• 한국수산과학회지
• /
• 제50권2호
• /
• pp.195-206
• /
• 2017

Joint time-frequency images of the broadband echo signals of six fish species were obtained using the smoothed pseudo-Wigner-Ville distribution in controlled environments. Affine transformation and principal component analysis were used to obtain eigenimages that provided species-specific acoustic features for each of the six fish species. The echo images of an unknown fish species, acquired in real time and in a fully automated fashion, were identified by finding the smallest Euclidean or Mahalanobis distance between each combination of weight matrices of the test image of the fish species to be identified and of the eigenimage classes of each of six fish species in the training set. The experimental results showed that the Mahalanobis classifier performed better than the Euclidean classifier in identifying both single- and mixed-species groups of all species assessed.

• 한국군사과학기술학회지
• /
• 제8권3호
• /
• pp.83-91
• /
• 2005

Pyrolysis-mass spectrometry has been used to characterize the 17 biological materials including bacteria and proteins. In this study, an in situ thermal-hydrolysis methylation(THM) procedure using tetramethylammonium hydroxide(TMAH) was employed. The biological materials are ionized using chemical ionization(CI) method with ethanol by ion trap mass spectrometer(ITMS), which attached with our own made pyrolyzer module, and then their pyrolysis mass spectra were obtained. The major distinct characteristic peaks were selected from all the range of mass spectra, and analyzed using principal component analysis(PCA) method to assess the classification/identification possibility of biological materials.

• Smart Structures and Systems
• /
• 제31권2호
• /
• pp.171-181
• /
• 2023

Using the most up-to-date system identification methods in both time and frequency domains, the dynamic monitoring data from the reinforced concrete Egebaekvej Bridge near Holte, Denmark, is examined in this investigation. The bridge was erected in the 1960s and was still standing during test campaign before demolishing. The ARTeMIS Modal was adopted to derive the modal parameters from ambient vibration data. Several Operational Modal Analysis (OMA) approaches were applied, including Enhanced Frequency Domain Decomposition (EFDD), Curve-fit Frequency Domain Decomposition (CFDD), and Frequency Domain Decomposition (FDD). Afterward, Principal Component (SSI-PC), Unweighted Principal Component (SSI-UPC) Stochastic Subspace Identification methods were utilized. Danish engineering consulting company, COWI with the allowance of the bridge contractor BARSLUND, allow the researcher for this experimental test to demonstrate the impact of OMA applications.

• 인지과학
• /
• 제18권4호
• /
• pp.445-455
• /
• 2007

본 논문은 주성분분석기법을 이용한 치아의 다면특징을 기반으로 한 새로운 생체 식별시스템을 제안한다. 치아의 다면 특징들은 정면치아와 좌측, 우측 치아들로 이루어진다. 우리는 실생활 환경에서 보안 접속을 위하여 치아를 이용한 생체식별을 목표로 한다. 다면 치아 영상들은 특별히 고안된 실험환경에서 획득되었으며, 개인 식별을 위한 특징으로 42개의 주성분이 개발되었다. 개인 식별은 학습된 다면치아와 회전된 다면치아 사이의 최소근접기법에 의해 계산되었다. 2도 회전 후의 다면치아 인식성능은 평균값으로 좌측면 치아 95.2%, 우측면 치아 91.3%을 보였다.

• 한국자기공명학회논문지
• /
• 제16권2호
• /
• pp.133-146
• /
• 2012

Three different derivatives were obtained in the synthesis of cobalt-binding BLM-A2 and characterized by NMR and Mass spectrometry. It was found that Component 1 is Co(II)($2H_2O$)(BLM-A2), component 2 is Co(III)($OOH^-$)(BLM-A2) and component 3 is Co(III)($H_2O$)($OH^-$)(BLM-A2), respectively. Component 2 and 3 were interestingly dominated when CoBLM-A2 complex was synthesized under basic condition. In this experiment, it was revealed newly that the brown form (component 1) was 6-coordinated structure composed with not 5 ligands but 4 ligands from BLM-A2 and with $2H_2O$ as the axial ligands. The component 3 exhibiting a novel ligand configuration is found, and the structure of component 3 was observed to be very similar to that of component 1 in the kind of their ligands but one of the axial ligand is $OH^-$ instead of $H_2O$. These ligand configurations are different from the green form (component 2) exhibiting 6-coordinate structure composed of 5 ligands from BLM-A2 and one ligand of $OOH^-$, being consistent with former studies.

