• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.333-336
• /
• 2001

본 논문에서는 웹에서 온라인상으로 발생되는 기록 데이터들의 연관 규칙을 구성할 수 있는 효과적인 기법을 제안하고 있다. 기본적으로, 온라인상에서 연관 규칙을 추출하는 방법은 Carma 알고리즘을 바탕으로 하였기 때문에 최대 데이터의 scan 회수를 2회로 유지하였다. 각 사용자가 방문한 웹 사이트의 수에 대하여 정규 분포를 따르는 가중치를 Phase I 알고리즘의 지지도 관련 변수에 영향을 줌으로써, lattice 의 크기를 조절하는 요소로 사용하여 처리 시간을 단축시키고 있다. 기존의 Carma 알고리즘과 제안하는 W-Carma(Weighted-Carma) 알고리즘과 처리 시간을 비교하였으며, 대량의 데이터일 경우 좋은 성능을 보이고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1573-1576
• /
• 2004

멀티미디어 압축 및 이동 통신 기술의 발전으로 다양한 형태의 멀티미디어 서비스가 이슈화되고 있다. 비디오를 전송하기 위해서는 많은 대역폭을 필요로 하지만, 모든 네트워크가 높은 수준의 대역 및 처리 능력을 가지는 것은 아니다. 이질적인 네트워크간의 멀티미디어를 서비스하기 위해서는 네트워크 상황 또는 수신자의 처리 능력에 맞도록 재 부호화해야 하지만 그 처리비용이 높다. 트랜스코딩 기법 중에서 시간당 요구된 프레임의 개수를 조절하면 제거된 프레임의 움직임 벡터를 재 사용하여 비트율을 감소시킬 수 있다. 본 논문에서는 기존의 기법보다 향상된 움직임과 중첩 영역의 정보를 적용한 WBVC(Weight-Based Vector Composition) 기법을 제안한다. 실험을 통한 기존의 기법과의 비교 분석 결과, 비슷한 계산 복잡도에서 제안한 WBVC 기법이 높은 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.201-203
• /
• 2013

본 논문에서는 SIFT 와 particle 특징 궤적을 이용한 새로운 행동 인식 시스템을 제안한다. 먼저, 영상에서 중요한 지역적 특징 정보를 얻기 위하여 SIFT 특징 점들을 탐지하고, 탐지한 특징 점들을 SIFT descriptor matching 기법을 이용하여 그 궤적을 추출한다. 또한, SIFT 특징 궤적들의 수량이 적은점과 영상내의 조명변화, 부분적 가려짐 등의 변화로 인해 SIFT 특징 궤적이 종종 없어지는 단점을 보완하기 위하여, SIFT 특징 궤적 주위에 particle 점들을 탐지하고, dense optical flow 기법을 기반으로 그 특징 궤적을 추출한다. 그리고 SIFT 와 particle 궤적의 중요도를 조절하기 위해 가중치를 부여한다. 제안한 행동 인식 시스템의 효율성을 범용 데이터 셋을 이용한 실험을 통해 증명하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.448-449
• /
• 2022

In the image upscaling field, the method using deep learning is showing better results than using the interpolation method. And for hologram upscaling, using deep learning is showing better results than general interpolation. In this paper, the network structure and learning results are analyzed. The learning results are compared by adjusting the depth of the network and the number of channels at the same weight.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.78-79
• /
• 2021

본 논문에서는 시간 영역 오토인코더의 성능 개선을 위한 다중 대역 손실 함수를 제안한다. 기존의 시간 영역 오토인코더를 사용하는 압축 및 복원 모델은 저 대역 손실에 치중되어 고 대역 신호를 생성하지 못하고 다운 샘플링된 신호를 결과로 출력하는 문제점을 가진다. 이를 해결하기 위해 대역별로 손실을 분리하여 가중치를 조절할 수 있는 다중 대역 손실 함수를 제안한다. 제안하는 손실 함수가 적용된 오토인코더에 음성 신호를 입력하여 학습을 진행한 결과, 다운 샘플링이 발생하지 않으며 고 대역 신호가 복원되는 것을 스펙트로그램을 통해 확인하였다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.4
• /
• pp.102-115
• /
• 2011

