, variance reduction",

author = "Najiya Omar and Hamed Aly and Timothy Little",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2022",

doi = "10.1109/ACCESS.2022.3171230",

language = "English",

volume = "10",

pages = "48643--48659",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model

AU - Omar, Najiya

AU - Aly, Hamed

AU - Little, Timothy

PY - 2022

Y1 - 2022

KW - Feature importance

KW - GHI forecasting

KW - data perturbation

KW - exogenous and endogenous variables

KW - long short-term memory

KW - random forest regression

KW - recursive feature elimination

KW - redundancy and relevancy measures

KW - variance reduction

UR - http://www.scopus.com/inward/record.url?scp=85129647752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85129647752&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2022.3171230

DO - 10.1109/ACCESS.2022.3171230

M3 - Article

AN - SCOPUS:85129647752

SN - 2169-3536

VL - 10

SP - 48643

EP - 48659

JO - IEEE Access

JF - IEEE Access

ER -

Optimized Feature Selection Based on a Least-Redundant and Highest-Relevant Framework for a Solar Irradiance Forecasting Model

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this