• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1377-1389
• /
• 2016

This paper presents a target model update scheme for the mean-shift tracking with background weighted histogram. In the scheme, the target candidate histogram is corrected by considering the back-projection weight of each pixel in the kernel after the best target candidate in the current frame image is chosen. In each frame, the target model is updated by the weighted average of the current target model and the corrected target candidate. We compared our target model update scheme with the previous ones by applying several test sequences. The experimental results showed that the object tracking accuracy was greatly improved by using the proposed scheme.

• 한국정보처리학회논문지
• /
• 제6권8호
• /
• pp.2245-2252
• /
• 1999

분산 공유 메모리(Distributed Shared Memory)시스템은 사용자에게 간단한 공유 메모리 개념을 제공하기 때문에 노드 사이의 데이터 이동에 관여할 필요가 없다. 각 노드는 프로세서, 메모리, 그리고 네트워크 연결장치 등으로 이루어져 있다. 메모리는 페이지 단위로 구분되며 페이지는 여러 노드에 복제본을 소유할 수 있다. 이들간 일치성을 유지하기 위하여 무효화 방식(invalidate protocol)과 갱신 방식(update protocol)이 전통적으로 많이 사용되었다. 이 두 가지 프로토콜의 성능은 시스템 변수 또는 응용 프로그램의 공유 메모리 사용 형태에 따라 좌우된다. 메모리 사용 형태에 적응하기 위하여 경쟁적 갱신(competitive update) 프로토콜은 가까운 장래에 사용되어질 복제본을 갱신시키는 반면, 다른 복제본은 무효화시킨다. 본 논문에서는 노드 사이의 통신비용이 동일하지 않은 구조를 감안한 가중치를 고려한(weighted) 경쟁적 갱신 프로토콜을 제안하였다. 시뮬레이션에 의한 성능 측정 결과 가중치를 고려한 경쟁적 갱신 프로토콜의 성능 향상을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.871-891
• /
• 2019

Visual tracking is a challenging task that needs learning an effective model to handle the changes of target appearance caused by factors such as pose variation, illumination change, occlusion and motion blur. In this paper, a novel tracking algorithm based on weighted local sub-space reconstruction error is presented. First, accounting for the appearance changes in the tracking process, a generative weight calculation method based on structural reconstruction error is proposed. Furthermore, a template update scheme of occlusion-aware is introduced, in which we reconstruct a new template instead of simply exploiting the best observation for template update. The effectiveness and feasibility of the proposed algorithm are verified by comparing it with some state-of-the-art algorithms quantitatively and qualitatively.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.264-267
• /
• 2002

This paper proposed a effective priority selection algorithm named weighted round-robin algorithm and show the implementation result of DMAC priority selection module using prosed weighted round-robin algorithm. I parameterize timing constraints of each functional module, which decide the effectiveness of system. Proposed weighted round-robin algorithm decide the most effective module for data transmission using parameterize timing constraints and update timing parameter of each module for next transmission module selection. I implement DMAC priority selection module using this weighted round-robin algorithm and can improve the timing effective for data transmission from memory to functional module or one functional module to another functional module.

• 한국통신학회논문지
• /
• 제16권7호
• /
• pp.628-639
• /
• 1991

GaAs MESFET 모델의 정확한 매채변수 값을 구하기 위하여 바이어스 의존성을 바탕으로 3가지 바이어스 변화에 대한 S-,파라미터 측정만으로 모델 매개변수를 추출할 수 있는 새로운 계산 방법을 제시한다. Weighted Broyden update방법의 최적화 과정에서 얻어지는 오차 함수에 대한 매개 변수의 검토를 이용하여 전형 및 비전형 매개 변수의 유일해를 결정한다. 제안된 방법을 적용하기 위해 Marterka & Kacprzak 모델을 사용하였으며 추출한 매개변수 값의 정당성을 측정치와 비교함으로서 입증하였다.

• 전자공학회논문지B
• /
• 제33B권9호
• /
• pp.117-123
• /
• 1996

In this paper, we present a new learning method for the fuzzy ARTMAP which is effective for the noisy input patterns. Conventional fuzzy ARTMAP employs only fuzzy AND operation between input vector and weight vector in learning both top-down and bottom-up weight vectors. This fuzzy AND operation causes excessive update of the weight vector in the noisy input environment. As a result, the number of spurious categories are increased and the recognition ratio is reduced. To solve these problems, we propose a new method in updating the weight vectors: the top-down weight vectors of the fuzzy ART system are updated using weighted average of the input vector and the weight vector itself, and the bottom-up weight vectors are updated using fuzzy AND operation between the updated top-down weitht vector and bottom-up weight vector itself. The weighted average prevents the excessive update of the weight vectors and the fuzzy AND operation renders the learning fast and stble. Simulation results show that the proposed method reduces the generation of spurious categories and increases the recognition ratio in the noisy input environment.

