Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations

Ioannis Mallioras; Zaharias D. Zaharis; Pavlos Lazaridis; Traianos V. Yioultsis; Nikolaos V. Kantartzis; Ioannis P. Chochliouros

doi:10.1007/978-3-031-08341-9_9

Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations

Ioannis Mallioras, Zaharias D. Zaharis, Pavlos Lazaridis, Traianos V. Yioultsis, Nikolaos V. Kantartzis, Ioannis P. Chochliouros

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

Abstract

Future wireless networks depend on the development of new mechanisms that can increase the efficiency of the network. Antenna array adaptive beamforming (ABF) is an antenna operation that can be significantly improved with the use of machine learning. In this paper, a deterministic beamforming technique is compared with two different types of neural networks (NNs). These are the non-linear autoregressive network with exogenous inputs (NARX) and the recurrent NN (RNN) with long short-term memory (LSTM) units. To train the NNs, we produce a dataset using the minimum variance distortionless algorithm (MVDR) applied to a realistic antenna array. Using grid search, we find the best architecture for both NNs. Then, we train the final models and evaluate them by comparing their accuracy to that of the MVDR algorithm. We demonstrate how the use of NNs is preferable to that of deterministic algorithms as they appear to maintain high accuracy while having a much lower response time than that of deterministic algorithms. The RNN with LSTM units is the most promising out of the two NN models as it achieves higher accuracy with a slightly shorter training time.

Original language	English
Title of host publication	Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops
Subtitle of host publication	MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings
Editors	Ilias Maglogiannis, Lazaros Iliadis, John Macintyre, Paulo Cortez
Publisher	Springer, Cham
Pages	98-107
Number of pages	10
Volume	652
ISBN (Electronic)	9783031083419
ISBN (Print)	9783031083402, 9783031083433
DOIs	https://doi.org/10.1007/978-3-031-08341-9_9
Publication status	Published - 17 Jun 2022
Event	11th Mining Humanistic Data Workshop, MHDW 2022, 7th 5G-Putting Intelligence to the Network Edge Workshop, 5G-PINE 2022, 1st workshop on AI in Energy, Building and Micro-Grids, AIBMG 2022, 1st Workshop/Special Session on Machine Learning and Big Data in Health Care, ML@HC 2022 and 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics, AIBEI 2022 held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022 - Hersonissos, Greece Duration: 17 Jun 2022 → 20 Jun 2022

Publication series

Name	IFIP Advances in Information and Communication Technology
Publisher	Springer
Volume	652 IFIP
ISSN (Print)	1868-4238
ISSN (Electronic)	1868-422X

Conference

Conference	11th Mining Humanistic Data Workshop, MHDW 2022, 7th 5G-Putting Intelligence to the Network Edge Workshop, 5G-PINE 2022, 1st workshop on AI in Energy, Building and Micro-Grids, AIBMG 2022, 1st Workshop/Special Session on Machine Learning and Big Data in Health Care, ML@HC 2022 and 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics, AIBEI 2022 held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022
Abbreviated title	MHDW 2022 / 5G-PINE 2022 / AIBMG 2022 / ML@HC 2022 / AIBEI 2022 / IFIP WG / AIAI 2022
Country/Territory	Greece
City	Hersonissos
Period	17/06/22 → 20/06/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-08341-9_9Licence: Unspecified

AAMAccepted author manuscript, 1.21 MBLicence: Unspecified

Cite this

Mallioras, I., Zaharis, Z. D., Lazaridis, P., Yioultsis, T. V., Kantartzis, N. V., & Chochliouros, I. P. (2022). Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations. In I. Maglogiannis, L. Iliadis, J. Macintyre, & P. Cortez (Eds.), Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings (Vol. 652, pp. 98-107). (IFIP Advances in Information and Communication Technology; Vol. 652 IFIP). Springer, Cham. https://doi.org/10.1007/978-3-031-08341-9_9

Mallioras, Ioannis ; Zaharis, Zaharias D. ; Lazaridis, Pavlos et al. / Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations. Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings. editor / Ilias Maglogiannis ; Lazaros Iliadis ; John Macintyre ; Paulo Cortez. Vol. 652 Springer, Cham, 2022. pp. 98-107 (IFIP Advances in Information and Communication Technology).

