컨볼루션 신경망 기반의 능동소나 표적 식별

Recently, deep learning algorithms have good performance in various fields, but they are not actively applied to sonar systems. In this study, we carried out experiments to classify active sonar returns into a metal object such as a mine and a rock using a convolutional neural network which is one o...

Full description

Saved in:
Bibliographic Details
Published in한국정보통신학회논문지 Vol. 21; no. 10; pp. 1909 - 1916
Main Authors 김정훈(Jeong-Hun Kim), 최대성(Dae-Sung Choi), 이형수(Hyung-Soo Lee), 이정우(Jung-Woo Lee)
Format Journal Article
LanguageKorean
Published 한국정보통신학회 2017
Subjects
Online AccessGet full text
ISSN2234-4772
2288-4165
DOI10.6109/jkiice.2017.21.10.1909

Cover

More Information
Summary:Recently, deep learning algorithms have good performance in various fields, but they are not actively applied to sonar systems. In this study, we carried out experiments to classify active sonar returns into a metal object such as a mine and a rock using a convolutional neural network which is one of the deep learning algorithms. Data augmentation is applied on this paper to avoid overfitting and increase performance. And we analyzed performance variation depending on hyperparameter value and change of the number of training data through data augmentation. The experiments are performed with two training data; an aspect-angle independent and an aspect-angle dependent. As a result, the performances are 88.9% and 94.9% in aspect-angle independent and dependent, respectively. These are up to 4.5% point higher than the performance obtained by applying artificial neural network and support vector machine algorithm in the previous study. 최근 딥 러닝 알고리듬이 다양한 분야에 적용되어 좋은 성능을 내고 있지만, 소나시스템에는 아직 활발히 적용되지 않고 있다. 본 논문에서는 기뢰와 같은 금속 물체와 바위로부터 반사된 능동소나 수신음 데이터를 딥 러닝 알고리듬의 하나인 컨볼루션 신경망으로 식별하는 실험을 수행하였다. 과적합 방지 및 성능 향상을 위해 데이터 확장을 하였고, 확장 및 하이퍼파라미터 값 변화에 따른 성능 변화를 분석하였다. 훈련데이터를 수신각도에 독립적인 경우와 의존적인 경우로 나누어 실험을 수행하였고, 그 결과 각각 88.9%, 94.9%의 성능을 보였다. 이는 이전 연구에서 인공신경망 및 Support Vector Machine 알고리듬을 적용하여 얻은 성능보다 최대 4.5% 포인트 향상되었다.
Bibliography:KISTI1.1003/JNL.JAKO201732839400327
http://jkiice.org
ISSN:2234-4772
2288-4165
DOI:10.6109/jkiice.2017.21.10.1909