http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
지식증류 방안을 활용한 무인 군사 이미지 분류 AI 모델의 데이터 부족 및 경량화 모델 한계 극복
정자훈,송윤호,강인욱,류준열 한국산학기술학회 2024 한국산학기술학회논문지 Vol.25 No.3
Developing AI models for military unmanned systems requires consideration of the unique operational environment. Constraints like limited battery power and the high risk of destruction at the frontline necessitate restrictions on using costly, high-performance chips. In this study, we explored methods to enhance image classification performance of AI models under two key challenges. Firstly, constraints such as power and cost limit the utilization of high-capacity, high-performance models in unmanned systems. Secondly, there's a shortage of sufficient training data to ensure the performance of military AI models. To address these issues, we propose knowledge distillation. We selected EfficientNetB4 as the Teacher model, known for its superior performance despite high computational complexity, and SqueezeNet, ShuffleNetV2, and MobileNetV3 small as Student models. Through knowledge distillation, the high-accuracy knowledge of the Teacher model effectively enhanced the Student models, improving classification performance even under constraints. Such results are expected to enhance military utility by addressing the performance limitations of lightweight models applied to on device AI model in scenarios with limited training data.
XGBoost를 활용한 EBM 3D 프린터의 결함 예측
정자훈,Jeong, Jahoon 한국정보통신학회 2022 한국정보통신학회논문지 Vol.26 No.5
This paper is a study to find out the factors affecting the defects that occur during the use of Electron Beam Melting (EBM), one of the 3D printer output methods, through data analysis. By referring to factors identified as major causes of defects in previous studies, log files occurring between processes were analyzed and related variables were extracted. In addition, focusing on the fact that the data is time series data, the concept of a window was introduced to compose variables including data from all three layers. The dependent variable is a binary classification problem with the presence or absence of defects, and due to the problem that the proportion of defect layers is low (about 4%), balanced training data were created through the SMOTE technique. For the analysis, I use XGBoost using Gridsearch CV, and evaluate the classification performance based on the confusion matrix. I conclude results of the stuy by analyzing the importance of variables through SHAP values.
마이크로 모세관 유동 해석을 위한 CFD-VOF 모델 응용
정자훈(J. H. Jeong),임예훈(Y. H. Im),한상필(S. P. Han),석지원(J. W. Suk),김영득(Y. D. Kim) 한국전산유체공학회 2004 한국전산유체공학회 학술대회논문집 Vol.2004 No.-
The objective of this work is not only to perform feasibility studies on the CFD (computational fluid dynamics) analysis for the capillary system design but also to provide an enhanced understanding of the autonomous capillary flow. The capillary flow is evaluated by means of the commercial CFD software of FLUENT, which includes the VOF (volume-of-fluid) model for multiphase flow analysis. The effect of wall adhesion at fluid interfaces in contact with rigid boundaries is considered in terms of static contact angle. Feasibility studies are first performed, including mesh-resolution influence on pressure profile, which has a sudden increase at the liquid/gas interface. Then we perform both 2D and 3D simulations and examine the transient nature of the capillary flow. Analytical solutions are also derived for simple cases and compared with numerical results. Through this work, essential information on the capillary system design is brought out. Our efforts and initial success in numerical description of the microfluidic capillary flows enhance the fundamental understanding of the autonomous capillary flow and will eventually pave the road for full-scale, computer-aided design of microfltridic networks.
