An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field

Sigurd S. Petersen; Emil Lytje-Dorfman; Rune Drongesen; Jacob Vitfell Køpke; Puchu Li; Zhinong Ying; Ming Shen

doi:10.1109/iWAT64079.2025.10931217

An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field

Sigurd S. Petersen, Emil Lytje-Dorfman, Rune Drongesen, Jacob Vitfell Køpke, Puchu Li, Zhinong Ying, Ming Shen

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

Abstract

This paper focuses on using Reconfigurable Intelligent Surfaces (RIS) for gesture recognition through AI with experimental data. Using a mono-static setup of a RIS, 4.9 – 5 GHz radio waves can be directly beamed at a hand, which reflects the incident wave depending on the hand gesture. The received reflection signal from the hand is processed and given to a Convolutional Neural Network (CNN). The CNN performs with a prediction accuracy of 97.65%. Through this it is shown that it is possible to use an AI-powered RIS to recognise simple hand gestures, thereby adding to hand gesture recognition methods, and expanding on integrated sensing and communication (ISAC).

Originalsprog	Engelsk
Titel	2025 IEEE International Workshop on Antenna Technology, iWAT 2025
Antal sider	4
Forlag	IEEE Communications Society
Publikationsdato	21 feb. 2025
Sider	1-4
Artikelnummer	10931217
ISBN (Trykt)	979-8-3315-2737-2
ISBN (Elektronisk)	9798331527365
DOI	https://doi.org/10.1109/iWAT64079.2025.10931217
Status	Udgivet - 21 feb. 2025
Begivenhed	2025 IEEE International Workshop on Antenna Technology (iWAT) - Cocoa Beach, FL, USA Varighed: 19 feb. 2025 → 21 feb. 2025

Konference

Konference	2025 IEEE International Workshop on Antenna Technology (iWAT)
Lokation	Cocoa Beach, FL, USA
Periode	19/02/2025 → 21/02/2025

Adgang til dokumentet

10.1109/iWAT64079.2025.10931217

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

Citationsformater

@inproceedings{66bb7d74a6e14967ac056f751f796c8a,

title = "An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field",

abstract = "This paper focuses on using Reconfigurable Intelligent Surfaces (RIS) for gesture recognition through AI with experimental data. Using a mono-static setup of a RIS, 4.9 – 5 GHz radio waves can be directly beamed at a hand, which reflects the incident wave depending on the hand gesture. The received reflection signal from the hand is processed and given to a Convolutional Neural Network (CNN). The CNN performs with a prediction accuracy of 97.65%. Through this it is shown that it is possible to use an AI-powered RIS to recognise simple hand gestures, thereby adding to hand gesture recognition methods, and expanding on integrated sensing and communication (ISAC).",

keywords = "Accuracy, Artificial intelligence, Convolutional neural networks, Gesture recognition, Hands, Integrated sensing and communication, Reconfigurable intelligent surfaces, Reflector antennas, Residual neural networks, Spectrogram, Joint Sensing and Communication, Artificial Intelligence, Reflective Intelligent Surface, Integrated Sensing and Communications, hand gesture recognition",

author = "Petersen, {Sigurd S.} and Emil Lytje-Dorfman and Rune Drongesen and K{\o}pke, {Jacob Vitfell} and Puchu Li and Zhinong Ying and Ming Shen",

year = "2025",

month = feb,

day = "21",

doi = "10.1109/iWAT64079.2025.10931217",

language = "English",

isbn = "979-8-3315-2737-2",

pages = "1--4",

booktitle = "2025 IEEE International Workshop on Antenna Technology, iWAT 2025",

publisher = "IEEE Communications Society",

address = "United States",

note = "2025 IEEE International Workshop on Antenna Technology (iWAT) ; Conference date: 19-02-2025 Through 21-02-2025",

}

Petersen, SS, Lytje-Dorfman, E, Drongesen, R, Køpke, JV, Li, P , Ying, Z & Shen, M 2025, An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field. i 2025 IEEE International Workshop on Antenna Technology, iWAT 2025., 10931217, IEEE Communications Society, s. 1-4, 2025 IEEE International Workshop on Antenna Technology (iWAT), 19/02/2025. https://doi.org/10.1109/iWAT64079.2025.10931217

An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field. / Petersen, Sigurd S.; Lytje-Dorfman, Emil; Drongesen, Rune et al.
2025 IEEE International Workshop on Antenna Technology, iWAT 2025. IEEE Communications Society, 2025. s. 1-4 10931217.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field

AU - Petersen, Sigurd S.

AU - Lytje-Dorfman, Emil

AU - Drongesen, Rune

AU - Køpke, Jacob Vitfell

AU - Li, Puchu

AU - Ying, Zhinong

AU - Shen, Ming

PY - 2025/2/21

Y1 - 2025/2/21

N2 - This paper focuses on using Reconfigurable Intelligent Surfaces (RIS) for gesture recognition through AI with experimental data. Using a mono-static setup of a RIS, 4.9 – 5 GHz radio waves can be directly beamed at a hand, which reflects the incident wave depending on the hand gesture. The received reflection signal from the hand is processed and given to a Convolutional Neural Network (CNN). The CNN performs with a prediction accuracy of 97.65%. Through this it is shown that it is possible to use an AI-powered RIS to recognise simple hand gestures, thereby adding to hand gesture recognition methods, and expanding on integrated sensing and communication (ISAC).

AB - This paper focuses on using Reconfigurable Intelligent Surfaces (RIS) for gesture recognition through AI with experimental data. Using a mono-static setup of a RIS, 4.9 – 5 GHz radio waves can be directly beamed at a hand, which reflects the incident wave depending on the hand gesture. The received reflection signal from the hand is processed and given to a Convolutional Neural Network (CNN). The CNN performs with a prediction accuracy of 97.65%. Through this it is shown that it is possible to use an AI-powered RIS to recognise simple hand gestures, thereby adding to hand gesture recognition methods, and expanding on integrated sensing and communication (ISAC).

KW - Accuracy

KW - Artificial intelligence

KW - Convolutional neural networks

KW - Gesture recognition

KW - Hands

KW - Integrated sensing and communication

KW - Reconfigurable intelligent surfaces

KW - Reflector antennas

KW - Residual neural networks

KW - Spectrogram

KW - Joint Sensing and Communication

KW - Artificial Intelligence

KW - Reflective Intelligent Surface

KW - Integrated Sensing and Communications

KW - hand gesture recognition

UR - http://www.scopus.com/inward/record.url?scp=105002271319&partnerID=8YFLogxK

U2 - 10.1109/iWAT64079.2025.10931217

DO - 10.1109/iWAT64079.2025.10931217

M3 - Article in proceeding

SN - 979-8-3315-2737-2

SP - 1

EP - 4

BT - 2025 IEEE International Workshop on Antenna Technology, iWAT 2025

PB - IEEE Communications Society

T2 - 2025 IEEE International Workshop on Antenna Technology (iWAT)

Y2 - 19 February 2025 through 21 February 2025

ER -

An AI-Powered RIS Technology for Hand Gesture Recognition in the Radiating Near Field

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Citationsformater