• Journal of Ginseng Research
• /
• 제31권2호
• /
• pp.69-73
• /
• 2007

Since chemical structures of ginsenoside as active ingredient of Panax ginseng are known, accumulating evidence have shown that ginsenoside is one of bio-active ligands through the diverse physiological and pharmacological evaluations. Chemical structures of ginsenoside could be divided into three parts depending on diol or triol ginsenoside: Steroid- or cholesterol-like backbone structure, carbohydrate portions, which are attached at the carbon-3, -6 or -20, and aliphatic side chain coupled to the backbone structure at the carbon-20. Ginsenosides also exist as stereoisomer at the carbon-20. Bioactive ligands usually exhibit the their structure-function relationships. In ginsenosides, there is little known about the relationship of chemical structure and biological activity. Recent reports have shown that ginsenoside $Rg_3$, one of active ginsenosides, exhibits its differential physiological or pharmacological actions depending on its chemical structure. This review will show how ginsenoside $Rg_3$, as a model compound, is functionally coupled to voltage-gated ion channel or ligand-gated ion channel regulations in related with its chemical structure.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.1-10
• /
• 1995

A graphic user interface for effectively browsing object-oriented databases in complex applications is designed and implemented. The rationale behind our design lies in enabling the users of various levels and needs to investigate the database according to their respective interests and desired depths. A novel idea in our design is the introduction of zooming techniques from a logical view, which vidualize the backbone abstraction concepts of the object-oriented data model. These objectives are verified by evaluating the results of its implementation.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2000년도 International Symposium on Bioinformatics
• /
• pp.28-31
• /
• 2000

We describe a hidden Markov model, HMMTIR, for general protein sequence based on the I-sites library of sequence-structure motifs. Unlike the linear HMMs used to model individual protein families, HMMSTR has a highly branched topology and captures recurrent local features of protein sequences and structures that transcend protein family boundaries. The model extends the I-sites library by describing the adjacencies of different sequence-structure motifs as observed in the database, and achieves a great reduction in parameters by representing overlapping motifs in a much more compact form. The HMM attributes a considerably higher probability to coding sequence than does an equivalent dipeptide model, predicts secondary structure with an accuracy of 74.6% and backbone torsion angles better than any previously reported method, and predicts the structural context of beta strands and turns with an accuracy that should be useful for tertiary structure prediction. HMMSTR has been incorporated into a public, fully-automated protein structure prediction server.

• 정보보호학회논문지
• /
• 제16권3호
• /
• pp.165-172
• /
• 2006

누구나 인터넷에 접속할 수 있는 환경이 구축됨에 따라 해킹, 악성코드 등의 다양한 위협도 함께 등장하고 있다. 그 중 인터넷 웜은 1.25 대란과 같이 국가 기간망을 뒤흔들 수 있는 위협으로 인식되고 있다. 본 논문은 인터넷 환경에서 웜 확산의 모델링을 그 목표로 한다. 이를 위해 인터넷 원에 적용 가능한 확산 모델을 제안하고, 인터넷 환경에서 웜에 적용하여 동작을 분석한다. 제안 모델은 고속의 인터넷 웡 확산에 따른 영향을 분석함으로써 인터넷 웜의 확산을 보다 정확하게 예측할 수 있다.

• 전기전자학회논문지
• /
• 제27권3호
• /
• pp.345-349
• /
• 2023

본 논문은 영상장치를 이용한 차세대 스마트 LED 전광판의 불량픽셀 검출을 위한 딥러닝 구조 개발에 관한 연구를 제안한다. 이 연구에서는 영상장치를 활용하여 딥러닝을 통해 실외 LED 전광판의 결함을 자동으로 검출하는 기법을 제안한다. 이를 통해 LED 전광판의 효율적인 관리와 발생할 수 있는 다양한 오류와 문제를 해결하고자 한다. 연구 과정은 3단계를 거쳐 이루어진다. 첫 번째로, 평면화된 전광판 이미지 데이터를 calibration을 통해 배경을 완전히 제거하고 필요한 전처리 과정을 거쳐 학습 데이터셋을 생성한다. 두 번째로, 생성된 데이터셋은 객체 인식 네트워크를 학습을 시키는 데 활용된다. 네트워크는 Backbone과 Head로 구성된다. Backbone에서는 CSP-Darknet을 활용하여 특징 맵을 추출하고, Head에서는 추출된 Feature Map을 기반으로 물체를 검출한다. 이 과정에서 네트워크는 Confidence score와 IoU가 일치하도록 오차를 수정하며 지속적으로 학습된다. 세 번째에서는 생성된 모델을 활용하여 실제 실외 LED 전광판에서 불량픽셀을 자동으로 검출한다. 본 논문에서 제안하는 방법을 적용하여 LED 전광판의 불량픽셀 검출에 대한 공인 측정 실험 결과로는 실제 LED 전광판에서 불량픽셀을 100% 검출한 결과를 얻을 수 있었다. 이를 통해 LED 전광판의 불량 관리와 유지보수의 효율성이 향상되었음을 확인할 수 있다. 이러한 연구 결과는 LED 전광판 관리의 획기적인 개선을 이룰 것으로 기대된다.