@inproceedings{f1c394bd721544ea8ee51ec9f55f1553,

title = "Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations",

abstract = "Future wireless networks depend on the development of new mechanisms that can increase the efficiency of the network. Antenna array adaptive beamforming (ABF) is an antenna operation that can be significantly improved with the use of machine learning. In this paper, a deterministic beamforming technique is compared with two different types of neural networks (NNs). These are the non-linear autoregressive network with exogenous inputs (NARX) and the recurrent NN (RNN) with long short-term memory (LSTM) units. To train the NNs, we produce a dataset using the minimum variance distortionless algorithm (MVDR) applied to a realistic antenna array. Using grid search, we find the best architecture for both NNs. Then, we train the final models and evaluate them by comparing their accuracy to that of the MVDR algorithm. We demonstrate how the use of NNs is preferable to that of deterministic algorithms as they appear to maintain high accuracy while having a much lower response time than that of deterministic algorithms. The RNN with LSTM units is the most promising out of the two NN models as it achieves higher accuracy with a slightly shorter training time.",

keywords = "Adaptive beamforming, Antenna array, Long short-term memory (LSTM), Neural network (NN), Non-linear autoregressive network with exogenous inputs (NARX), Recurrent neural network (RNN)",

author = "Ioannis Mallioras and Zaharis, {Zaharias D.} and Pavlos Lazaridis and Yioultsis, {Traianos V.} and Kantartzis, {Nikolaos V.} and Chochliouros, {Ioannis P.}",

note = "Funding Information: Acknowledgements. This research was supported by the European Union, partially 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, and partially through the Horizon 2020 Marie Sk{\l}odowska-Curie Research and Innovation Staff Exchange Programme “Research Collaboration and Mobility for Beyond 5G Future Wireless Networks (RECOMBINE)” under grant agreement no. 872857. Funding Information: This research was supported by the European Union, partially through the Horizon 2020 Marie Sk{\l}odowska-Curie Innovative Training Networks Programme “Mobil-ity and Training for beyond 5G Ecosystems (MOTOR5G)” under grant agreement no. 861219, and partially through the Horizon 2020 Marie Sk{\l}odowska-Curie Research and Innovation Staff Exchange Programme “Research Collaboration and Mobility for Beyond 5G Future Wireless Networks (RECOMBINE)” under grant agreement no. 872857. Publisher Copyright: {\textcopyright} 2022, IFIP International Federation for Information Processing.; 11th Mining Humanistic Data Workshop, MHDW 2022, 7th 5G-Putting Intelligence to the Network Edge Workshop, 5G-PINE 2022, 1st workshop on AI in Energy, Building and Micro-Grids, AIBMG 2022, 1st Workshop/Special Session on Machine Learning and Big Data in Health Care, ML@HC 2022 and 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics, AIBEI 2022 held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022, MHDW 2022 / 5G-PINE 2022 / AIBMG 2022 / ML@HC 2022 / AIBEI 2022 / IFIP WG / AIAI 2022 ; Conference date: 17-06-2022 Through 20-06-2022",

year = "2022",

month = jun,

day = "17",

doi = "10.1007/978-3-031-08341-9_9",

language = "English",

isbn = "9783031083402",

volume = "652",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer, Cham",

pages = "98--107",

editor = "Ilias Maglogiannis and Lazaros Iliadis and John Macintyre and Paulo Cortez",

booktitle = "Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops",

address = "Switzerland",

}

Mallioras, I, Zaharis, ZD, Lazaridis, P, Yioultsis, TV, Kantartzis, NV & Chochliouros, IP 2022, Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations. in I Maglogiannis, L Iliadis, J Macintyre & P Cortez (eds), Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings. vol. 652, IFIP Advances in Information and Communication Technology, vol. 652 IFIP, Springer, Cham, pp. 98-107, 11th Mining Humanistic Data Workshop, MHDW 2022, 7th 5G-Putting Intelligence to the Network Edge Workshop, 5G-PINE 2022, 1st workshop on AI in Energy, Building and Micro-Grids, AIBMG 2022, 1st Workshop/Special Session on Machine Learning and Big Data in Health Care, ML@HC 2022 and 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics, AIBEI 2022 held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022, Hersonissos, Greece, 17/06/22. https://doi.org/10.1007/978-3-031-08341-9_9

Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations. / Mallioras, Ioannis; Zaharis, Zaharias D.; Lazaridis, Pavlos et al.

Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings. ed. / Ilias Maglogiannis; Lazaros Iliadis; John Macintyre; Paulo Cortez. Vol. 652 Springer, Cham, 2022. p. 98-107 (IFIP Advances in Information and Communication Technology; Vol. 652 IFIP).

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

TY - GEN

T1 - Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations

AU - Mallioras, Ioannis

AU - Zaharis, Zaharias D.

AU - Lazaridis, Pavlos

AU - Yioultsis, Traianos V.

AU - Kantartzis, Nikolaos V.

AU - Chochliouros, Ioannis P.

