DC Field | Value | Language |
---|---|---|
dc.contributor.author | 최순현 | ko |
dc.contributor.author | 조인철 | ko |
dc.contributor.author | 현준석 | ko |
dc.contributor.author | 최원준 | ko |
dc.contributor.author | 손성환 | ko |
dc.contributor.author | 최정우 | ko |
dc.date.accessioned | 2024-07-30T02:00:06Z | - |
dc.date.available | 2024-07-30T02:00:06Z | - |
dc.date.created | 2024-04-12 | - |
dc.date.issued | 2024-04 | - |
dc.identifier.citation | 한국군사과학기술학회지, v.27, no.2, pp.189 - 196 | - |
dc.identifier.issn | 1598-9127 | - |
dc.identifier.uri | http://hdl.handle.net/10203/321183 | - |
dc.description.abstract | Classification of drones and birds is challenging due to diverse flight patterns and limited data availability. Previous research has focused on identifying the flight patterns of unmanned aerial vehicles by emphasizingdynamic features such as speed and heading. However, this approach tends to neglect crucial spatial information,making accurate discrimination of unmanned aerial vehicle characteristics challenging. Furthermore, training methodsfor situations with imbalanced data among classes have not been proposed by traditional machine learningtechniques. In this paper, we propose a data processing method that preserves angle information while maintainingpositional details, enabling the deep learning model to better comprehend positional information of drones. Additionally, we introduce a training technique to address the issue of data imbalance. | - |
dc.language | Korean | - |
dc.publisher | 한국군사과학기술학회 | - |
dc.title | 딥 러닝 기법을 이용한 무인기 표적 분류 방법 연구 | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.citation.volume | 27 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 189 | - |
dc.citation.endingpage | 196 | - |
dc.citation.publicationname | 한국군사과학기술학회지 | - |
dc.identifier.kciid | ART003063079 | - |
dc.contributor.localauthor | 최정우 | - |
dc.contributor.nonIdAuthor | 조인철 | - |
dc.contributor.nonIdAuthor | 현준석 | - |
dc.contributor.nonIdAuthor | 최원준 | - |
dc.contributor.nonIdAuthor | 손성환 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.