• 한국방사선학회논문지
• /
• 제16권1호
• /
• pp.25-34
• /
• 2022

뇌 전산화단층촬영은 비침습성, 3차원 영상 제공, 저방사선량 등의 장점 때문에 뇌출혈과 같은 질병 진단을 위해 시행된다. 하지만 뇌 전산화단층영상 판독을 위한 전문의의 인력 공급 부족 및 막대한 업무량으로 인해 수많은 판독 오류 및 오진이 발생하고 있다. 이와 같은 문제를 해결하기 위해 객체 검출을 위한 다양한 인공지능 기술이 개발되고 있다. 본 연구에서는 뇌 전산화단층영상으로부터 뇌출혈 검출을 위한 딥러닝 기반 YOLOv5s 모델의 적용 가능성을 확인하였다. 또한 YOLOv5s 모델 학습 시 초매개변수를 변화시켜 학습된 모델의 성능을 평가하였다. YOLOv5s 모델은 backbone, neck 및 output 모듈로 구성하였고, 입력 CT 영상 내 뇌출혈로 의심되는 부위를 검출하여 출력할 수 있도록 하였다. YOLOv5s 모델 학습 시 활성화함수, 최적화함수, 손실함수 및 학습 횟수를 변화시켰고, 학습된 모델의 뇌출혈 검출 정확도 및 학습 시간을 측정하였다. 연구결과 학습된 YOLOv5s 모델은 뇌출혈로 의심되는 부위에 대한 경계 박스 및 해당 경계박스에 대한 정확도를 출력할 수 있음을 확인하였다. Mish 활성화함수, stochastic gradient descent 최적화함수 및 completed intersection over union 손실함수 적용 시 YOLOv5s 모델의 뇌출혈 검출 정확도 향상 및 학습 시간이 단축되는 결과를 확인하였다. 또한 YOLOv5s 모델의 뇌출혈 검출 정확도 및 학습 시간은 학습 횟수에 비례하여 증가하는 결과를 확인하였다. 따라서 YOLOv5s 모델은 뇌 전산화단층영상을 이용한 뇌출혈 검출을 위해 활용할 수 있으며, 최적의 초매개변수 적용을 통해 성능을 향상 시킬 수 있다.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• 천문학논총
• /
• 제30권2호
• /
• pp.473-474
• /
• 2015

Halo merger trees are the essential backbone of semi-analytic models for galaxy formation and evolution. Srisawat et al. (2013) show that different tree building algorithms can build different halo merger histories from a numerical simulation for structure formation. In order to understand the differences induced by various tree building algorithms, we investigate the impact of halo merger trees on a semi-analytic model. We find that galaxy properties in our models show differences between trees when using a common parameter set. The models independently calibrated for each tree can reduce the discrepancies between global galaxy properties at z=0. Conversely, with regard to the evolutionary features of galaxies, the calibration slightly increases the differences between trees. Therefore, halo merger trees extracted from a common numerical simulation using different, but reliable, algorithms can result in different galaxy properties in the semi-analytic model. Considering the uncertainties in baryonic physics governing galaxy formation and evolution, however, these differences may not necessarily be significant.

• Structural Engineering and Mechanics
• /
• 제76권3호
• /
• pp.355-365
• /
• 2020

In this study, considering the hydroelastic response represented by the springing and whipping phenomena, we propose a method of estimating the fatigue damage in the longitudinal connections of ships. First, we screened the design sea states using a load transfer function based on the frequency domain. We then conducted a time domain fluid-structure interaction (FSI) analysis using WISH-FLEX, an in-house code based on the weakly nonlinear approach. To obtain an effective and robust analytical result of the hydroelastic response, we also conducted an experimental model test with a 1/50-scale backbone-based model of a ship, and compared the experimental results with those obtained from the FSI analysis. Then, by combining the results obtained from the hydroelastic response with those obtained from the numerical fatigue analysis, we developed a fatigue damage estimation method. Finally, to demonstrate the effectiveness of the developed method, we evaluated the fatigue strength for the longitudinal connections of the real ship and compared it with the results obtained from the model tests.