• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1248-1259
• /
• 2016

Classification methods based on dual energy X-ray absorptiometry, ultrasonic waves, and quantitative computed tomography have been proposed. Also, a classification method based on machine learning with bone mineral density and structural indicators extracted from the CT images has been proposed. We propose a method which enhances the performance of existing classification method based on bone mineral density and structural indicators by extending structural indicators and using principal component analysis. Experimental result shows that the proposed method in this paper improves the correctness of osteoporosis classification 2.8% with extended structural indicators only and 4.8% with both extended structural indicators and principal component analysis. In addition, this paper proposes a method of automatic phantom analysis needed to convert the CT values to BMD values. While existing method requires manual operation to mark the bone region within the phantom, the proposed method detects the bone region automatically by detecting circles in the CT image. The proposed method and the existing method gave the same conversion formula for converting CT value to bone mineral density.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권1호
• /
• pp.51-58
• /
• 2022

Korea Augmentation Satellite System (KASS) is a Satellite Based Augmentation System (SBAS) system under development in South Korea and aims to provide air navigation services after 2023. In order to provide reliable service, detailed design for the operation of this system is required. This paper proposes a detailed operation-based designs based on mission, architecture, operation definition of the system. For the stable operation of the system, an operation organization was designed and operation activities were classified in consideration of the architecture and function of the system. Detailed operation procedures were designed according to this classification and operation procedures related to the command and configuration of subsystem were verified on the Integration, Verification and Qualification (IVQ) platform for integrated testing and verification. The proposed operation concepts and procedures will be continuously confirmed and verified during verification, qualification and service preparation, and will be updated event after official KASS service.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.613-614
• /
• 2017

최근 가정 내부에 IoT(Internet of Things)를 적용시킨 홈 IoT의 자동화 관련 연구가 진행되고 있다. 그러나 기존 IoT 자동화 시스템은 기기 동작이 센서의 임계값만을 통해 진행되기 때문에 기기간 충돌 및 간섭이 발생할 수 있으며 기기의 오작동으로 인해 작업의 효율성이 낮은 문제점이 있다. 본 논문에서는 이러한 문제점을 해결하기 위해 상황 별 작업 분류 알고리즘을 제안한다. 센서의 임계값과 현재 날짜를 의사결정트리의 분류 값으로 활용하여 가정 내부 상황에 따른 작업을 분류하고 그에 해당하는 기기를 선정하여 작업을 진행한다. 이에 따라 사용자는 가정 내부 상황 변화에 유동적으로 변화하는 서비스를 제공받을 수 있으며 기기 간 충돌과 기기의 오작동이 감소함으로써 작업의 정확도가 증대될 것으로 사료된다.

• 한국전산구조공학회논문집
• /
• 제36권3호
• /
• pp.147-154
• /
• 2023

하천시설물은 정보의 관리주체가 국가하천과 지방하천 등에 따라 달라서 통합되어 관리되지 못하고 있는 점, 설계 및 시공 단계의 정보화 축적이 미흡하여 시설물 정보의 망실이 우려되는 점 등 하천분야로 BIM 도입을 하기 위해서는 해결해야 할 과제들이 산재해 있다. 또한, 이로 인해 유지운영단계에서의 시설물 정보 활용 수준 역시 상당히 미흡한 편이다. 따라서, 하천시설물의 효과적인 유지운영을 위해서는 표준분류체계에 따라 시설물 정보를 정리함으로 데이터의 일관성을 확보하고 효율성을 증대시킬 필요가 있다. 본 연구에서는 이러한 하천분야의 시설물 특성을 고려하여 하천분야의 BIM 정보모델 도입과 3차원 기반의 하천시설의 효율적인 유지운영 전환을 위한 BIM 표준분류체계를 적용하는 방안을 제시한다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• Archives of Plastic Surgery
• /
• 제35권4호
• /
• pp.455-460
• /
• 2008