• The Journal of the Acoustical Society of Korea
• /
• 제25권4E호
• /
• pp.154-158
• /
• 2006

In this paper, we suggest a noise estimation method for speech enhancement in nonstationary noisy environments. The proposed method consists of the following two main processes. First, in order to receive fewer affect of variable signals, a best fitting regression line is used, which is obtained by applying a least squares method to coefficient magnitudes in a node with a uniform wavelet packet transform. Next, in order to update the noise estimation efficiently, a differential forgetting factor and a correlation coefficient per subband are used, where subband is employed for applying the weighted value according to the change of signals. In particular, this method has the ability to update the noise estimation by using the estimated noise at the previous frame only, without utilizing the statistical information of long past frames and explicit nonspeech frames by voice activity detector. In objective assessments, it was observed that the performance of the proposed method was better than that of the compared (minima controlled recursive averaging, weighted average) methods. Furthermore, the method showed a reliable result even at low SNR.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.894-900
• /
• 2005

A new approach to the straightforward implementation of the unscented filter in a unit quaternion space is proposed for spacecraft attitude estimation. Since the unscented filter is formulated in a vector space and the unit quaternions do not belong to a vector space but lie on a nonlinear manifold, the weighted sum of quaternion samples does not produce a unit quaternion estimate. To overcome this difficulty, a method of weighted mean computation for quaternions is derived in rotational space, leading to a quaternion with unit norm. A quaternion multiplication is used for predicted covariance computation and quaternion update, which makes a quaternion in a filter lie in the unit quaternion space. Since the quaternion process noise increases the uncertainty in attitude orientation, modeling it either as the vector part of a quaternion or as a rotation vector is considered. Simulation results illustrate that the proposed approach successfully estimates spacecraft attitude for large initial errors and high tip-off rates, and modeling the quaternion process noise as a rotation vector is more optimal than handling it as the vector part of a quaternion.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.68-74
• /
• 2019

Along with the deeper architecture in the deep learning approaches, the need for the data becomes very big. In the real problem, to get huge data in some disciplines is very costly. Therefore, learning on limited data in the recent years turns to be a very appealing area. Meta-learning offers a new perspective to learn a model with this limitation. A state-of-the-art model that is made using a meta-learning framework, Meta-SGD, is proposed with a key idea of learning a hyperparameter or a learning rate of the fast adaptation stage in the outer update. However, this learning rate usually is set to be very small. In consequence, the objective function of SGD will give a little improvement to our weight parameters. In other words, the prior is being a key value of getting a good adaptation. As a goal of meta-learning approaches, learning using a single gradient step in the inner update may lead to a bad performance. Especially if the prior that we use is far from the expected one, or it works in the opposite way that it is very effective to adapt the model. By this reason, we propose to add a weight term to decrease, or increase in some conditions, the effect of this prior. The experiment on few-shot learning shows that emphasizing or weakening the prior can give better performance than using its original value.

• 대한전자공학회논문지SD
• /
• 제38권8호
• /
• pp.54-61
• /
• 2001

High-bandwidth DRAM을 위해 1Gb/s의 데이터 전송률까지 동작하고 그 출력 전압 스윙이 온도와 전원 전압(VDD) 변동에 무관한 CMOS open-drain 출력 구조 회로를 설계하였다. 출력 구동 회로는 여섯 개의 binary-weighted NMOS 트랜지스터로 구성되는데, 이 여섯 개 중에서 ON시킬 current control register의 내용은 추가 호로 없이 DRAM 칩에 존재하는 auto refresh 신호를 이용하여 새롭게 수정하였다. Auto refresh 시간 구간동안 current control register를 수정하는데, 이 시간 구간동안 부궤환 (negative feedback) 동작에 의해 low level 출력 전압($V_OL$)이 저전압 밴드갭 기준전압 발생기(bandgap reference voltage generator)에 의해서 만들어진 기준전압($V_{OL.ref}$)과도 같도록 유지된다. 테스트 칩은 1Gb/s의 데이터 전송률까지 성공적으로 동작하였다. 온도 $20^{\circ}C$~$90^{\circ}C$, 전원 전압 2.25V~2.75V영역에서 최악의 경우 제안된 출력 구동 회로의 $V_{OL.ref}$와 $V_OL$의 변동은 각각 2.5%와 725%로 측정된 반면, 기존의 출력 구동 회로의 $V_OL$의 변동은 같은 온도의 전원 접압의 영역에 대해 24%로 측정되었다.