HOME

Korea Society for Naval Science and Technology - Vol. 7 , No. 1

[Paper List] [ Prev] [Go to Volume List] [ Next]


[ Article ]
Journal of the KNST - Vol. 7, No. 1, pp. 78-84
Abbreviation: KNST
ISSN: 2635-4926 (Print)
Print publication date 31 Mar 2024
Received 24 Feb 2024 Revised 10 Mar 2024 Accepted 26 Mar 2024
DOI: https://doi.org/10.31818/JKNST.2024.3.7.1.78
엣지 컴퓨팅 환경을 위한 토널 주파수 탐지 기법
정대진^*

해군사관학교 인공지능학과 조교수
Tonal Frequency Detection Method for an Edge-computing Environment
Dae-Jin Jung^*
Assistant professor, Dept. of Artificial Intelligence, Republic of Korea Naval Academy

Correspondence to : ^*Dae-Jin Jung Department of Artificial Intelligence, Republic of Korea Naval Academy, Republic of Korea 1 Jungwon-ro, Jinhae-gu, Changwon-si, Gyungsangnam-do, 51704, Republic of Korea Tel: +82-55-907-5244 E-mail: djjung@navy.ac.kr
Ⓒ 2024 Korea Society for Naval Science & Technology

초록

해군 무인운용 체계에서 활용 가능한 저전력 고성능의 소나탐지 기술을 위하여, 본 연구에서는 엣지 컴퓨팅 환경에서 동작 가능한 딥러닝 기반의 로파그램 토널 탐지 기술을 제안한다. 일반적인 딥러닝 운용환경인 GPU를 활용하지 않는 엣지 컴퓨팅 환경에서도 효율적으로 토널 신호 탐지를 위한 설계 기법을 제시하고 상용의 엣지 컴퓨팅 환경에서 제안 기술의 효율성과 우수성을 확인하였다.

Abstract

In this study, a deep learning-based tonal frequency detection technology is proposed to operate in an edge computing environment, enabling low-power, high-performance sonar detection capabilities for naval unmanned systems. Design techniques for efficient tunnel signal detection are presented, even in edge computing environments without the typical deep learning hardware support, such as GPUs. Additionally, the effectiveness and superiority of the proposed technology are validated in commercial edge computing environments.


Keywords: Tonal Frequency, Passive SONAR, Edge-computing Environment, Deep Learning 키워드: 토널 주파수, 수동 소나, 엣지 컴퓨팅 환경, 딥 러닝

References


1.	R. P. Gorman and T. J. Sejnowski, “Analysis of Hidden Units in a Layered Network Trained to Classify Sonar Targets,” Neural Networks, Vol. 1, No. 1, pp. 75-89, 1988.
2.	A. Galusha, J. Dale, J. Keller, and A. Zare, “Deep Convolutional Neural Network Target Classification for Underwater Synthetic Aperture Sonar Imagery,” in Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV, Vol. 11012, International Society for Optics and Photonics, 1101205, 2019.
3.	D. Kim, “Use of One-shot Learning for Automatic Target Recognition of Surface Ship Noise”, Journal of KNST, Vol. 6, No.3, pp. 221-226, 2023.
4.	J. Park, and D.-J. Jung, “Deep Convolutional Neural Network Architectures for Tonal Frequency Identification in a Lofargram,” International Journal of Control, Automation and Systems, Vol. 19, pp. 1103-1112, 2021.
5.	J. Park et al. "Multi-object Tracking on SWIR Images for City Surveillance in an Edge-computing Environment,” Sensors, Vol. 23, No. 14, 6373, 2023.
6.	J. H. Shapiro and T. J. Green, “Performance of Split-window Multipass-mean Noise Spectral Estimators,” in IEEE Transactions on Aerospace and Electronic Systems, Vol. 36, No. 4, pp. 1360-1370, Oct. 2000.