• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• ETRI Journal
• /
• 제32권5호
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제9권4호
• /
• pp.455-469
• /
• 2003

최근 SAN과 NAS 같은 기술의 발전과 함께 대용량의 데이타를 효과적으로 백업하기 위한 요구들이 증가되고 있다. 본 논문에서는 네트웍 기반의 백업을 위해 제안된 개방형 표준 프로토콜인 NDMP를 이용하여 SAN 환경에 적합한 백업 소프트웨어를 설계하고 구현한다. 제안하는 백업 소프트웨어는 SAN을 기반으로 한 LAN-free 백업을 지원한다. 또한 사용자의 스케줄링에 의한 자동 백업과 다양한 유형의 백업 및 복구 타입을 지원한다. 파일 시스템, 원시 장치 그리고 데이타베이스에 대한 백업 및 복구를 수행한다. 향후 제안하는 백업 소프트웨어는 백업 센터로 사용한 수 있다.

• 대기
• /
• 제27권4호
• /
• pp.411-422
• /
• 2017

The aim of this research is to review recent trends in weather and climate research in North Korea. We selected North Korean journal 'Weather and Hydrology' for the last 10 years (2007-2016), and identified trends in research subject, researchers, and affiliations. Furthermore, we analyzed the major achievements and trends by research sector. Our main results are same as follows. The largest number of researches on 'modernization and informatization on prediction' have been carried out in North Korea's recent meteorological and climatological research. This could be implicated that the scope of national science policy directly affected the promotion of specific research field. Especially, North Korea was evaluated to be concentrating its efforts on numerical model research and development. The numerical model which enables very short-term (6 hours) rainfall forecast which using ensemble Kalman filter data assimilation method (4D EnKF) was developed. In addition, development of automatic weather system and improvement of the data transfer system were promoted. However, the result reveals that the automated real-time data transfer system was not fully equipped yet. These results could be used as a basic data for meteorological cooperation between South and North Korea.

• 전기학회논문지P
• /
• 제60권2호
• /
• pp.68-71
• /
• 2011

In the case of Seoul Metro, prior to installation of platform screen doors, had seen 4~6 cases a month of mortal injuries from accidents on the platforms, including suicide attempts towards the oncoming train. However, since the installation of platform screen doors, Seoul Metro has achieved a feat of '0 mortal injuries'. In the initial stages of introducing platform screen doors domestically, due to a lack of experience in controlling platform screen doors, the products were imported and installed through technical cooperations from Japan, France and the United States. Thereafter, following investments in technologies by domestic firms, domestic production of parts such as overall control mechanism, specific control mechanism, RF devices and others were achieved. However, having installed platform screen doors in a relatively short period of time, DCU(Door Control Unit), an integral part of the whole platform screen door system, is yet to be fully domestically produced. At this moment in time, installation is being done with imported products or DCUs developed with DC motors. In this research, advantages and disadvantages of DC and BLDC motors for use in DCU will be analyzed and will produce an own BLDC controlling unit in order to solve any problems arised. Furthermore, the BLDC controlling unit produced will be integrated with DCU to improve the performance of the product and its price competitiveness.

• Journal of Korean Neurosurgical Society
• /
• 제45권3호
• /
• pp.151-156
• /
• 2009

Objective : It is well known that changes in cerebral hemodynamics occur after traumatic brain injury (TBI). Osmo-regulation in the brain is important for maintaining a constant milieu in the central nervous system. Nevertheless, to our knowledge, early osmolarity changes after minor head injury have not been studied until now. Methods : In this study, serum osmolarity was measured in 99 patients with minor head trauma. As a control group, blood samples were drawn from 99 patients who had a minor trauma in an extremity. Serum osmolarity was estimated using a fully automatic biochemical autoanalyzer within the first 3 hours after the trauma. Results : The mean serum osmolarity levels were $286.08{\pm}10.1\;mOsm/L$ in the study group and $290.94{\pm}5.65\;mOsm/L$ in the control group (p<0.001). However, after age adjustment between the study and control groups, this statistical significance was found to be valid only for patients over 30 years of age. Conclusion : It was noted that serum osmolarity levels decrease in the first 3 hours following minor head trauma in patients over 30 years of age. Further studies into this area could provide guidance for the management/treatment of elderly patients.