The purpose of this study is to establish the evaluation model through the systematic process of selecting the indicators and to evaluate the environmental-control function on forest using GIS in Deagu for the sustainable forest planning. The 35 indicators as basic items were selected by literature review and those were squeezed into the 29 indicators through expert brainstorming. Also, the 8 indicators to evaluate environmental-control function were selected by the first survey and the 5 final indicators such as carbon sink, temperature decrease, wind formation, water circulation, air purification were determined by MCB analysis using the second survey. The evaluation model was established through the weight of each indicator by AHP analysis using the third survey. According to the result of evaluating the environmental-control function on forest, the functions around the top area of Mt. Ap, Mt. Biseul, Mt. Palgong had more than 66 scores. On the other hand, the functions around Mt. Waryong and forest of Chilgok in Buk-gu had less than 40 scores. It is necessary to improve the function through the sustainable restoration and management in case of forest that the environmental-control function was lower. Furthermore, these results will be able to be utilized as basic data in order to establish the preservation area and control development area at the urban, environmental, and forest planning.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.147-159
• /
• 2013

In medical visualization, volume visualization is widely used. Applying 3D images to diagnose requires high resolution and accurately implement visualization techniques are being researched accordingly. However, when a three-dimensional image volume visualization is implemented using volume data, aliasing will occur since using discrete data. Supersampling method, getting lots of samples, is used to reduce artifacts. One of the supersampling methods is Catmull-rom spline. This method calculates accurate interpolation value because it is easy to compute and pass through control points. But, Catmull-rom spline method occurs overshoot or undershoot in large gradient of pixel values. So, interpolated values are different from original signal. In this paper, we propose an adaptive adjusting weights interpolation method using Gaussian function. Proposed method shows that overshoot is reduced on the point has a large gradient and PSNR is higher than other interpolated image results.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.3
• /
• pp.315-321
• /
• 2014

This paper presents an integrated chassis control system with fail safety using optimum yaw moment distribution for a vehicle with steer-by-wire and brake-by-wire devices. The proposed system has two-level structure: upper- and lower-level controllers. In the upper-level controller, the control yaw moment is computed with sliding mode control theory. In the lower-level controller, the control yaw moment is distributed into the tire forces of active front steering(AFS) and electronic stability control(ESC) with the weighted pseudo-inverse based control allocation(WPCA) method. By setting the variable weights in WPCA, it is possible to take the sensor/actuator failure into account. In this framework, it is necessary to optimize the variables weights in order to enhance the yaw moment distribution. For this purpose, simulation-based tuning is proposed. To show the effectiveness of the proposed method, simulations are conducted on a vehicle simulation package, CarSim.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.6
• /
• pp.1175-1184
• /
• 2015

A depth map is an image which contains 3D distance information. Generally, it is difficult to acquire a high resolution (HD), noise-removed, good quality depth map directly from the camera. Therefore, many researches have been focused on acquisition of the high resolution and the good quality depth map by up-sampling and pre/post image processing of the low resolution depth map. However, many researches are lack of effective up-sampling for the edge region which has huge impact on image perceptual-quality. In this paper, we propose an up-sampling method, based on joint bilateral filter, which improves up-sampling of the edge region and visual quality of synthetic images by adopting different weights for the edge parts that is sensitive to human perception characteristics. The proposed method has gains in terms of PSNR and subjective video quality compared to previous researches.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.5
• /
• pp.402-409
• /
• 2018

In this paper, we propose a lunar landing scenario of a robotic lunar landing mission and implements an optimal landing trajectory at the powered descent phase based on the proposed scenario. The change of attitude of the lunar lander in the power descent phase affects not only the amount of fuel used but also sensor operation of image based navigation. Therefore, the attitude angular velocity is included in the cost function of the optimal control problem to minimize the unnecessary attitude change when the optimal landing trajectory generates at powered descent phase of the lunar landing. The influence of the change of attitude angular velocity on the optimal landing trajectory are analyzed by adjusting the weight of the attitude angular velocity. Based on the results, we suggest the proper weight to generate the optimal landing trajectory in order to minimize the influence of the attitude angular velocity.