Purpose: We have classified blepharoptosis into the categories including pseudoptosis in Koreans and compared with other previous studies. Methods: Total of 250 patients(398 eyes) who underwent surgery for blepharoptosis from 1987 to 2006 were studied. By classification of Beard, patients were categorized into congenital, acquired and pseudo blepharoptosis and later they were reclassified by their etiologies. Also addition of pseudoptosis to the classification of Frueh, blepharoptosis were categorized into neurogenic type, myogenic type, aponeurotic type, mechanical type and pseudoptosis. And we divided these cases by the degree of blepharoptosis, levator function and the operation methods. Results: Out of the 250 patients, 175 patients were congenital type, 49 were acquired type and 26 were pseudoptosis. According to the mechanistic classification, 177 myogenic type, 30 aponeurotic, 7 mechanic, 8 neurogenic and 28 pseudoptosis were categorized. Regarding severity of blepharoptosis, there were 29.2% of mild, 40% of moderate, and 30.8% of severe cases. Out of the 398 cases, in terms of the operation methods, there were 39 aponeurosis plication, 184 levator resection, 5 Muller tucking, 60 Orbicularis oculi muscle flap, 66 frontalis transfer, and 21 blepharoplasty. Conclusion: The cause and degree of ptosis, and levator function are very important when considering the amount of resected muscle. There were only a few studies about blepharoptosis classification including pseudoptosis category. Therefore, through this study, we can investigate the relationship between the pseudoptosis and the others. This study could be useful for the making future management plans of blepharoptosis in Korean patients.

• 대한설비공학회지:설비저널
• /
• 제22권1호
• /
• pp.28-35
• /
• 1993

• 기록학연구
• /
• 제9호
• /
• pp.41-73
• /
• 2004

This article provides the base in relation to the classification system of public records of Japan and Tiwan which the original order of the classification system of public records of Government-General of Chosun is reconstructed and the efficient classification system is prepared. The classification system of public records at the period of Meiji(明治) in Japan was classified two forms, one is function-based classification, the other is organization-based classification. Each ministry(省) was fundamentally based In function-based classification and organization-based classification, adopted them in changed forms as its condition and situation had been changed. Government-General of Tiwan adopted Japan's archival management system and put its classification system and life schedule In operation. The classification system of Government-General of Tiwan adopted function-based classification of the ministry of foreign affairs in Japan, changed its forms as the organization and business activity were transformed. As a result of arrangement and analysis of examples for the classification of public records of Government-General of Chosun from 1910' to the middle area of 1930', the classification of public records of Government-General of Chosun was constructed on level order; 'organization of ministry(部) or department(局)--business activity of ministry or department--low function of business activity of ministry or department'. But this classification system had two sides, flexible and unstable in that the classification system had exeptional parts and the breadth of items was changed greatly. The classification system of Government-General of Chosun, which had adopted organization-based classification of the ministry of home affairs in Japan, result in expanding the breadth of items and causing great change of items for the organization and business activity were vast and its change was very great.

• Journal of Electrical Engineering and Technology
• /
• 제1권2호
• /
• pp.257-262
• /
• 2006

Insulation failure in an electrical utility depends on the continuous stress imposed upon it. Monitoring of the insulation condition is a significant issue for safe operation of the electrical power system. In this paper, comparison of recognition rate variable classification scheme of PD (partial discharge) sources that occur within an electrical utility are studied. To acquire PD data, five defective models are made, that is, air discharge, void discharge and three types of treeinging discharge. Furthermore, these statistical distributions are applied to classify PD sources as the input data for the classification tools. ANFIS shows the highest rate, the value of which is 99% and PCA-LDA and ANFIS are superior to BP in regards to other matters.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2007년도 정기총회 및 학술발표대회
• /
• pp.526-529
• /
• 2007

Storm and flood damage management systems in national disaster management system(NDMS) were organized into three operation systems. They are prevention, preparation, response, and recovery systems. Disaster resources in each system must be promptly and exactly applied to minimize casualties and loss of properties. However, the disaster resources in current management system can not be immediately used in calamity situation due to the lack of efficiency in statistical data. In this study, the classification system of the disaster resources in storm and flood damage systems was examined to develop the a standard technology in disaster resources management. Problems and reformation points of the classification system were also presented to improve the classification technique and to construct the data base.