• 대한전자공학회논문지SP
• /
• 제41권2호
• /
• pp.11-22
• /
• 2004

겹쳐진 물체의 분리에 대한 기존의 연구들은 주로 모델기반 정합방법을 사용하고 있어서 적용가능물체가 2차원물체에 한정되었고, 모델물체의 수가 증가하면 정합과정에 소요되는 시간이 지수적으로 증가하는 문제를 갖는다. 이러한 문제를 해결하기 위해 본 논문에서는 곡면을 포함하는 3차원물체를 대상으로 물체에 대한 정보가 없는 상황에서도 가리는 물체를 찾아내는 알고리즘을 제시한다. 이 방법을 이용함으로써 겹쳐진 물체의 인식이 독립된 하나의 물체를 인식하는 문제로 단순화될 수 있다. 제안하는 알고리즘은 물체를 면의 결합으로 해석하고 면들은 경계선을 속성으로 표현된다. 3차원 물체의 겹침은 2차원 영상에서 면의 겹침으로 보여 지고 면의 겹침은 경계선의 교차로 나타나는 특성을 이용하여 겹침의 형태를 경계선의 형태로 일반화하여 분류하는 기법을 사용하였다. 면사이의 겹침 관계를 면특징 관계도를 이용하여 표현하기 위해 관계계수를 정의하였고 관계계수의 값은 겹침의 형태를 보여주도록 개념화하였다. 제안된 알고리즘의 성능은 산업현장에서 사용되는 표준 부품을 임의로 겹치게하여 영상을 획득한 후 가리는 물체를 구분하는 실험을 통해 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5419-5435
• /
• 2017

The construction of panoramic images on smartphones and low-powered devices is a challenging task. In this paper, we propose a new approach for smoothly stitching images on mobile phones in the presence of moving objects in the scene. Our main contributions include handling moving object problems, reducing processing time, and generating rectangular panoramic images. First, unique and robust feature points are extracted using fast ORB method and a feature matching technique is applied to match the extracted feature points. After obtaining good matched feature points, we employ the non-deterministic RANSAC algorithm to discard wrong matches, and the hommography transformation matrix parameters are estimated with the algorithm. Afterward, we determine precise overlap regions of neighboring images and calculate their absolute differences. Then, thresholding operation and noise removal filtering are applied to create a mask of possible moving object regions. Sequentially, an optimal seam is estimated using dynamic programming algorithm, and a combination of linear blending with the mask information is applied to avoid seam transition and ghosting artifacts. Finally, image-cropping operation is utilized to obtain a rectangular boundary image from the stitched image. Experiments demonstrate that our method is able to produce panoramic images quickly despite the existence of moving objects.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.220-228
• /
• 2022

The directed tests produce an expectation model to assist the organization's heads and professionals with settling on the right and speedy choice. A directed deep learning strategy has been embraced and applied for SCADA information. In this paper, for the load shedding expectation overall power organization of Libya, a convolutional neural network with multi neurons is utilized. For contributions of the neural organization, eight convolutional layers are utilized. These boundaries are power age, temperature, stickiness and wind speed. The gathered information from the SCADA data set were pre-handled to be ready in a reasonable arrangement to be taken care of to the deep learning. A bunch of analyses has been directed on this information to get a forecast model. The created model was assessed as far as precision and decrease of misfortune. It tends to be presumed that the acquired outcomes are promising and empowering. For assessment of the outcomes four boundary, MSE, RMSE, MAPE and R2 are determined. The best R2 esteem is gotten for 1-overlap and it was 0.98.34 for train information and for test information is acquired 0.96. Additionally for train information the RMSE esteem in 1-overlap is superior to different Folds and this worth was 0.018.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1103-1108
• /
• 2003

The fatigue strength of welded joint is influenced by the welding residual stress which is relaxed depending on local stress distributed in vicinity of stress raisers, eg. under cut, overlap and blow hole. To evaluate its fatigue life the geometry of the stress raisers and the welding residual stress should be taken into account. The several methods based on notch strain approach have been proposed in order to consider the two factors above mentioned. These methods, however, have shown considerable differences between analytical and experimental results. It is due to the fact that the amount of the relaxed welding residual stress evaluated by the cyclic stress-strain relationship do not correspond with that occurred in reality. In this paper the residual stress relaxation model based on experimental results was used in order to reduce the discrepancy of the estimated amount of the relaxed welding residual stress. Under an assumption of the superimposition of the relaxed welding residual stress and the local stress, a modified notch strain approach was proposed and verified to the cruciform welded joint.

• 경영과학
• /
• 제22권1호
• /
• pp.167-178
• /
• 2005

The 2DBPP(Two-Dimensional Bin Packing Problem) is a problem of packing each item into a bin so that no two items overlap and the number of required bins is minimized under the set of rectangular items which may not be rotated and an unlimited number of identical .rectangular bins. The 2DBPP is strongly NP-hard and finds many practical applications in industry. In this paper we discuss a tabu search approach which includes tabu list, intensifying and diversification Strategies. The HNFDH(Hybrid Next Fit Decreasing Height) algorithm is used as an internal algorithm. We find that use of the proper parameter and function such as maximum number of tabu list and space utilization function yields a good solution in a reduced time. We present a tabu search algorithm and its performance through extensive computational experiments.

