• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2163-2170
• /
• 2009

We present an automated, energy minimized-based method for Lung parenchyma segmenting Chest Computed Tomography(CT) datasets. Deformable model is used for energy minimized segmentation. Quantitative knowledge including expected volume, shape of Chest CT provides more feature constrain to diagnosis or surgery operation planning. Segmentation subdivides an lung image into its consistent regions or objects. Depends on energy-minimizing, the level detail image of subdivision is carried. Segmentation should stop when the objects or region of interest in an application have been detected. The deformable model that has attracted the most attention to date is popularly known as snakes. Snakes or deformable contour models represent a special case of the general multidimensional deformable model theory. This is used extensively in computer vision and image processing applications, particularly to locate object boundaries, in the mean time a new type of external force for deformable models, called gradient vector flow(GVF) was introduced by Xu. Our proposed algorithm of deformable model is new external energy of GVF for exact segmentation. In this paper, Clinical material for experiments shows better results of proposal algorithm in Lung parenchyma segmentation on Chest CT.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.1
• /
• pp.55-62
• /
• 2007

Recent advances in airborne LiDAR technology allow rapid and inexpensive measurements of topography over large areas. The generation of DTM/DEM is essential to numerous applications such as the fields of civil engineering, environment, city planning and flood modeling. The demand for LiDAR data is increasing due to the reduced cost for DTM generation and the increased reliability, precision and completeness. In order to generate DTM, measurements from non-ground features such as building and vegetation have to be classified and removed. In this paper, a segmented morphology filter was developed to detect non-ground LiDAR measurements. First, segments LiDAR point clouds based on the elevation. Secondly classifies those protruding segments into non-ground points. Those non-ground points such as building and vegetation are removed, while ground points are preserved for DTM generation. For experiments, data sets used in Comparison of Filters (ISPRS, 2003) depicting urban and rural areas were selected. The experimental results show that the proposed filter can remove most of the non-ground points effectively with less commission and omission errors.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.115-119
• /
• 2023

The natural language processing models used in current artificial intelligence are huge, causing various difficulties in processing and analyzing data in real time. In order to solve these difficulties, we proposed a method to improve the efficiency of processing by using less memory and checked the performance of the proposed model. The technique applied in this paper to evaluate the performance of the proposed model is to divide the large corpus by adjusting the number of attention heads and embedding size of the BERT[1] model to be small, and the results are calculated by averaging the output values of each forward. In this process, a random offset was assigned to the sentences at every epoch to provide diversity in the input data. The model was then fine-tuned for classification. We found that the split processing model was about 12% less accurate than the unsplit model, but the number of parameters in the model was reduced by 56%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.157-168
• /
• 2014

We propose an novel artificial visual attention model that is capable of automatic detection and segmentation of saliency region on natural images in this paper. The proposed model is based on human visual perceptions in biological vision and contains there are main contributions. Firstly, we propose a novel framework of artificial visual attention model based on the opponent process theory using intensity and color features, and an entropy filter is designed to perceive salient regions considering the amount of information from intensity and color feature channels. The entropy filter is able to detect and segment salient regions in high segmentation accuracy and precision. Lastly, we also propose an adaptive combination method to generate a final saliency map. This method estimates scores about intensity and color conspicuous maps from each perception model and combines the conspicuous maps with weight derived from scores. In evaluation of saliency map by ROC analysis, the AUC of proposed model as 0.9256 approximately improved 15% whereas the AUC of previous state-of-the-art models as 0.7824. And in evaluation of salient region segmentation, the F-beta of proposed model as 0.7325 approximately improved 22% whereas the F-beta of previous state-of-the-art models.

• Journal of Navigation and Port Research
• /
• v.27 no.5
• /
• pp.487-492
• /
• 2003

The paper describes on the implementation of marine casualty prediction model that is one of the main part of Korean MArine Casualty FOrecasting System (K-MACFOS). In this work, Cell Distributed Linear-In-the-Parameter (CD-LIP) model is proposed and discussed its usability with comparing Baltic model and revised LIP model. As evaluation results by regression analysis of variance, it is known that the CD-LIP model gives best performance to the marine casualty numerical D/B of the target sea area.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2003.05a
• /
• pp.60-65
• /
• 2003

