• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.687-688
• /
• 2023

Bone age assessment is a crucial task in pediatric radiology for assessing growth and development in children. In this paper, we explore the potential of Vision Transformer, a state-of-the-art deep learning model, for bone age assessment using X-ray images. We generate heatmap outputs using a pre-trained Vision Transformer model on a publicly available dataset of hand X-ray images and show that the model tends to focus on the overall hand and only the bone part of the image, indicating its potential for accurately identifying the regions of interest for bone age assessment without the need for pre-processing to remove background noise. We also suggest two methods for extracting the region of interest from the heatmap output. Our study suggests that Vision Transformer holds great potential for bone age assessment using X-ray images, as it can provide accurate and interpretable output that may assist radiologists in identifying potential abnormalities or areas of interest in the X-ray image.

• Journal of Ginseng Research
• /
• 제35권4호
• /
• pp.497-503
• /
• 2011

In order to enhance bioactive functionalities of ginseng, an acid impregnation processing was applied as a pre-treatment in producing red ginseng. Acid impregnation studies were conducted, and acids (ascorbic, malic, and citric acid) were selected. The optimal concentration of each acid was investigated in this study in terms of ginsenoside contents. The most concerned ginsenoside, $Rg_3$ was increased by ascorbic, malic, and citric acid pre-treated red ginseng up to 1 M acid concentration. In the case of ascorbic acid pre-treated red ginseng, $Rg_2$ concentration was increased depending on acid concentrations. Citric acid pre-treatment enhanced $Rg_2$, $Rg_3$, and $Rh_1+Rh_2$ formation in red ginseng. Therefore, ginsenoside patterns in red ginseng could be changed by acid impregnation pre-treatment depending on acid concentration and acid types. This research is expected to contribute to the development of the ginseng industry via new red ginseng products with selective and intensified functionality.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2008년도 춘계학술대회 논문집
• /
• pp.439-443
• /
• 2008

We investigate the mechanical behavior of a pre-heat treated steel of ESW95, which is being used for automotive parts including tie-rods to save manufacturing cost and enhance product quality. SCM435 is also investigated to reveal the characteristics of the pre-heat treated steel tested. AFDEX/MAT is used to extract the true stress-strain curve over the large strain with higher accuracy. It has been found that ESW95 has very week strain-hardening behavior which can be negligible compared with SCM435 and that the initial yield strength is quite high and the toughness of ESW95 reaches nearly 75% of SCM435. ESW95 is characterized by the weak strain-hardening behavior and high yield strength that can be lead to minimization of post-processing including heat treatment and straightening. ESW95 and SCM435 are also compared by applying them to ball-stud forging by computer simulation. It is expected that a great deal of change may take place in production as well as in service if the pre-heated steels are adopted.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.38-44
• /
• 2018

In this paper, we propose Intelligent Driver Assistance System (I-DAS) for driver safety. The proposed system recognizes safety and danger status by analyzing blind spots that the driver cannot see because of a large angle of head movement from the front. Most studies use image pre-processing such as face detection for collecting information about the driver's head movement. This not only increases the computational complexity of the system, but also decreases the accuracy of the recognition because the image processing system dose not use the entire image of the driver's upper body while seated on the driver's seat and when the head moves at a large angle from the front. The proposed system uses a convolutional neural network to replace the face detection system and uses the entire image of the driver's upper body. Therefore, high accuracy can be maintained even when the driver performs head movement at a large angle from the frontal gaze position without image pre-processing. Experimental result shows that the proposed system can accurately recognize the dangerous conditions in the blind zone during operation and performs with 95% accuracy of recognition for five drivers.

