• 전자공학회논문지CI
• /
• 제47권1호
• /
• pp.92-103
• /
• 2010

본 논문에서는 Dynamic Space Time Warping(DSTW) 알고리즘을 이용하여 손동작을 다양한 배경에서도 정확하게 인식할 수 있는 방법을 제안한다. DSTW 알고리즘을 이용한 기존의 손동작 인식 방법은 질의 영상의 매 프레임마다 검출된 다수의 손 후보 영역과 모델 영상을 시간 축 상으로 비교하는 방법이다. 그러나 DSTW 알고리즘을 이용한 기존의 손동작 인식 방법은 손을 포함하지 않은 후보 영역들(배경, 팔꿈치 등)에 의해 오 인식될 수 있는 경로를 생성하며, 그 결과로 사용자가 의도하지 않은 손동작으로 인식된다. 이러한 단점을 해결하기 위해서, 본 논문에서는 손 후보 영역의 불변 모멘트를 이용하여 질감정보를 추출한 후 후보 영역들 사이의 유사도를 비교한다. 제안한 방법을 통해 계산된 유사도는 모델 영상과 질의 영상의 매칭 비용에 가중치로 적용된다. 실험 결과를 통해 제안한 방법은 다양한 배경에서도 사용자의 손동작을 정확하게 인식하였으며 기존의 방법에 비해 약 13%의 인식률이 향상한 것을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제27권11호
• /
• pp.123-130
• /
• 2022

최근 API Call 정보를 기반으로 안드로이드 악성코드를 탐지 및 분류하는 연구가 활발하게 진행되고 있다. 그러나 API Call 기반의 악성코드 분류는 방대한 데이터 양과 높은 차원 특성으로 인해 악성코드 분석과 학습 모델 구축 과정에서 과도한 시간과 자원이 소모된다는 심각한 제한사항을 가진다. 이에 본 연구에서는 방대한 API Call 정보를 포함하고 있는 CICAndMal2020 데이터세트를 대상으로 PCA(Principal Component Analysis, 주성분분석)를 사용하여 차원을 대폭 축소시킨 후 LightGBM, Random Forest, k-Nearest Neighbors 등의 다양한 분류 기법 모델을 적용하여 결과를 분석하였다. 그 결과 PCA가 원본 데이터의 특성을 유지하면서 데이터 특성의 차원은 획기적으로 감소시키고 우수한 악성코드 분류 성능을 달성함을 확인하였다. 이진분류 및 다중분류 모두 데이터 특성을 전체 크기의 1% 수준 이하로 줄이더라도 이전 연구 결과보다 높은 수준의 정확도를 나타내었다.

• 한국CDE학회논문집
• /
• 제14권1호
• /
• pp.60-68
• /
• 2009

Because of the reduced product life-cycle, industries are making an effort to bring down the process planning time. In the traditional approach, we have to analyze established process planning, then design the time chart based on process information and drawing the formal time chart such as SOP(sequence of operation). Thereafter, it will be converted to PLC code that is a time consuming and redundant job. Similarly, Industrial automated process uses PLC Code to control the factory; however, control information and control code(PLC code) are difficult to understand. Hence, industries prefer writing new control code instead of using the existing one. It shows the lack of information reusability in the existing process planning. As a result, to reduce this redundancy and lack of reusability, we propose SOS-Net modeling method. Unlike past stabilized process planning that is rigid to any change; our proposed SOS-Net modeling method is more adaptable to the new changes. The SOS-Net model is easy to understand and easy to convert into PLC Code accordingly. Therefore, we can easily modify the control information and reuse it for new process planning. The proposed model plays an intermediary role between process planning and PLC code generation. It can reduce the process planning and implementation time as well as cost.

• 대한수학회논문집
• /
• 제20권3호
• /
• pp.579-588
• /
• 2005

In this paper we study the asymptotics for the energy density in the self-dual Chern-Simons CP(1) model. When the sequence of corresponding multivortex solutions converges to the topological limit, we show that the field configurations saturating the energy bound converges to the limit function. Also, we show that the energy density tends to be concentrated at the vortices and antivortices as the Chern-Simons coupling constant $\kappa$ goes to zero.

• 한국지능시스템학회논문지
• /
• 제26권6호
• /
• pp.471-476
• /
• 2016

본 논문은 깊이 정보를 기반으로 모션 히스토리 영상 및 기울기 방향성 히스토그램과 적출 모델을 사용하여 연속적인 사람 행동들을 인식하는 시스템을 설명하고 연속적인 행동 인식 시스템에서 인식 성능을 개선하기 위해 행동 적출을 수행하는 적출 모델을 제안한다. 본 시스템의 구성은 전처리 과정, 사람 행동 및 적출 모델링 그리고 연속적인 사람 행동 인식으로 이루어져 있다. 전처리 과정에서는 영상 분할과 시공간 템플릿 기반의 특징을 추출하기 위하여 Depth-MHI-HOG 방법을 사용하였으며, 추출된 특징들은 사람 행동 및 적출 모델링 과정을 통해 시퀀스들로 생성된다. 이 생성된 시퀀스들과 은닉 마르코프 모델을 사용하여 정의된 각각의 행동에 적합한 사람 행동 모델과 제안된 적출 모델을 생성한다. 연속적인 사람 행동 인식은 연속적인 행동 시퀀스에서 적출 모델에 의해 의미 있는 행동과 의미 없는 행동을 분할하는 행동 적출과 의미 있는 행동 시퀀스에 대한 모델의 확률 값들을 비교하여 연속적으로 사람 행동들을 인식한다. 실험 결과를 통해 제안된 모델이 연속적인 행동 인식 시스템에서 인식 성능을 효과적으로 개선하는 것을 검증한다.