한정된 군사 데이터를 활용한 이미지 분류 AI의 성능 향상 방안: Grad-CAM을 활용한 준지도학습 적용
정자훈(Ja-Hoon Jeong),김용기(Yong-Gi Kim),나성중(Seong-Jung Na),류준열(Jun-yeol Ryu) 한국산학기술학회 2023 한국산학기술학회논문지 Vol.24 No.9
무인 지상 차량, 무인 비행체 등과 같은 자율 무인체계에 탑재된 AI 모델은 센서를 통해 획득한 적 인원, 무기체계 등을 탐지하고 분류한다. 이때 무기체계를 정확하게 분류하는 것은 화력 및 장애물의 운용 등 작전 수행에 있어 중요한 사안이다. AI 모델의 성능 향상을 위해서는 적 인원, 무기체계에 대한 학습데이터가 필요하다. 그러나 평시 적 무기체계에 대한 이미지 데이터 등을 확보하기 어려울 뿐만 아니라 위장, 부착 무장의 변경 등의 다양한 요인으로 인해 전쟁초기에는 평소 학습한 형태와 다른 상태의 적 무기체계를 분류해야 한다. 이 경우 초기에 확보된 부족한 적 무기체계 데이터를 학습하여 AI 모델의 분류성능을 향상해야 한다. 본 연구에서는 Grad-CAM을 활용하여 이미지 분류 모델이 학습한 데이터 영역을 분석하고, 분류를 위한 관심 구역에 맞춰 노이즈를 추가하는 준지도학습을 사용하여 적 무기체계에 대한 데이터가 부족한 상황에서도 AI 모델의 분류성능을 향상하는 방법을 제안하였다. 본 연구에서의 준지도학습을 적용했을 때 비교적 적은 수의 데이터를 학습시켜도 VGG-16과 MobilNetV2의 분류성능이 향상되는 것을 확인할 수 있었다. 향후 준지도학습을 적용하여 제한된 군사데이터 상황에서도 작전수행 역량을 향상시키는데 활용되기를 기대한다. AI models embedded in autonomous unmanned systems classify enemy personnel and weapon systems acquired through sensors. Accurate classification of weapon systems is crucial for operational tasks. Training data on enemy weapon systems are required to enhance the performance of AI models. On the other hand, Acquiring image data during peacetime is challenging. During the initial stages of war, the AI model must classify enemy weapon systems in states different from what it was trained on because of factors such as camouflage and changes in attached armaments. In such cases, it is necessary to improve the classification performance of AI models by training them on the limited data of enemy weapon systems acquired at the early stages. In this study, Grad-CAM was utilized to analyze the data regions learned by image classification models. A Weakly Supervised Learning approach was proposed, which added noise to the regions of interest for classification, addressing situations with a shortage of data for enemy weapon systems. The classification performance of VGG-16 and MobileNetV2 improved even when trained on a relatively small amount of data. Weakly supervised learning can improve operational capabilities, even in limited military data.
Does sulfasalazine have frequent side effects in adult-onset Still`s disease?
정자훈 ( Ja Hun Jung ),전재범 ( Jae Bum Jun ),유대현 ( Dae Hyun Yoo ),고희관 ( Hee Kwan Koh ),심승철 ( Seung Cheol Shim ),장대국 ( Dae Kook Chang ),김태환 ( Tae Hwan Kim ),정성수 ( Sung Soo Jung ),이인홍 ( In Hong Lee ),배상철 ( S 대한내과학회 1998 대한내과학회 추계학술대회 Vol.1998 No.1
Does Sulfasalazine have Frequent side Effects in Adult - onset Still`s Disease ?
정자훈(Ja Hun Jung),전재범(Jae Bum Jun),유대현(Dae Hyun Yoo),고희관(Hee Kwan Koh),정성수(Sung Soo Jung),이인홍(In Hong Lee),배상철(Sang Cheol Bae),김성윤(Seong Yoon Kim),(Seung Cheol Shim),(Dae Kook Chang),(Tae Hwan Kim) 대한내과학회 1998 대한내과학회 추계학술대회 Vol.55 No.-
소화기 탄 대비 재질별 관입깊이 해석을 위한 머신러닝 모델 분석
김종환,정자훈,정윤영 한국국방경영분석학회 2022 한국국방경영분석학회지 Vol.48 No.2
As small caliber ammunition in Soviet Union is continuously improved, attention about the protective performance of unmanned combat systems that perform the close combat has been increasing. Unlike the existing manned system, the unmanned combat system does not have a combatant inside, so it is necessary to study the depth of penetration for functional continuation of the main components. However, research on the penetration depth of the protective material against the small caliber threat is still insufficient. In order to develop a predictive model, this study conducted 119 times of real fire ballistic experiments, meas- ured the penetration depth of each target, and the relationship between threat and the penetration depth was analyzed. For this, 5.56mm K100 and 5.45mm 7N10 bullets were defined as threats, and ballistic experi- ments were performed in four different cases by setting uniformly rolled steel and aluminum plates as targets. For an accurate prediction, five machine learning regression models were applied, and the difference between the actual measured value and the predicted value was quantitatively assessed by applying the three criteria of R^2, RMSE, and MAPE. As a result, the performance of XGBoost model were recorded as 0.999, 0.025, and 0.229, showing high suitability for penetration depth research on the small caliber ammunitions.