• International Journal of Control, Automation, and Systems
• /
• 제6권6호
• /
• pp.809-817
• /
• 2008

Program plagiarism is widespread due to intelligent software and the global Internet environment. Consequently the detection of plagiarized source code and software is becoming important especially in academic field. Though numerous studies have been reported for detecting plagiarized pairs of codes, we cannot find any profound work on understanding the underlying mechanisms of plagiarism. In this paper, we study the evolutionary process of source codes regarding that the plagiarism procedure can be considered as evolutionary steps of source codes. The final goal of our paper is to reconstruct a tree depicting the evolution process in the source code. To this end, we extend the well-known bioinformatics approach, a local alignment approach, to detect a region of similar code with an adaptive scoring matrix. The asymmetric code similarity based on the local alignment can be considered as one of the main contribution of this paper. The phylogenetic tree or evolution tree of source codes can be reconstructed using this asymmetric measure. To show the effectiveness and efficiency of the phylogeny construction algorithm, we conducted experiments with more than 100 real source codes which were obtained from East-Asia ICPC(International Collegiate Programming Contest). Our experiments showed that the proposed algorithm is quite successful in reconstructing the evolutionary direction, which enables us to identify plagiarized codes more accurately and reliably. Also, the phylogeny construction algorithm is successfully implemented on top of the plagiarism detection system of an automatic program evaluation system.

• 한국콘텐츠학회논문지
• /
• 제6권10호
• /
• pp.134-142
• /
• 2006

본 논문에서는 영상의 유사성을 측정하는데 많이 이용되는 Hausdorff거리 기법이 텍스트 영상을 검색하는 분야에도 효과적임을 입증하고자 한다. 즉, 시차를 두고 스캔된 임의의 텍스트 영상들의 동일성 여부를 판단할 수 있는 영상기반 텍스트 매칭 기법을 제안하고 이를 위해 지역 밀집도와 Hausdorff 거리를 이용한다. Hausdorff 거리 방법은 처리시간이 오래 걸리는 단점이 존재하는데, 본 논문에서는 지역 밀집도 알고리즘을 이용한 특징점 추출을 수행하여 이를 보완하였다. 우편 봉투에서 얻은 텍스트 영상으로 190개의 동일 영상 190개의 비등일 영상을 만들어 실험을 수행하였다. 기존에 영상 간의 유사도 매칭에 가장 일반적으로 이용되는 이진 상관도 및 Hausdorff 거리 방법과 본 논문에서 제안한 수정된 Hausdorff 방법의 실험 결과를 비교한 결과, 유사한 영역을 찾고 일치하는 정도를 얻는데 있어 다른 방법에 비해 약 2.7%에서 9.0%의 높은 정확률을 얻어 성능의 우수성을 입증하였다.

• 대한전자공학회논문지SP
• /
• 제39권4호
• /
• pp.370-380
• /
• 2002

전방 관측 적외선 영상에서 가려짐이 없거나 가려짐이 있는 군용차량을 인식할 수 있는 자동 표적인식 알고리즘을 제안한다. 표적을 배경으로부터 분리한 후에 광역적인 형상 특징을 찾기 위해 표적의 경계선에 대해 물체의 중심을 기준으로 방사함수 (radial function)를 정의한다. 또한, 형상 정보가 집중되어 있는 표적의 윗 부분으로부터 국부적인 형상 특징을 찾기 위해 두 개의 특징점과 경계선으로부터 거리함수를 정의한다. 두 개의 함수와 경계선으로부터 4개의 광역적 형상 특징과 4개의 국부적 형상 특징을 제안한다. 이 특징들은 병진, 회전 그리고 크기변화에 대해 기존의 특징 벡터들 보다 좋은 불변성을 가진다. 이 특징들을 이용하여 가려짐이 있는 표적과 가려짐이 없는 표적을 구분하여 인식하기 위한 새로운 분류 방식을 제안한다. 실험을 통해 제안한 특징들의 불변성과 인식 성능을 기존의 특징벡터들과 비교하여 제안한 표적 인식 알고리즘의 우수성을 입증한다.

• 한국환경과학회지
• /
• 제22권11호
• /
• pp.1373-1381
• /
• 2013

Mt. Yeonae is at Gijang-gun in Busan and is surrounded by farming lands on three sides. The search for the species composition and dynamics of local communities were studied at Mt. Yeonae of how spatial similarity decays with geographic distance. The index values of Z$\ddot{u}$rich-Montpellier School's phytosociology at the 12 plots was compared to a distribution of similarly using 20 m quadrates at 12 sites. The specific communities were five including Pinus densiflora - Quercus variabilis community. Six species were significant similarity between neighboring sites by using the spatial autocorrelation coefficient, Moran's I. If Mt. Yeonae was destroyed by an artificial action, some spatial correlated species such as P. densiflora and Q. variabilis will be collapsed because of no maintaining the effective population sizes.