• 한국음향학회지
• /
• 제22권7호
• /
• pp.519-527
• /
• 2003

음성신호는 주변 잡음과 화자의 발성 패턴 변화, 음성 검출 오류에서 생기는 이상치(outlier)에 많은 영향을 받고 있다. 이러한 음성 신호를 이용하여 화자인식에 이용할 경우 인식률이 저하된다. 본 논문에서는 화자식별 (speaker identification)에서 학습 특징 벡터의 이상치와 고차원 문제를 해결하기 위하여 M-추정을 이용한 강인한 주성분 분석 가우시안 혼합모델 (Robust Principal Component Analysis-Gaussian Mixture Model)방법을 제안하였다. 제안된 방법은 먼저, 특징 벡터에 이상치가 존재할 경우 M-추정에 의하여 강인한 공분산 행렬을 재추정하여 얻어진 고유벡터로부터 변환 행렬을 구하여 감소된 차원을 갖는 새로운 특징벡터를 구한다. 여기에서 얻은 선형변환된 특징벡터로부터 화자의 가우시안 혼합 모델을 구한다. 제안된 방법의 성능을 검증하기 위하여 화자식별 실험을 하였다. 실험은 전형적인 가우시안 혼합 모델 방법과 주성분 분석법, 제안된 방법을 비교 분석하였다. 이상치가 2%씩 증가할 때마다 가우시안 혼합모델 방법과 주성분 분석법은 각각 0.65%, 0.55%씩 화자식별 성능이 저하되었지만, 제안된 방법은 0.03%정도 감소하였으므로 이상치에 더욱 강인함을 알 수 있다.

• Structural Engineering and Mechanics
• /
• 제25권5호
• /
• pp.631-636
• /
• 2007

• 한국콘텐츠학회논문지
• /
• 제13권11호
• /
• pp.28-36
• /
• 2013

본 논문은 손 형상 인식을 위한 보다 안정적이며 조명 변화와 회전에 강인하게 손 영역을 검출하며, 계산의 효율성과 검출 성능을 동시에 만족시키는 강인한 검출 알고리즘에 대해 제안한다. 제안한 알고리즘은 단일 카메라 환경에서 손 형상을 입력정보로 사용하여 전처리 과정을 거쳐 손 영역만을 분할한 후 자기조직화 특징 지도(SOFM: Self Organized Feature Map) 알고리즘을 이용하여 손 형상을 인식하게 된다. 그러나 조명 변화에 민감하고 자유도가 큰 손 영역을 정확히 인식하기란 쉽지 않으며 오차 범위도 크기 때문에 본 논문에서는 인식률을 높이기 위해 각각의 손 형상에 대한 회전 정보를 데이터베이스화 한 후 주성분 분석을 적용하여 군집화 함으로서 인식오차를 줄였다. 또한 차원 축소로 인해 많은 계산 량이 요구되지 않기 때문에 실시간 인식 시간도 줄일 수 있었다.

• 대한음성학회지:말소리
• /
• 제66호
• /
• pp.105-116
• /
• 2008

In this research, we propose a speaker identification system using a kernel method which is expected to model the non-linearity of speech features well. We have been using principal component analysis (PCA) successfully, and extended to kernel PCA, which is used for many pattern recognition tasks such as face recognition. However, we cannot use kernel PCA for speaker identification directly because the storage required for the kernel matrix grows quadratically, and the computational cost grows linearly (computing eigenvector of $l{\times}l$ matrix) with the number of training vectors I. Therefore, we use greedy kernel PCA which can approximate kernel PCA with small representation error. In the experiments, we compare the accuracy of the greedy kernel PCA with the baseline Gaussian mixture models using MFCCs and PCA. As the results with limited enrollment data show, the greedy kernel PCA outperforms conventional methods.

• International Journal of Ocean Engineering and Technology Speciallssue:Selected Papers
• /
• 제4권1호
• /
• pp.31-37
• /
• 2001

In this paper, an integrated damage identification system (IDIS) is proposed to locate and size damage in real structures. The application of the IDIS to real structures includes the measurement of modal responses, the construction of damage-detection models, and the implementation of measurements and models into the damage-detection process. Firstly, the theory of the damage identification method is outlined. Secondly, the schematic and each component of the IDIS are described. Finally, the practicality of the IDIS is verified from experiments on two different bridge-models, a model plate-grider and a model truss.