N1 - Funding Information: Acknowledgements. This research was supported by the European Union, partially through the Horizon 2020 Marie Skłodowska-Curie Innovative Training Networks Programme “Mobility and Training for beyond 5G Ecosystems (MOTOR5G)” under grant agreement no. 861219, and partially through the Horizon 2020 Marie Skłodowska-Curie Research and Innovation Staff Exchange Programme “Research Collaboration and Mobility for Beyond 5G Future Wireless Networks (RECOMBINE)” under grant agreement no. 872857. Funding Information: This research was supported by the European Union, partially through the Horizon 2020 Marie Skłodowska-Curie Innovative Training Networks Programme “Mobil-ity and Training for beyond 5G Ecosystems (MOTOR5G)” under grant agreement no. 861219, and partially through the Horizon 2020 Marie Skłodowska-Curie Research and Innovation Staff Exchange Programme “Research Collaboration and Mobility for Beyond 5G Future Wireless Networks (RECOMBINE)” under grant agreement no. 872857. Publisher Copyright: © 2022, IFIP International Federation for Information Processing.

PY - 2022/6/17

Y1 - 2022/6/17

N2 - Future wireless networks depend on the development of new mechanisms that can increase the efficiency of the network. Antenna array adaptive beamforming (ABF) is an antenna operation that can be significantly improved with the use of machine learning. In this paper, a deterministic beamforming technique is compared with two different types of neural networks (NNs). These are the non-linear autoregressive network with exogenous inputs (NARX) and the recurrent NN (RNN) with long short-term memory (LSTM) units. To train the NNs, we produce a dataset using the minimum variance distortionless algorithm (MVDR) applied to a realistic antenna array. Using grid search, we find the best architecture for both NNs. Then, we train the final models and evaluate them by comparing their accuracy to that of the MVDR algorithm. We demonstrate how the use of NNs is preferable to that of deterministic algorithms as they appear to maintain high accuracy while having a much lower response time than that of deterministic algorithms. The RNN with LSTM units is the most promising out of the two NN models as it achieves higher accuracy with a slightly shorter training time.

AB - Future wireless networks depend on the development of new mechanisms that can increase the efficiency of the network. Antenna array adaptive beamforming (ABF) is an antenna operation that can be significantly improved with the use of machine learning. In this paper, a deterministic beamforming technique is compared with two different types of neural networks (NNs). These are the non-linear autoregressive network with exogenous inputs (NARX) and the recurrent NN (RNN) with long short-term memory (LSTM) units. To train the NNs, we produce a dataset using the minimum variance distortionless algorithm (MVDR) applied to a realistic antenna array. Using grid search, we find the best architecture for both NNs. Then, we train the final models and evaluate them by comparing their accuracy to that of the MVDR algorithm. We demonstrate how the use of NNs is preferable to that of deterministic algorithms as they appear to maintain high accuracy while having a much lower response time than that of deterministic algorithms. The RNN with LSTM units is the most promising out of the two NN models as it achieves higher accuracy with a slightly shorter training time.

KW - Adaptive beamforming

KW - Antenna array

KW - Long short-term memory (LSTM)

KW - Neural network (NN)

KW - Non-linear autoregressive network with exogenous inputs (NARX)

KW - Recurrent neural network (RNN)

UR - http://www.scopus.com/inward/record.url?scp=85133226074&partnerID=8YFLogxK

UR - https://doi.org/10.1007/978-3-031-08341-9

U2 - 10.1007/978-3-031-08341-9_9

DO - 10.1007/978-3-031-08341-9_9

M3 - Conference contribution

AN - SCOPUS:85133226074

SN - 9783031083402

SN - 9783031083433

VL - 652

T3 - IFIP Advances in Information and Communication Technology

SP - 98

EP - 107

BT - Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops

A2 - Maglogiannis, Ilias

A2 - Iliadis, Lazaros

A2 - Macintyre, John

A2 - Cortez, Paulo

PB - Springer, Cham

T2 - 11th Mining Humanistic Data Workshop, MHDW 2022, 7th 5G-Putting Intelligence to the Network Edge Workshop, 5G-PINE 2022, 1st workshop on AI in Energy, Building and Micro-Grids, AIBMG 2022, 1st Workshop/Special Session on Machine Learning and Big Data in Health Care, ML@HC 2022 and 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics, AIBEI 2022 held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022

Y2 - 17 June 2022 through 20 June 2022

ER -

Mallioras I, Zaharis ZD, Lazaridis P, Yioultsis TV, Kantartzis NV, Chochliouros IP. Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations. In Maglogiannis I, Iliadis L, Macintyre J, Cortez P, editors, Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings. Vol. 652. Springer, Cham. 2022. p. 98-107. (IFIP Advances in Information and Communication Technology). Epub 2022 Jun 16. doi: 10.1007/978-3-031-08341-9_9

Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

MOTOR5G: H2020 ITN MOTOR5G : MObility and Training fOR beyond 5G Ecosystems

H2020 RISE RECOMBINE: Research Collaboration and Mobility for Beyond 5G Future Wireless Networks

Cite this

Comparative Study of a Deterministic Adaptive Beamforming Technique with Neural Network Implementations

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

MOTOR5G: H2020 ITN MOTOR5G : MObility and Training fOR beyond 5G Ecosystems

H2020 RISE RECOMBINE: Research Collaboration and Mobility for Beyond 5G Future Wireless Networks

Cite this