• 품질경영학회지
• /
• 제47권4호
• /
• pp.823-835
• /
• 2019

Purpose: This study deals with a production planning and scheduling problem to minimize the total weighted tardiness on hybrid flow shop with sets of non-identical parallel machines on stages, where parallel machines in the set are dedicated to perform specific subsets of jobs and sequence-dependent setup times are also considered. Methods: A two-stage approach, that applies MILP model in the 1st stage and dispatching rules in the 2nd stage, is proposed in this paper. The MILP model is used to assign jobs to a specific machine in order to equalize the workload of the machines at each stage, while new dispatching rules are proposed and applied to sequence jobs in the queue at each stage. Results: The proposed two-stage approach was implemented by using a commercial MILP solver and a commercial simulation software and a case study was developed based on the spark plug manufacturing process, which is an automotive component, and verified using the company's actual production history. The computational experiment shows that it can reduce the tardiness when used in conjunction with the dispatching rule. Conclusion: This proposed two-stage approach can be used for HFS systems with dedicated machines, which can be evaluated in terms of tardiness and makespan. The method is expected to be used for the aggregated production planning or shop floor-level production scheduling.

• BMB Reports
• /
• 제29권1호
• /
• pp.1-10
• /
• 1996

The binding interaction of ethidium to a series of synthetic deoxyoligonucleotides containing a B-Z junction between left-handed Z-DNA and right-handed B-DNA, was studied. The series of deoxyoligonucleotides was designed so as to vary a dinucleotide step immediately adjacent to a B-Z junction region. Ethidium binds to the right-handed DNA forms and hybrid B-Z forms which contain a B-Z junction, in a highly cooperative manner. In a series of deoxyoligonucleotides, the binding affinity of ethidium with DNA forms which were initially hybrid B-Z forms shows over an order of magnitude higher than that with any other DNA forms, which were entirely in B-form DNA The cooperativity of binding isotherms were described by an allosteric binding model and by a neighbor exclusion model. The binding data were statistically compared for two models. The conformation of allosterically converted DNA forms under binding with ethidium is found to be different from that of the initial B-form DNA as examined by CD spectra. The ratio of the binding constant was interestingly correlated to the free energy of base unstacking and the conformational conversion of the dinucleotide. The more the base stacking of the dinucleotide is unstable, or the harder the conversion of B to A conformation, the higher the ratio of the binding constant of ethidium with the allosterically converted DNA forms and with the initial B-Z hybrid forms. DNA sequence around a B-Z junction region affects the binding affinity of ethidium. The results in this study demonstrate that ethidium could preferentially interact with unusual DNA structures.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2000년도 춘계공동학술대회 논문집
• /
• pp.405-408
• /
• 2000

The objective of this paper is to develop a model to integrate process planning and resource planning through analysis of the machine tool selection and operations sequencing problem. The model is formulated as a travelling salesman problem with precedence relations. To solve our model, we also propose an efficient genetic algorithm based on topological sort concept.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제12권3호
• /
• pp.169-178
• /
• 2005

In this paper we study the existence and local asymptotic limit of the topological Chern-Simons vortices of the CP(1) model in $\mathbb{R}^2$. After reducing to semilinear elliptic partial differential equations, we show the existence of topological solutions using iteration and variational arguments & prove that there is a sequence of topological solutions which converges locally uniformly to a constant as the Chern­Simons coupling constant goes to zero and the convergence is exponentially fast.

• 전자공학회논문지S
• /
• 제35S권3호
• /
• pp.176-184
• /
• 1998

We present a sequential factorization method using singular value decomposition (SVD) for recovering both the three-dimensional shape of an object and the motion of camera from a sequence of images. We employ paraperpective projection [6] for camera model to handle significant translational motion toward the camera or across the image. The proposed mthod not only quickly gives robust and accurate results, but also provides results at each frame becauseit is a sequential method. These properties make our method practically applicable to real time applications. Considerable research has been devoted to the problem of recovering motion and shape of object from image [2] [3] [4] [5] [6] [7] [8] [9]. Among many different approaches, we adopt a factorization method using SVD because of its robustness and computational efficiency. The factorization method based on batch-type computation, originally proposed by Tomasi and Kanade [1] proposed the feature trajectory information using singular value decomposition (SVD). Morita and Kanade [10] have extenened [1] to asequential type solution. However, Both methods used an orthographic projection and they cannot be applied to image sequences containing significant translational motion toward the camera or across the image. Poleman and Kanade [11] have developed a batch-type factorization method using paraperspective camera model is a sueful technique, the method cannot be employed for real-time applications because it is based on batch-type computation. This work presents a sequential factorization methodusing SVD for paraperspective projection. Initial experimental results show that the performance of our method is almost equivalent to that of [11] although it is sequential.