Detail View

A lightweight deep-learning radar gesture recognition based on a structured pruning-NAS
Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

DC Field Value Language
dc.contributor.author Son, Eungang -
dc.contributor.author Song, Seungeon -
dc.contributor.author Lee, Jonghun -
dc.date.accessioned 2024-02-27T14:40:16Z -
dc.date.available 2024-02-27T14:40:16Z -
dc.date.created 2024-02-22 -
dc.date.issued 2023-10-13 -
dc.identifier.isbn 9798350313277 -
dc.identifier.issn 2162-1241 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/47989 -
dc.description.abstract This paper proposes a structured pruning-network architecture search (NAS) algorithm for a lightweight deep-learning radar foot gesture recognition in a conventional lightweight deep-learning models to quantitatively evaluate its performance. Our goal is to recognize foot gestures using a CW radar, generate their STFT unique signatures, and build a foot gesture recognition system that could be implemented on an edge device. The proposed scheme shows that model size and FLOPs were reduced, and a sub-optimal lightweight model for a foot gesture recognition device based on MobileNet was obtained with a slight decrease in accuracy. © 2023 IEEE. -
dc.language English -
dc.publisher 한국통신학회 (The Korean Institute of Communications and Information Sciences, KICS) -
dc.relation.ispartof International Conference on ICT Convergence -
dc.title A lightweight deep-learning radar gesture recognition based on a structured pruning-NAS -
dc.type Conference Paper -
dc.identifier.doi 10.1109/ICTC58733.2023.10393376 -
dc.identifier.scopusid 2-s2.0-85184565320 -
dc.identifier.bibliographicCitation Son, Eungang. (2023-10-13). A lightweight deep-learning radar gesture recognition based on a structured pruning-NAS. International Conference on Information and Communication Technology Convergence, ICTC 2023, 1729–1731. doi: 10.1109/ICTC58733.2023.10393376 -
dc.identifier.url https://journal-home.s3.ap-northeast-2.amazonaws.com/site/ictc2023a/ICTC+2023+Final+Program_v12.pdf -
dc.citation.conferenceDate 2023-10-11 -
dc.citation.conferencePlace KO -
dc.citation.conferencePlace 제주 -
dc.citation.endPage 1731 -
dc.citation.startPage 1729 -
dc.citation.title International Conference on Information and Communication Technology Convergence, ICTC 2023 -
Show Simple Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Related Researcher

송승언
Song, Seungeon송승언

Division of Mobility Technology

read more

Total Views & Downloads