• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.952-959
• /
• 2018

Clustering is one of the most fundamental algorithms in machine learning. The performance of clustering is affected by the distribution of data, and when there are more data or more dimensions, the performance is degraded. For this reason, we use a stacked auto encoder, one of the deep learning algorithms, to reduce the dimension of data which generate a feature vector that best represents the input data. We use k-means, which is a famous algorithm, as a clustering. Sine the feature vector which reduced dimensions are also multi dimensional, we use the Euclidean distance as well as the cosine similarity to increase the performance which calculating the similarity between the center of the cluster and the data as a vector. A deep clustering networks combining a stacked auto encoder and k-means re-trains the networks when the k-means result changes. When re-training the networks, the loss function of the stacked auto encoder and the loss function of the k-means are combined to improve the performance and the stability of the network. Experiments of benchmark image ad document dataset empirically validated the power of the proposed algorithm.

• BMB Reports
• /
• 제39권5호
• /
• pp.578-585
• /
• 2006

The cDNA of a firefly luciferase from lantern mRNA of Lampyroidea maculata has been cloned, sequenced and functionally expressed. The cDNA has an open reading frame of 1647 bp and codes for a 548-residue-long polypeptide. Noteworthy, sequence comparison as well as homology modeling showed the highest degree of similarity with H. unmunsana and L. mingrelica luciferases, suggesting a close phylogenetic relationship despite the geographical distance separation. The deduced amino acid sequence of the luciferase gene of firefly L. maculata showed 93% identity to H. unmunsana. Superposition of the three-dimensional model of L. maculata luciferase (generated by homology modeling) and three dimensional structure of Photinus pyralis luciferase revealed that the spatial arrangements of Luciferin and ATP-binding residues are very similar. Putative signature of AMP-binding domain among the various firefly species and Lampyroidea maculata was compared and a striking similarity was found. Different motifs and sites have been identified in Lampyroidea maculata by sequence analysis. Expression and purification of luciferase from Lampyroidea maculata was carried out using Ni-NTA Sepharose. Bioluminescence emission spectrum was similar to Photinus pyralis luciferase.

• 한국화재소방학회논문지
• /
• 제15권2호
• /
• pp.91-95
• /
• 2001

복도나 터널과 같이 특정한 방향성을 가지는 공간에서는 천장아래에 형성되는 연기선단의 성상해석이 학술적인 면에서나 실용적인 면에서도 매우 중요하다. 본 연구는 2차원 축대칭 천장제트 선단의 전파속도를 모델화하기 위하여 상사해석 및 차원해석을 수행하였다. 실험에서는 질소와 헬륨의 혼합가스를 원형 천장에 노즐로 분출시켜 화재로 인한 연기를 구현하였으며 속도측정을 위하여 레이저와 고속카메라를 이용한 가시화 기법이 사용되었다.

• Bulletin of the Korean Chemical Society
• /
• 제34권4호
• /
• pp.1212-1220
• /
• 2013

The human coagulation factor XI (FXI) is a serine protease that plays a significant role in blocking of the blood coagulation cascade as an attractive antithrombotic target. Selective inhibition of FXIa (an activated form of factor XI) disrupts the intrinsic coagulation pathway without affecting the extrinsic pathway or other coagulation factors such as FXa, FIIa, FVIIa. Furthermore, targeting the FXIa might significantly reduce the bleeding side effects and improve the safety index. This paper reports on a docking-based three dimensional quantitative structure activity relationship (3D-QSAR) study of the potent FXIa inhibitors, the chloro-phenyl tetrazole scaffold series, using comparative molecular field analysis (CoMFA) and comparative molecular similarity analysis (CoMSIA) methods. Due to the characterization of FXIa binding site, we classified the alignment of the known FXIa inhibitors into two groups according to the docked pose: S1-S2-S4 and S1-S1'-S2'. Consequently, highly predictive 3D-QSAR models of our result will provide insight for designing new potent FXIa inhibitors.

• 정보처리학회논문지B
• /
• 제8B권5호
• /
• pp.515-522
• /
• 2001

특징정보를 기반으로 한 유사화상 검색은 화상 데이터베이스에 있어서 중요한 과제의 하나이다. 화상 데이터의 특징정보를 각 화상을 식별하는데 유용한 정보이다. 본 논문에서는 자기조직화 맵기반의 고속 k-NN 탐색 알고리즘을 제안한다. 자기조직화 맵은 학습을 통하여 고차원 특징벡터를 2차원 공간에 맵핑함으로서 위상 특징맵을 생성한다. 위상 특징맵은 입력 데이터의 특징공간의 상호간의 유사성을 가지고 있으며, 각 노드는 노드벡터와 각 노드벡터에 가장 가까운 유사화상이 분류된다. 이러한 자기조직화 맴에 의한 유사화상 분류결과에 대한 k-NN 탐색을 구현하기 위한여, (1) 위상특징 맵에 대한 접근방법, (2) 고속탐색을 위한 pruning strategy의 적용을 실현하였다. 본 연구에서는 실험을 통하여 실제화상으로부터 추출한 색상 특징을 사용하여 제안한 알고리즘의 성능을 평가함으로써 유사화상 검색에 유효한 결과를 얻을 수 있었다.

• 한국콘텐츠학회논문지
• /
• 제4권3호
• /
• pp.81-90
• /
• 2004

최근 컴퓨팅 환경의 급속한 발전으로 다양한 응용에서 다차원 데이터에 대한 활용이 증가되고 있다. 본 논문에서는 내용 기반 다차원 데이터 검색을 위한 벡터 관사 트리를 제안한다 제안하는 색인 구조는 공간 분할 방식과 벡터 근사화 기법을 이용하여 영역 정보를 표현하기 때문에 하나의 노드 안에 많은 영역 정보를 저장하여 트리의 높이를 감소시킨다 또한 다차원의 데이터 공간에 동적인 비트로 할당하여 다차원색인 구조의 문제점인 '차원의 저주 현상'을 해결한다. 또한 군집화된 데이터에 대해서 효과적인 표현 기법을 제공한다. 자식 노드의 영역 정보는 부모 노드를 기준으로 상대적으로 표현함으로서 좀더 정확한 영역을 표현할 수 있다. 제안하는 색인 구조의 우수성을 보이기 위해 실험을 통해 기존에 제안된 색인구조와의 비교 분석을 수행한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1077-1080
• /
• 1987

Images are 2-dimensional projection of 3-dimensional scenes and many problems of scene analysis arise due to inherent depth ambiguities in a monocular 2-D image. Therefore, depth recovery is a crucial problem in image understanding. This paper proposes modified algorithm which is focused on accurate correspondnce in stereo vision. The feature we use is zero-crossing points and the similarity measure with two property evaluation function is used to estimate initial probability. And we introduce relaxation technique for accurate and global correspondence.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1998년도 제27회 춘계학술대회
• /
• pp.314-320
• /
• 1998

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• Tribology and Lubricants
• /
• 제15권2호
• /
• pp.206-211
• /
• 1999

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• 한국정보처리학회논문지
• /
• 제6권3호
• /
• pp.821-831
• /
• 1999

3차운 물체 인식 중 오목과 볼록을 갖고 있는 물체의 인식은 대단히 어려운 문제이다. 본 논문에서는 물체의 인식을 위한 피처(Feature)의 추출 방법으로 오픈-볼(Open-Ball)을 제안한다. 이 새로운 방법은 물체의 크기, 이동고 회전에 불변성을 갖는 피처(Feature)를 생성하는 것뿐만이 아니라, 비교되는 물체를 인식하는 것을 상대적인 닮음 정도 측정으로 구현한다.