• 대한의용생체공학회:의공학회지
• /
• 제28권6호
• /
• pp.713-720
• /
• 2007

In image-guided surgery, automatic bone segmentation of Computed Tomography (CT) images is an important but challenging step. Previous attempts include intensity-, edge-, region-, and deformable curve-based approaches [1], but none claims fully satisfactory performance. Although active contour (AC) techniques possess many excellent characteristics, their applications in CT image segmentation have not worthily exploited yet. In this study, we have evaluated the automaticity and performance of the model of Chan-Vese Multiphase AC Without Edges towards knee bone segmentation from CT images. This model is suitable because it is initialization-insensitive and topology-adaptive. Its segmentation results have been qualitatively compared with those from four other widely used AC models: namely Gradient Vector Flow (GVF) AC, Geometric AC, Geodesic AC, and GVF Fast Geometric AC. To quantitatively evaluate its performance, the results from a commercial software and a medical expert have been used. The evaluation results show that the Chan-Vese model provides superior performance with least user interaction, proving its suitability for automatic bone segmentation from CT images.

• 한국컴퓨터그래픽스학회논문지
• /
• 제4권1호
• /
• pp.31-40
• /
• 1998

활성외곽선모델(active contour model)은 물체의 경계를 분할하기 위한 효과적인 방법으로 사용되고 있다. 그런데, 기존 활성외곽선모텔에서는 초기곡선을 분할하고자하는 물체의 경계면에 위치시키고 지역적으로 에너지를 최소화 함에 따라 결과가 초기 곡선의 위치와 형태에 따라 달라지는 단점이 있었다. 본 논문에서는 활성외곽선모델을 B-Spline 곡선에 의해 표현하고, 에너지 최소화 과정에 유전자 알고리즘(Genetic Algorithm: GA)과 시뮬레이티드 어닐링 (Simulated Annealing : SA)을 적용함으로써 기존 활성외곽선모델이 갖는 초기 곡선에 대한 제약성을 개선하고자 했으며, 두가지 방법에 따른 분할 결과와 문제점을 비교하고자 하였다. 제안한 방법의 성능비교를 위하여 이진 합성 영상과 CT 영상, MR 영상을 대상으로 실험을 수행하였다.

• 한국멀티미디어학회논문지
• /
• 제21권7호
• /
• pp.779-786
• /
• 2018

In this paper, we are applied a nerve network to allow for the reflection of data learning methods in their overall forms by using cluster data rather than data learning by the stages and then selected a nerve network model and analyzed its variables through learning by the cluster. The CkLR algorithm was proposed to analyze the reaction variables of clustering outcomes through an approach to the initialization of K-means clustering and build a model to assess the prediction rate of clustering and the accuracy rate of prediction in case of new data inputs. The performance evaluation results show that the accuracy rate of test data by the class was over 92%, which was the mean accuracy rate of the entire test data, thus confirming the advantages of a specialized structure found in the proposed learning nerve network by the class.

• 대기
• /
• 제22권4호
• /
• pp.455-464
• /
• 2012

This study investigates a 12 month-lead predictability of PNU Coupled General Circulation Model (CGCM) V1.1 hindcast, for which an oceanic data assimilated initialization is used to generate ocean initial condition. The CGCM, a participant model of APEC Climate Center (APCC) long-lead multi-model ensemble system, has been initialized at each and every month and performed 12-month-lead hindcast for each month during 1980 to 2011. The 12-month-lead hindcast consisted of 2-5 ensembles and this study verified the ensemble averaged hindcast. As for the sea-surface temperature concerns, it remained high level of confidence especially over the tropical Pacific and the mid-latitude central Pacific with slight declining of temporal correlation coefficients (TCC) as lead month increased. The CGCM revealed trustworthy ENSO prediction skills in most of hindcasts, in particular. For atmospheric variables, like air temperature, precipitation, and geopotential height at 500hPa, reliable prediction results have been shown during entire lead time in most of domain, particularly over the equatorial region. Though the TCCs of hindcasted precipitation are lower than other variables, a skillful precipitation forecasts is also shown over highly variable regions such as ITCZ. This study also revealed that there are seasonal and regional dependencies on predictability for each variable and lead.

• 로봇학회논문지
• /
• 제12권1호
• /
• pp.33-41
• /
• 2017

We present a region-based approach for accurate pose estimation of small mechanical components. Our algorithm consists of two key phases: Multi-view object co-segmentation and pose estimation. In the first phase, we explain an automatic method to extract binary masks of a target object captured from multiple viewpoints. For initialization, we assume the target object is bounded by the convex volume of interest defined by a few user inputs. The co-segmented target object shares the same geometric representation in space, and has distinctive color models from those of the backgrounds. In the second phase, we retrieve a 3D model instance with correct upright orientation, and estimate a relative pose of the object observed from images. Our energy function, combining region and boundary terms for the proposed measures, maximizes the overlapping regions and boundaries between the multi-view co-segmentations and projected masks of the reference model. Based on high-quality co-segmentations consistent across all different viewpoints, our final results are accurate model indices and pose parameters of the extracted object. We demonstrate the effectiveness of the proposed method using various examples.