• 정보처리학회논문지B
• /
• 제10B권1호
• /
• pp.33-40
• /
• 2003

데이터 마이닝은 지식발견 과정에서 중요한 역할을 수행하며, 여러 데이터 마이닝의 알고리즘들은 특정의 목적을 위하여 선택될 수 있다. 대부분의 전통적인 계층적 클러스터링 방법은 적은 양의 데이터 집합을 처리하는데 적합하여 제한된 리소스와 부족한 효율성으로 인하여 대용량의 데이터 집합을 다루기가 곤란하다. 본 연구에서는 대용량의 데이터에 적용되어 알려지지 않은 패턴을 발견할 수 있는 하이브리드형 신경망 클러스터링 기법의 PPC(Pre-Post Clustrering) 기법을 제안한다. PPC 기법은 인공지능적 방법인 자기조직화지도(SOM)와 통계적 방법인 계층적 클러스터링을 결합하여 두 과정에서는 군집의 내부적 특징을 나타내는 응집거리와 군집간의 외부적 거리를 나타내는 인접거리에 따라 유사도를 측정한다. 최종적으로 PPC 기법은 측정된 유사도를 이용하여 대용량 데이터 집합을 군집화한다. PPC 기법은 UCI Repository 데이터를 이용하여 실험해 본 결과, 다른 클러스터링 기법들 보다 우수한 응집도를 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.96.6-96
• /
• 2002

In this study an image processing system is designed and developed, which can detect and assort some defects on the surface of an object moving with high speed. For real time surface detection of high speed moving object, the fast processing should be managed and the image information including some surface features should be captured. It is difficult to acquire the noise free image due to various light sources and high speed moving materials under the environment of the general industrial site. In general, because pre-processing methods are employed for getting a noise free feature, the image processing speed has some limitation and the expensive image processing devices are required. This...

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 1999년도 Japanese Journal of Medical Physics
• /
• pp.141-142
• /
• 1999

• 소성∙가공
• /
• 제29권6호
• /
• pp.362-369
• /
• 2020

In this study, elastoplastic finite element analysis with multi-body treatment was used to elucidate the mechanical phenomena occurring from pre-stressing of die-system. A finite element analysis model with detailed conditions is proposed. The effects of die pre-stressing slope on the circumferential components of the pre-stressed die inserts were evaluated. The role of tight fitting between the supporter and die case was also emphasized because it has a significant effect on the undesirable change in the target slope of machined inner surface of the die case around the die insert. The two mechanical problems include the one between die-insert and die case and the other between supporter and die case, and their correlation is minimized to establish the optimum design in the die structural design stage because it cannot be quantitatively controlled owing to various factors affecting the die structural behavior during die pre-stressing.

• 한국정보통신학회논문지
• /
• 제23권3호
• /
• pp.276-281
• /
• 2019

푸드 프린터는 반드시 식품의약품안전처의 허가를 받은 식용 잉크 카트리지를 사용해야한다. 잉크 카트리지의 정품 여부를 판독하기 위해 2D 바코드를 사용하는데 색소가 열압력에 의해 발산하여 인쇄가 되기 때문에 바코드에 오염이 발생한다. 본 논문에서는 라떼 아트 프린터에서 식용 색소 분진에 의한 정품 인증 바코드의 오염 문제를 해결하고자 다양한 모폴로지 연산에 기반한 전처리(pre-processing) 알고리즘을 제안하였다. 오염된 바코드 이미지들을 QR코드 리더기로 인식시키기 전에 본 알고리즘을 적용하면 기존의 리더기 대비 인식이 가능한 오염도가 25%에서 40%로 증가함을 알 수 있었으며 45%의 오염도에서도 50%의 확률로 인식이 되는 것을 확인하였다.

• 한국정보과학회논문지:데이타베이스
• /
• 제30권5호
• /
• pp.532-539
• /
• 2003

본 논문은 대량의 XML 문서들이 존재하는 정보 검색 시스템에서, XML 질의의 효과적인 처리를 위한 선 처리 방법을 제안한다. 선 처리를 위해 시그너처 기반의 접근 방식을 사용한다. 기존의 (평면적인 문서를 사용하는) 정보 검색 시스템에서는, 대부분 사용자 질의들이 키워드와 부울 연산자로 구성되고, 따라서 시그너처 역시 평면적인 형태로 구성하고 있다. 하지만, XML 기반의 정보 검색 시스템에서는 사용자 질의가 경로 질의의 형태를 띄게 된다. 따라서, 평면적인 시그너처는 XML 문서에 대하여 효과적이지 못하다 본 논문에서는 XML 문서를 위한 구조화된 시그너처 방법을 제안한다. 실험을 통해 제안하는 방법의 성능을 평가한다.