• Journal of Computational Design and Engineering
• /
• 제3권4호
• /
• pp.330-336
• /
• 2016

The present work is concerned with heat and mass transfer of an electrically conducting second grade MHD fluid past a semi-infinite stretching sheet with convective surface heat flux. The analysis accounts for thermophoresis and thermal radiation. A similarity transformations is used to reduce the governing equations into a dimensionless form. The local similarity equations are derived and solved using Nachtsheim-Swigert shooting iteration technique together with Runge-Kutta sixth order integration scheme. Results for various flow characteristics are presented through graphs and tables delineating the effect of various parameters characterizing the flow. Our analysis explores that the rate of heat transfer enhances with increasing the values of the surface convection parameter. Also the fluid velocity and temperature in the boundary layer region rise significantly for increasing the values of thermal radiation parameter.

• 방송공학회논문지
• /
• 제7권2호
• /
• pp.136-144
• /
• 2002

본 논문에서는 다양하게 변화되는 캐릭터 영상을 색상과 형태의 정보를 포함한 국부 색상 분포(local color histogram)를 이용하여 유사도 검색을 하는 강인한 방법을 제안한다. 국부 색상 분포의 값을 양자화 하여 특징 값을 최적화하고, 대규모 데이터베이스에 저장되어 있는 영상정보와 Bipartite matching을 이용하여 검색한다. 제안되는 방법은 다양하게 변화되는 영상의 유사도 검색, 동영상 및 정지 영상에서 유사 영상 검색에 매우 효과적인 방법이다.

• Journal of information and communication convergence engineering
• /
• 제10권1호
• /
• pp.40-44
• /
• 2012

Data mining, which is attracting public attention, is a process of drawing out knowledge from a large mass of data. The key technique in data mining is the ability to maximize the similarity in a group and minimize the similarity between groups. Since grouping in data mining deals with a large mass of data, it lessens the amount of time spent with the source data, and grouping techniques that shrink the quantity of the data form to which the algorithm is subjected are actively used. The current grouping algorithm is highly sensitive to static and reacts to local minima. The number of groups has to be stated depending on the initialization value. In this paper we propose a gene algorithm that automatically decides on the number of grouping algorithms. We will try to find the optimal group of the fittest function, and finally apply it to a data mining problem that deals with a large mass of data.

• International Journal of Fluid Machinery and Systems
• /
• 제10권3호
• /
• pp.197-208
• /
• 2017

When Francis turbines operate at partial load, residual swirl in the draft tube causes low-frequency pulsation of pressure and power output. Scale effects and system response may bias the prediction of prototype behavior based on laboratory tests, but could be overcome by means of a 1D analytical model. This paper deals with the two most important features of such a model, the compliance and the source of excitation. In a distributed-parameter version, compliance should be represented as an exponential function of local pressure. Lack of similarity due to different Froude number can thus be compensated. The normally unknown gas content in the vortex cavity has significant influence on the pulsation, and should therefore be measured and considered as a test parameter.

• Genomics & Informatics
• /
• 제20권3호
• /
• pp.36.1-36.6
• /
• 2022

BLAST, a basic bioinformatics tool for searching local sequence similarity, has been one of the most widely used bioinformatics programs since its introduction in 1990. Users generally use the web-based NCBI-BLAST program for BLAST analysis. However, users with large sequence data are often faced with a problem of upload size limitation while using the web-based BLAST program. This proves inconvenient as scientists often want to run BLAST on their own data, such as transcriptome or whole genome sequences. To overcome this issue, we developed NBLAST, a graphical user interface-based BLAST program that employs a two-way system, allowing the use of input sequences either as "query" or "target" in the BLAST analysis. NBLAST is also equipped with a dot plot viewer, thus allowing researchers to create custom database for BLAST and run a dot plot similarity analysis within a single program. It is available to access to the NBLAST with http://nbitglobal.com/nblast.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.195-203
• /
• 2022

Noise generated during image acquisition and transmission can negatively impact the results of image processing applications, and noise removal is typically a part of image preprocessing. Denoising techniques combined with nonlocal techniques have received significant attention in recent years, owing to the development of sophisticated hardware and image processing algorithms, much attention has been paid to; however, this approach is relatively poor for edge preservation of fine image details. To address this limitation, the current study combined a steering kernel technique with adaptive masks that can adjust the size according to the noise intensity of an image. The algorithm sets the steering weight based on a similarity comparison, allowing it to respond to edge components more effectively. The proposed algorithm was compared with existing denoising algorithms using quantitative evaluation and enlarged images. The proposed algorithm exhibited good general denoising performance and better performance in edge area processing than existing non-local techniques.