• 한국항공우주학회지
• /
• 제50권8호
• /
• pp.531-540
• /
• 2022

본 논문에서는 IMM 필터 기반으로 장사정포의 탄종을 식별하고 탄착점을 신속하게 예측하는 알고리즘을 제시한다. 탄도궤적 방정식을 시스템 모델로 사용하고, 각각 다른 탄도계수 값을 갖는 3가지 모델을 IMM 필터에 적용한다. 가속도를 중력, 공기저항, 양력에 의한 3가지 성분으로 나누고 양력가속도를 새로운 상태변수로 추가하여 추정한다. 속도벡터와 양력가속도가 수직이라는 운동학 조건을 유사 측정값으로 추가한 측정방정식을 다룬다. IMM 필터를 통해 추정된 상태변수와 모드 확률이 가장 높은 모델의 탄도계수를 기반으로 탄착점을 예측한다. 탄착점 예측을 위해 일반적으로 사용되는 룽게-쿠타 수치적분 대신, 준해석적인 방법을 사용하여 적은 계산량으로 탄착점을 예측할 수 있음을 설명한다. 마지막으로 최소제곱법을 이용한 상태변수 초기화 방법에 대해 제안하고 성능을 확인하였다. 탄종식별, 탄착점 예측 및 초기화를 포함한 통합 알고리즘을 제시하고 시뮬레이션을 통해 제안한 방법의 타당성을 검증하였다.

• International journal of advanced smart convergence
• /
• 제6권4호
• /
• pp.73-79
• /
• 2017

The Convolutional Neural Network (CNN) has shown an excellent performance in computer vision task. Applications of CNN include image classification, object detection in images, autonomous driving, etc. This paper will evaluate the performance of CNN model with ReLU and SELU as activation function. The evaluation will be performed on four different choices of hyperparameter which are initialization method, network configuration, optimization technique, and regularization. We did experiment on each choice of hyperparameter and show how it influences the network convergence and test accuracy. In this experiment, we also discover performance improvement when using SELU as activation function over ReLU.

• 대한기계학회논문집
• /
• 제8권1호
• /
• pp.65-70
• /
• 1984

A recursive parameter estimation method is applied to spindle deflection model during boring process. The spindle infeed rate is then determined to preserve the diametral tolerance of bore. This estimation method is further extended to adaptive control by application of the variance perturbation method. The results of computer simulation attest that the proposed method renders the optimal cutting conditions, maintaining the diametral accuracy of bore, regardless of parameter fluctuations. The proposed method necessitating only post-process measurements features that initialization of parameter guess values in simple, a priori knowledge on parameter variations is not needed and the accurate estimation of optimal spindle infeed rate is obtained, even if the parameter estimation may be poor.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.443-451
• /
• 2015

The stability of a multi-terminal direct current (MTDC) system is often influenced by its control strategy. To improve the stability of the MTDC system, the control strategy of the MTDC system must be appropriately adopted. This paper deals with estimating stability of a MTDC system based on the line-commutated converter based high voltage direct current (LCC HVDC) system with an inverter with constant extinction angle (CEA) control or a rectifier with constant ignition angle (CIA) control. In order to evaluate effects of two control strategies on stability, a MTDC system is tested on two conditions: initialization and changing DC power transfer. In order to compare the stability effects of the MTDC system according to each control strategy, a mathematical MTDC model is analyzed in frequency domain and time domain. In addition, Bode stability criterion and transient response are carried out to estimate its stability.

• Smart Structures and Systems
• /
• 제5권5호
• /
• pp.507-515
• /
• 2009

The present work is an alternative methodology in order to balance a nonlinear highly flexible rotor by using neural networks. This procedure was developed aiming at improving the performance of classical balancing methods, which are developed in the context of linearity between acting forces and resulting displacements and are not well adapted to these situations. In this paper a fully experimental procedure using neural networks is implemented for dealing with the adaptive balancing of nonlinear rotors. The nonlinearity results from the large displacements measured due to the high flexibility of the foundation. A neural network based meta-model was developed to represent the system. The initialization of the learning procedure of the network is performed by using the influence coefficient method and the adaptive balancing strategy is prone to converge rapidly to a satisfactory solution. The methodology is tested successfully experimentally.