An Efficient Nocturnal Scenarios Beamforming Based on Multi-Modal Enhanced by Object Detection

Jiali NIE; Yuanhao CUI; Tiankuo YU; Junsheng MU; Weijie YUAN; Xiaojun JING

doi:10.1109/GCWkshps58843.2023.10464587

An Efficient Nocturnal Scenarios Beamforming Based on Multi-Modal Enhanced by Object Detection

Jiali NIE, Yuanhao CUI^*, Tiankuo YU, Junsheng MU, Weijie YUAN, Xiaojun JING

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

Abstract

The progress in integrated sensing and communication(ISAC) technologies has facilitated the application of sensing data for beamforming, resulting in a reduction of training overhead. Nevertheless, the diminished visibility during nocturnal scenarios poses a significant impact on beamforming performance. In this research, we proposed a machine-learning approach that relies on object detection and multimodal fusion to achieve efficient beamforming prediction by leveraging visual and positional data collected from nighttime vehicle communication scenarios. Experimental findings reveal that our developed model achieves the top-1 accuracy exceeding 60% and top-5 accuracy approaching 100%, all the while substantially mitigating the training overhead.

Original language	English
Title of host publication	2023 IEEE Globecom Workshops, GC Wkshps 2023
Publisher	IEEE
Pages	515-520
Number of pages	6
ISBN (Electronic)	9798350370218
DOIs	https://doi.org/10.1109/GCWkshps58843.2023.10464587
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE Globecom Workshops, GC Wkshps 2023 - Kuala Lumpur, Malaysia Duration: 4 Dec 2023 → 8 Dec 2023

Conference

Conference	2023 IEEE Globecom Workshops, GC Wkshps 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	4/12/23 → 8/12/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Deep learning
Integrated sensing and communications
Multi-modal assited beamforming
Object detection

Access to Document

10.1109/GCWkshps58843.2023.10464587

Cite this

@inproceedings{97a56dc1c2a34ac2a14b76a9e0d18e6f,

title = "An Efficient Nocturnal Scenarios Beamforming Based on Multi-Modal Enhanced by Object Detection",

abstract = "The progress in integrated sensing and communication(ISAC) technologies has facilitated the application of sensing data for beamforming, resulting in a reduction of training overhead. Nevertheless, the diminished visibility during nocturnal scenarios poses a significant impact on beamforming performance. In this research, we proposed a machine-learning approach that relies on object detection and multimodal fusion to achieve efficient beamforming prediction by leveraging visual and positional data collected from nighttime vehicle communication scenarios. Experimental findings reveal that our developed model achieves the top-1 accuracy exceeding 60% and top-5 accuracy approaching 100%, all the while substantially mitigating the training overhead.",

keywords = "Deep learning, Integrated sensing and communications, Multi-modal assited beamforming, Object detection",

author = "Jiali NIE and Yuanhao CUI and Tiankuo YU and Junsheng MU and Weijie YUAN and Xiaojun JING",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Globecom Workshops, GC Wkshps 2023 ; Conference date: 04-12-2023 Through 08-12-2023",

year = "2023",

doi = "10.1109/GCWkshps58843.2023.10464587",

language = "English",

pages = "515--520",

booktitle = "2023 IEEE Globecom Workshops, GC Wkshps 2023",

publisher = "IEEE",

}

TY - GEN

T1 - An Efficient Nocturnal Scenarios Beamforming Based on Multi-Modal Enhanced by Object Detection

AU - NIE, Jiali

AU - CUI, Yuanhao

AU - YU, Tiankuo

AU - MU, Junsheng

AU - YUAN, Weijie

AU - JING, Xiaojun

PY - 2023

Y1 - 2023

N2 - The progress in integrated sensing and communication(ISAC) technologies has facilitated the application of sensing data for beamforming, resulting in a reduction of training overhead. Nevertheless, the diminished visibility during nocturnal scenarios poses a significant impact on beamforming performance. In this research, we proposed a machine-learning approach that relies on object detection and multimodal fusion to achieve efficient beamforming prediction by leveraging visual and positional data collected from nighttime vehicle communication scenarios. Experimental findings reveal that our developed model achieves the top-1 accuracy exceeding 60% and top-5 accuracy approaching 100%, all the while substantially mitigating the training overhead.

AB - The progress in integrated sensing and communication(ISAC) technologies has facilitated the application of sensing data for beamforming, resulting in a reduction of training overhead. Nevertheless, the diminished visibility during nocturnal scenarios poses a significant impact on beamforming performance. In this research, we proposed a machine-learning approach that relies on object detection and multimodal fusion to achieve efficient beamforming prediction by leveraging visual and positional data collected from nighttime vehicle communication scenarios. Experimental findings reveal that our developed model achieves the top-1 accuracy exceeding 60% and top-5 accuracy approaching 100%, all the while substantially mitigating the training overhead.

KW - Deep learning

KW - Integrated sensing and communications

KW - Multi-modal assited beamforming

KW - Object detection

UR - http://www.scopus.com/inward/record.url?scp=85190309990&partnerID=8YFLogxK

U2 - 10.1109/GCWkshps58843.2023.10464587

DO - 10.1109/GCWkshps58843.2023.10464587

M3 - Conference paper (refereed)

AN - SCOPUS:85190309990

SP - 515

EP - 520

BT - 2023 IEEE Globecom Workshops, GC Wkshps 2023

PB - IEEE

T2 - 2023 IEEE Globecom Workshops, GC Wkshps 2023

Y2 - 4 December 2023 through 8 December 2023

ER -

An Efficient Nocturnal Scenarios Beamforming Based on Multi-Modal Enhanced by Object Detection

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this