• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 가을 학술발표논문집 Vol.31 No.2 (2)
• /
• pp.697-699
• /
• 2004

Stochastic Neighbor Embedding(SNE) is a probabilistic method of mapping high-dimensional data space into a low-dimensional representation with preserving neighbor identities. Even though SNE shows several useful properties, the gradient-based naive SNE algorithm has a critical limitation that it is very slow to converge. To overcome this limitation, faster optimization methods should be considered by using trust region method we call this method fast TR SNE. Moreover, this paper presents a couple of useful optimization methods(i.e. conjugate gradient method and Newton's method) to embody fast SNE algorithm. We compared above three methods and conclude that TR-SNE is the best algorithm among them considering speed and stability. Finally, we show several visualizing experiments of TR-SNE to confirm its stability by experiments.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• 대한수학회보
• /
• 제54권1호
• /
• pp.145-158
• /
• 2017

We present a finite difference method for solving the Ohta-Kawasaki model, representing a model of mesoscopic phase separation for the block copolymer. The numerical methods for solving the Ohta-Kawasaki model need to inherit the mass conservation and energy dissipation properties. We prove these characteristic properties and solvability and unconditionally gradient stability of the scheme by using Hessian matrices of a discrete functional. We present numerical results that validate the mass conservation, and energy dissipation, and unconditional stability of the method.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.823-826
• /
• 2000

Motion detection is an important step in computer vision and image processing. Traditional motion detection systems are classified into two categories, namely, feature based and gradient based. In feature based motion detection, features in consecutive frames are detected and matched. Gradient based methods assume that the intensity varies linearly and locally. The method, which we propose, is neither feature nor gradient based but uses the electric field theory. The pixels in an image are modeled as point charges and motion is detected by using the variations between the two electric fields produced by the charges corresponding to the two images.

• 대한의용생체공학회:의공학회지
• /
• 제17권1호
• /
• pp.93-98
• /
• 1996

The purpose of this paper is to propose a new localized imaging method of reduced imaging time luting a locally-linear gradient. Since most fast MR(Magnetic Resonance) imaging methods need the whole $\kappa$-space(Spatial frequency space) data corresponding to the whole imaging area, there are limitstions in reducing the minimum imaging time. The imaging method proposed in this paper uses a specially-made gradient coil generating a local ramp-shape field and uniform field outside of the imaging areal Conventional imaging sequences can be used without any RF/gradient pulse sequence modifiestions except the change in the number of encoding steps and the field of view.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.3147-3149
• /
• 1999

In this paper, we develop a TMS320C31- 60 DSP board to generate spiral gradient waveforms for Spiral imaging, one of the ultra fast MRI methods. In Spiral imaging, accurate gradient waveforms are very important to acquire high quality image. For this purpose, sampling rate for generating the gradient waveforms is set twice as high as the data sampling rate. With the developed DSP board accurate gradient waveforms are obtained. Ultra fast MR image with the developed DSP board is currently under development.

• 대한전자공학회논문지SP
• /
• 제47권1호
• /
• pp.120-127
• /
• 2010

본 논문은 높은 품질 SR 이미지를 획득하기 위해 국소 그라디언트를 기반으로 적응형 보간법을 이용하는 SR 방법을 제공한다. 이 방법에서, 내삽 화소와 인접하는 유효한 화소 사이에 거리는 국소 그라디언트 특징을 이용하여 고려되며, 보간 계수는 LR 이미지의 국소 그라디언트를 고려한다. 픽셀의 국소 그라디언트는 더 작을수록, 그리고 메디안 필터는 보간된 HR 이미지의 블러링과 노이즈를 감소시키기 위해 적용된다. 실험 결과는 특히 이미지의 에지 부분에서, 다른 방법과 비교하여 제안된 방법의 유효성을 보여준다.

• 센서학회지
• /
• 제9권3호
• /
• pp.233-241
• /
• 2000

본 연구에서는 동일한 테스트 구조물을 사용하여 현재 다결정실리콘 표면 미세가공 기술에서 널리 사용되고 있는 여러 가지 점착 방지법들의 성능을 비교하였다. 테스트 구조물로는 다양한 폭과 길이를 갖는 일반적인 cantilever와 dimple, antistiction tip, plate를 가지는 cantilever를 사용하였으며 구조물 형태에 따른 점착 방지 결과를 관찰하였다. 희생층 제거 후 구조물과 기판의 점착을 결정하는 건조과정에서는 증발법과 승화건조법을 사용하였다. 증발법에서는 methanol, IPA, DI water 등을 여러 최종 세척액으로 사용하여 표면장력과 세척 온도에 따른 점착 방지 결과를 비교하였다. 승화건조법에서는 중간 세척액으로 methanol을 사용하였다. 그리고 동일한 실험조건으로 stress gradient가 있는 동일한 구조물을 사용하여 stress gradient에 의한 점착 방지 결과를 관찰하였다. 결론적으로 승화건조법이 여러 가지 증발법보다 우수한 결과를 보여주었고 다결정 실리콘 표면 미세가공 기술로 미세 구조물을 부양시킬 때 승화건조법이 가장 우수한 방법이라고 사료된다.

• Journal of applied mathematics & informatics
• /
• 제32권5_6호
• /
• pp.609-619
• /
• 2014

Nonsmooth equations with finitely many maximum functions is often used in the study of complementarity problems, variational inequalities and many problems in engineering and mechanics. In this paper, we consider the global convergence methods for nonsmooth equations with finitely many maximum functions. The steepest decent method and the smoothing gradient method are used to solve the nonsmooth equations with finitely many maximum functions. In addition, the convergence analysis and the applications are also given. The numerical results for the smoothing gradient method indicate that the method works quite well in practice.

• 대한임베디드공학회논문지
• /
• 제4권4호
• /
• pp.190-194
• /
• 2009

Iris recognition is a biometric technology which can identify a person using the iris pattern. Recently, using iris information is used in many fields such as access control and information security. But Perform complex operations to extract features of the iris. Because high-end hardware for real-time iris recognition is required. This paper is appropriate for the embedded environment using local gradient histogram embedded system with iris feature extraction methods based on USN(Ubiquitous Sensor Network). Experimental results show that the performance of proposed method is comparable to existing methods using Gabor transform noticeably improves recognition performance and it is noted that the processing time of the local gradient histogram transform is much faster than that of the existing method and rotation was also a strong attribute.