Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

Saud Alhajaj Aldossari

doi:10.3390/electronics12030497

Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

Saud Alhajaj Aldossari

Electrical Engineering

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

18 Scopus citations

Abstract

The propagation of signal and its strength in an indoor area have become crucial in the era of fifth-generation (5G) and beyond-5G communication systems, which use high bandwidth. High millimeter wave (mmWave) frequencies present a high signal loss and low signal strength, particularly during signal propagation in indoor areas. It is considerably difficult to design indoor wireless communication systems through deterministic modeling owing to the complex nature of the construction materials and environmental changes caused by human interactions. This study presents a methodology of data-driven techniques that will be applied to predict path loss using artificial intelligence. The proposed methodology enables the prediction of signal loss in an indoor environment with an accuracy of 97.4%.

Original language	English
Article number	497
Journal	Electronics (Switzerland)
Volume	12
Issue number	3
DOIs	https://doi.org/10.3390/electronics12030497
State	Published - Feb 2023

Keywords

5G
artificial intelligence
decision tree
gradient boosting
indoor communications
lasso regression
neural network
path loss
random forest

Access to Document

10.3390/electronics12030497

Cite this

@article{f58f9b6c09df40308308ed7da58bd4ca,

title = "Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band",

abstract = "The propagation of signal and its strength in an indoor area have become crucial in the era of fifth-generation (5G) and beyond-5G communication systems, which use high bandwidth. High millimeter wave (mmWave) frequencies present a high signal loss and low signal strength, particularly during signal propagation in indoor areas. It is considerably difficult to design indoor wireless communication systems through deterministic modeling owing to the complex nature of the construction materials and environmental changes caused by human interactions. This study presents a methodology of data-driven techniques that will be applied to predict path loss using artificial intelligence. The proposed methodology enables the prediction of signal loss in an indoor environment with an accuracy of 97.4\%.",

keywords = "5G, artificial intelligence, decision tree, gradient boosting, indoor communications, lasso regression, neural network, path loss, random forest",

author = "Aldossari, \{Saud Alhajaj\}",

note = "Publisher Copyright: {\textcopyright} 2023 by the author.",

year = "2023",

month = feb,

doi = "10.3390/electronics12030497",

language = "English",

volume = "12",

journal = "Electronics (Switzerland)",

issn = "2079-9292",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "3",

}

TY - JOUR

T1 - Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

AU - Aldossari, Saud Alhajaj

PY - 2023/2

Y1 - 2023/2

N2 - The propagation of signal and its strength in an indoor area have become crucial in the era of fifth-generation (5G) and beyond-5G communication systems, which use high bandwidth. High millimeter wave (mmWave) frequencies present a high signal loss and low signal strength, particularly during signal propagation in indoor areas. It is considerably difficult to design indoor wireless communication systems through deterministic modeling owing to the complex nature of the construction materials and environmental changes caused by human interactions. This study presents a methodology of data-driven techniques that will be applied to predict path loss using artificial intelligence. The proposed methodology enables the prediction of signal loss in an indoor environment with an accuracy of 97.4%.

AB - The propagation of signal and its strength in an indoor area have become crucial in the era of fifth-generation (5G) and beyond-5G communication systems, which use high bandwidth. High millimeter wave (mmWave) frequencies present a high signal loss and low signal strength, particularly during signal propagation in indoor areas. It is considerably difficult to design indoor wireless communication systems through deterministic modeling owing to the complex nature of the construction materials and environmental changes caused by human interactions. This study presents a methodology of data-driven techniques that will be applied to predict path loss using artificial intelligence. The proposed methodology enables the prediction of signal loss in an indoor environment with an accuracy of 97.4%.

KW - 5G

KW - artificial intelligence

KW - decision tree

KW - gradient boosting

KW - indoor communications

KW - lasso regression

KW - neural network

KW - path loss

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=85147823456&partnerID=8YFLogxK

U2 - 10.3390/electronics12030497

DO - 10.3390/electronics12030497

M3 - Article

AN - SCOPUS:85147823456

SN - 2079-9292

VL - 12

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

IS - 3

M1 - 497

ER -

Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this