• 방송공학회논문지
• /
• 제6권2호
• /
• pp.160-168
• /
• 2001

본 논문에서는 동영상 정보를 파노라마로 합성하는 자동화된 알고리즘을 제안한다. 제안한 카메라 모델은 일반화된 파노라마 영상의 특성을 반영하며, 기존의 방법과는 달리 영상의 확대 및 축소를 고려하여 보다 개선된 파노라마 합성 영상을 제공한다. 또 한 통계적 특성을 이용하여 움직이는 물체 또는 기타 여러 잘음(nolle)의 영향을 배제하는 전역 움직임 추정 기법을 사용하여 기존 방법의 문제점을 보완한다. 이를 통해 파노라마 영상으로부터 움직이는 물체 또는 잡음을 제거하여 더 깨끗하고 완벽한 배경 영상을 얻을 수 있다. 제안한 방법은 전역 움직임 및 전체 파노라마 합성 과정에서 수동 작업을 배제하여 파노라마 합성 과정을 일반화시켰다고 할 수 있다. 성능 평가를 위해 실제 방송에서 사용되는 축구 경기 영상에 제안한 알고리즘을 적용하고 기존의 알고리즘과 비교를 통해 그 우수성을 검증한다.

• Computers and Concrete
• /
• 제6권2호
• /
• pp.167-185
• /
• 2009

Reinforced concrete floors constructed between movement restraints often crack seriously due to shrinkage after completion. One common mitigation measure is to construct the concrete floors in stages to allow part of the shrinkage movement to take place before completion. However, shrinkage movement analysis of concrete floors constructed in stages is quite cumbersome, as the structural configuration changes during construction, thus necessitating reanalysis of the partially completed structure at each stage. Herein, a finite element method for shrinkage movement analysis of concrete floors constructed in stages is developed. It analyses the whole structure, including the completed and uncompleted portions, at all stages. The same mesh is used all the time and therefore re-meshing and location matching are no longer necessary. This is achieved by giving negligibly small stiffness to the uncompleted portions, which in reality do not exist yet. In the analysis, the locked-in strains due to increase in elastic modulus as the concrete hardens and the creep of the hardened concrete are taken into account. Most important of all, this method would enable fully automatic shrinkage movement analysis for the purpose of construction control.

• 정보처리학회논문지D
• /
• 제9D권2호
• /
• pp.277-288
• /
• 2002

인터넷 마켓플레이스에서는 사용자를 도와주는 서비스 중개자가 가장 중요한 역할을 수행한다. 최근에 전자상거래나 온라인 쇼핑몰, 그리고 e-마켓플레이스를 위해 많은 지능적 중개자들이 개발되고 있다. 비록 이러한 시스템들은 많은 성공 사례를 보여주고 있지만 인터넷 마켓플레이스에서 요구되는 서비스 결합 및 자동 실행을 지원하는 시스템은 거의 없다. 이러한 관점에서 본 논문에서는 하나의 새로운 워크플로우 기반 서비스 중개가 시스템을 제안하다. 본 연구에서 종속된 서비스들은 워크플로우 프로세스로 표현되고 이 프로세스들은 워크플로우 엔진에 의해 자동 처리된다. 제안된 시스템에서 모든 데이터의 교환은 플랫폼 독립성, 확장성, 개방성, 그리고 상호운용성 구조를 제공하는 XML을 통해 구현된다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.719-723
• /
• 1997

The welding automation in ship manufacturing process,especially in the sub-assembly line is considered to be a difficult job because the welding part is too huge, various, unstructured for a welding robot to weld fully automatically. The weld orocess at the sub-assembly line for ship manufacturing is to joint the various stiffener on the base panel. In order to realize automatic robot weld in sub-assembly line, robot have to equip with the sensing system to recognize the position of the parts. In this research,we developed a vision system to detect the position of base panle for sub-assembly line is shipbuilding process. The vision system is composed of one CCD camera attached on the base of robot, 2-500W halogen lamps for active illumination. In the image processing algorithm,the base panel is represented by two set of lines located at its two corner through hough transform. However, the various noise line caused by highlight,scratches and stiffener,roller in conveyor, and so on is contained in the captured image, this nosie can be eliminated by region segmentation and threshold in hough transform domain. The matching process to recognize the position of weld panel is executed by finding patterns in the Hough transformed domain. The sets of experiments performed in the sub-assembly line show the effectiveness of the proposed algorithm.