The paper describes on the implementation of marine casualty prediction model that is one of the main part of Marine Casualty Forecasting System (MCFS). In this work, Cell Distributed Linear-In-the Parameter (CD-LIP) model is developed and compared with Baltic model using regression analysis of variance. As comparing, it is known that the proposed CD-LIP model has less residual than the Baltic model and, it gives best performance to the marine casualty numeric D/B of target area.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.1
• /
• pp.37-47
• /
• 2007

The shield tunneling method has been increasingly employed to minimize environmental damages and civil complaints in the populated and developed area. A lining segment, which is a main structure of the shield tunnel, consists of joints. Conventional foreign and domestic design data have been commonly used for design practices without a specific verification of structural analysis models, design load, and the effect of soil characteristics on the performance of lining segment. In this study, the suitability of existing analytic models used for the design of shield tunnel lining segment has been evaluated through a comparison between analytical and numerical solutions. Based on the evaluation of their suitability performed in the study, a full-circumferential beam jointed spring model (1R-S0) is proposed for design practices by considering user's convenience, the applicability of field conditions and the accuracy of analysis result. By using the proposed model, the parameter analysis was performed to investigate the effects of joint stiffness, ground rigidity, joint distribution and the number of joints on the behavior of lining segment. Parameters considered in the investigation have been appeared to affect the behavior of lining segment. Among those parameters, joint stiffness has been appeared to have the most significant effect on the bending moment and displacement of lining segment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.22-24
• /
• 2003

레거시 애플리케이션 시스템(이하 LAS: Legacy Application System)은 차세대 비즈니스 시스템들로 통합되어야 하는 가치 있는 자산이다. 이러한 LAS의 이점을 얻기 위해, 레거시 비즈니스 시스템을 역공학적으로 분석할 수 있다. 본 논문은 LAS의 폼으로부터 의미 있는 정보를 파악하여 다음 세대의 시스템에 통합될 수 있도록 객체단위로 분할하여 분석한 다음, 이러한 정보를 이용하여 재사용 및 재공학을 할 수 있도록 하기 위한 역공학적 객체 분석 프로세스(이하 FOAP)를 제안한다. 본 논문에서 제안하는 FOAP는 4단계 즉, 폼 사용사례 분석 단계, 폼 객체 분할 단계, 객체구조 모델링 단계, 객체 모델 통합 단계 등으로 구성되어있다. 폼 사용사례 분석 단계는 폼 구조 그리고 LAS와 사용자간의 상호작용 둥의 정보를 획득하는 단계다. 폼 객체분할 단계는 폼 정보를 의미 있는 필드들로 구분하는 단계다. 객체구조 모델링 단계는 폼 객체들간의 구조적 관계와 협력 관계를 파악하여 모델링하는 단계다. 마지막으로 객체 모델 통합단계는 객체 단위의 단위 모델들을 통합하여 추상화된 정보를 포함한 상위 수준의 통합 모텔을 유도하는 단계다. FOAP에 의해 결과적으로 생성된 객체 통합 모델은 역공학 기술자들의 LAS 이해와 LAS의 정보를 새로운 시스템에 적용하는데 있어 좀 더 용이한 효율성을 제공한다.

• Journal of the Korea Computer Graphics Society
• /
• v.4 no.1
• /
• pp.31-40
• /
• 1998

Active Contour Model(ACM) is an efficient method for segmenting an object. The main shortcoming of ACM is that its result is very dependent on the shape and location of an initial contour. To overcome this shortcoming, a new segmentation algorithm is proposed in this paper. The proposed algorithm uses B-splines to describe the active contour and applies Simulated Annealing (SA) and Genetic Algorithm(GA) as energy minimization techniques. We tried to overcome the initialization problem of traditional ACM and compared the result of ACM using GA and that using SA with 2D synthetic binary images. CT and MR images.

• Korean Journal of Food Science and Technology
• /
• v.23 no.5
• /
• pp.605-609
• /
• 1991

The physical properties which must be considered as engineering factors affecting on the evaporation process of fruit juices are boiling point rise, density, viscosity, thermal conductivity and specific heat. These factors are varied with food ingredients, soluble solids, pressure and temperature. In the reserch, it has been worked to obtain the data and to develop prediction model for the boiling point rise as a faction of soluble solid and pressure by the regression of SPSS package program. For the prediction model of density, it was developed as a fuction of soluble solid content on apple and pear juices. For the viscosity model, it was establised by the factors of temperature and content of soluble solid through the optimization program.