DOA Estimation for 6G Communication Systems

Haya Al Kassir; Ioannis T. Rekanos; Pavlos I. Lazaridis; Traianos V. Yioultsis; Nikolaos V. Kantartzis; Christos S. Antonopoulos; George K. Karagiannidis; Zaharias D. Zaharis

doi:10.1109/MOCAST57943.2023.10176899

DOA Estimation for 6G Communication Systems

Haya Al Kassir, Ioannis T. Rekanos, Pavlos I. Lazaridis, Traianos V. Yioultsis, Nikolaos V. Kantartzis, Christos S. Antonopoulos, George K. Karagiannidis, Zaharias D. Zaharis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

The objective of this study is to analyze and compare different neural network (NN) architectures as multi-class classifiers to estimate the direction of arrival (DOA) using a uniform linear array (ULA). The study specifically investigates the prediction skills of three NNs: feed forward NN (FFNN), convolutional NN (CNN), and residual NN (ResNet) when estimating incoming signal DOAs in a realistic ULA of (M = 16) elements under noisy conditions. The NNs are trained on a correlation matrix generated by a ULA to estimate the DOAs. The results of the simulations indicate that ResNet performs better than FFNN and CNN in accurately estimating incoming signals.

Original language	English
Title of host publication	2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	4
ISBN (Electronic)	9798350321074
ISBN (Print)	9798350321081
DOIs	https://doi.org/10.1109/MOCAST57943.2023.10176899
Publication status	Published - 17 Jul 2023
Event	12th International Conference on Modern Circuits and Systems Technologies - Athens, Greece Duration: 28 Jun 2023 → 30 Jun 2023 Conference number: 12

Conference

Conference	12th International Conference on Modern Circuits and Systems Technologies
Abbreviated title	MOCAST 2023
Country/Territory	Greece
City	Athens
Period	28/06/23 → 30/06/23

Access to Document

10.1109/MOCAST57943.2023.10176899Licence: Unspecified

Cite this

Kassir, H. A., Rekanos, I. T., Lazaridis, P. I., Yioultsis, T. V., Kantartzis, N. V., Antonopoulos, C. S., Karagiannidis, G. K., & Zaharis, Z. D. (2023). DOA Estimation for 6G Communication Systems. In 2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings [10176899] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MOCAST57943.2023.10176899

@inproceedings{27bf109588db48a091c1ad26fcc36e17,

title = "DOA Estimation for 6G Communication Systems",

abstract = "The objective of this study is to analyze and compare different neural network (NN) architectures as multi-class classifiers to estimate the direction of arrival (DOA) using a uniform linear array (ULA). The study specifically investigates the prediction skills of three NNs: feed forward NN (FFNN), convolutional NN (CNN), and residual NN (ResNet) when estimating incoming signal DOAs in a realistic ULA of (M = 16) elements under noisy conditions. The NNs are trained on a correlation matrix generated by a ULA to estimate the DOAs. The results of the simulations indicate that ResNet performs better than FFNN and CNN in accurately estimating incoming signals.",

keywords = "and residual NN (ResNet), convolutional NN (CNN), direction of arrival (DOA), feed forward NN (FFNN), neural network (NN), uniform linear array (ULA)",

author = "Kassir, {Haya Al} and Rekanos, {Ioannis T.} and Lazaridis, {Pavlos I.} and Yioultsis, {Traianos V.} and Kantartzis, {Nikolaos V.} and Antonopoulos, {Christos S.} and Karagiannidis, {George K.} and Zaharis, {Zaharias D.}",

note = "Funding Information: This research was supported by the European Union, through the Horizon 2020 Marie Sk{\l}odowska-Curie Innovative Training Networks Programme “Mobility and Training for beyond 5G Ecosystems (MOTOR5G)” under grant agreement no. 861219. Publisher Copyright: {\textcopyright} 2023 IEEE.; 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 ; Conference date: 28-06-2023 Through 30-06-2023",

year = "2023",

month = jul,

day = "17",

doi = "10.1109/MOCAST57943.2023.10176899",

language = "English",

isbn = "9798350321081",

booktitle = "2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings",

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

address = "United States",

}

Kassir, HA, Rekanos, IT, Lazaridis, PI, Yioultsis, TV, Kantartzis, NV, Antonopoulos, CS, Karagiannidis, GK & Zaharis, ZD 2023, DOA Estimation for 6G Communication Systems. in 2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings., 10176899, Institute of Electrical and Electronics Engineers Inc., 12th International Conference on Modern Circuits and Systems Technologies, Athens, Greece, 28/06/23. https://doi.org/10.1109/MOCAST57943.2023.10176899

DOA Estimation for 6G Communication Systems. / Kassir, Haya Al; Rekanos, Ioannis T.; Lazaridis, Pavlos I. et al.

2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. 10176899.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - DOA Estimation for 6G Communication Systems

AU - Kassir, Haya Al

AU - Rekanos, Ioannis T.

AU - Lazaridis, Pavlos I.

AU - Yioultsis, Traianos V.

AU - Kantartzis, Nikolaos V.

AU - Antonopoulos, Christos S.

AU - Karagiannidis, George K.

AU - Zaharis, Zaharias D.

N1 - Conference code: 12

PY - 2023/7/17

Y1 - 2023/7/17

N2 - The objective of this study is to analyze and compare different neural network (NN) architectures as multi-class classifiers to estimate the direction of arrival (DOA) using a uniform linear array (ULA). The study specifically investigates the prediction skills of three NNs: feed forward NN (FFNN), convolutional NN (CNN), and residual NN (ResNet) when estimating incoming signal DOAs in a realistic ULA of (M = 16) elements under noisy conditions. The NNs are trained on a correlation matrix generated by a ULA to estimate the DOAs. The results of the simulations indicate that ResNet performs better than FFNN and CNN in accurately estimating incoming signals.

AB - The objective of this study is to analyze and compare different neural network (NN) architectures as multi-class classifiers to estimate the direction of arrival (DOA) using a uniform linear array (ULA). The study specifically investigates the prediction skills of three NNs: feed forward NN (FFNN), convolutional NN (CNN), and residual NN (ResNet) when estimating incoming signal DOAs in a realistic ULA of (M = 16) elements under noisy conditions. The NNs are trained on a correlation matrix generated by a ULA to estimate the DOAs. The results of the simulations indicate that ResNet performs better than FFNN and CNN in accurately estimating incoming signals.

KW - and residual NN (ResNet)

KW - convolutional NN (CNN)

KW - direction of arrival (DOA)

KW - feed forward NN (FFNN)

KW - neural network (NN)

KW - uniform linear array (ULA)

UR - http://www.scopus.com/inward/record.url?scp=85166480284&partnerID=8YFLogxK

U2 - 10.1109/MOCAST57943.2023.10176899

DO - 10.1109/MOCAST57943.2023.10176899

M3 - Conference contribution

AN - SCOPUS:85166480284

SN - 9798350321081

BT - 2023 12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Modern Circuits and Systems Technologies

Y2 - 28 June 2023 through 30 June 2023

ER -

DOA Estimation for 6G Communication Systems

Abstract

Conference

Access to Document

Other files and links

Cite this