• 대한유전성대사질환학회지
• /
• 제23권2호
• /
• pp.1-7
• /
• 2023

유전성 대사질환은 생화학적 대사 이상에 의해 발생하는 질환 군으로, 매우 다양할 뿐만 아니라 임상 양상이 서로 겹칠 수 있어 진단에 어려움을 겪을 수 있다. 과거에는 유전성 대사질환의 원인이 될 수 있는 유전자를 선정한 후 한 개씩 분석하는 방식으로 유전자 검사를 시행했다. 하지만, 최근에는 차세대 염기서열분석 기술이 발전함에 따라 유전성 대사질환과 관련된 수백-수천개의 유전자를 한꺼번에 분석하거나, 인간의 모든 유전자를 포함하는 엑솜/게놈 분석을 시행한 후 원인 유전자를 찾는 방식으로 유전 진단의 패러다임이 바뀌고 있다. 본 종설에서는 차세대 염기서열분석을 이용한 유전성 대사질환의 유전 진단 방법과 진단율 및 주의점 등을 살펴보고자 한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.33-36
• /
• 2001

With all the researches to define human genom and to look for some new bio-activated material in the bio-technology field recently, it is more highly needed to analyse DNA or so called Material than ever before. First, the lanes are extracted based on histogram analysis and projection technique. And then three other approaches are applied for band extraction: SB, RG-1, and RG-2. In SB method, a search line is set dividing each lane equally and vertically to find peaks and valleys. And according to them, minimum enclosing rectangle of each band is determined. In RC-1 approach, on the other hand, band areas are extracted by region growing with the peaks as seeds, avoiding the overlap with the neighboring bands. In RC-2 approach, peaks and valleys are searched in two lines that trisect the lane vertically, and the pair of peaks in the same band are determined, and then used to grow the region. To compare the accuracy of the three suggested methods, we measure the location and amount of bands. The result shows that the mean deviation of the location is 0.06, 0.03, and 0.01 for SB, RG-1, and RC-2 respectively. And the mean deviation of the amount of bands is 0.08, 0.05, and 0.02 for SB, RG-1, and RG-2 respectively. In conclusion, the RG-2 method suggested in this paper appears to be the most reliable on the degree of the accuracy in measuring the location and amount of bands

• Structural Engineering and Mechanics
• /
• 제59권2호
• /
• pp.313-326
• /
• 2016

In this study the three-dimensional nonlinear finite element method was used to analyze the stresses distribution in the adhesive layer used to joint two Aluminum 2024-T3 adherends. We consider in this study the effect of different parameters witch directly affect the values of different stresses. The experimental design method is used to investigate the effects of geometrical parameters of the single lap joint in order to achieve an optimization of the assembly with simple lap joint. As a result, it can be said that both the geometrical modifications of the adhesive and adherends edge have presented a significant effect at the overlap edge thereby causing a decrease in peel and shear stresses. In addition, an analytical model is also given to predict in a simple but effective way the joint strength and its dependence on the geometrical parameters. This approach can help the designers to improve the quality and the durability of the structural adhesive joints.

• 한국문헌정보학회지
• /
• 제42권4호
• /
• pp.375-390
• /
• 2008

본 사례연구의 목적은 이용 당 비용 접근방법을 통하여 과학기술분야 해외학술지의 경제성을 분석하기 위한 것이다. 연구 목적을 달성하기 위하여 K기관이 구독중인 해외학술지 중 무작위로 선정한 1,745종을 대상으로 하였고, 심층 분석을 위하여 학술지 속성 중의 영향력 계수(IF), 타기관 중복소장수, 언어, 구독비용, 이용빈도에 따른 상관관계를 분석하였다. 연구 결과에 의하면 영향력 계수를 제외한 나머지 모든 속성들은 해외학술지의 이용당 비용과 서로 유의한 상관관계가 있는 것으로 나타났으며, 이들 각 속성의 내부 그룹 간 차이분석을 통하여 보다 자세한 분석하였다.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1089-1102
• /
• 2017

In software systems, it has been observed that a fault is often caused by an interaction between a small number of input parameters. Even for moderately sized software systems, exhaustive testing is practically impossible to achieve. This is either due to time or cost constraints. Combinatorial (t-way) testing provides a technique to select a subset of exhaustive test cases covering all of the t-way interactions, without much of a loss to the fault detection capability. In this paper, an approach is proposed to generate 2-way (pairwise) test sets using genetic algorithms. The performance of the algorithm is improved by creating an initial solution using the overlap coefficient (a similarity matrix). Two mutation strategies have also been modified to improve their efficiency. Furthermore, the mutation operator is improved by using a combination of three mutation strategies. A comparative survey of the techniques to generate t-way test sets using genetic algorithms was also conducted. It has been shown experimentally that the proposed approach generates faster results by achieving higher percentage coverage in a fewer number of generations. Additionally, the size of the mixed covering arrays was reduced in one of the six benchmark problems examined.