• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.523-525
• /
• 2001

컴퓨터의 보편화와 멀티미디어의 발전으로 많은 인공지능의 분야들이 실생활에 응용되고 있다. 이중에서 얼굴 인식은 최근에 연구가 활발한 분야 중의 하나이며 인터넷 또는 멀티미디어를 통한 보안 시스템 등에서 많은 응용이 기대되고 있다. 이러한 이유로 향후 얼굴인식이 차지하는 비중은 더욱 커질 것으로 예상된다. 본 논문에서는 조명에 대한 환경 변화에 덜 민감한 시스템을 구현하기 위하여 주성분 분석(PCA: Principal Component Analysis)과 가보 제트(Gabor jet)에 환경 파라미터를 추가하여 병렬적으로 수행하는 얼굴 인증시스템을 구형 하였다. 실험을 통하여 기존의 주성분 분석이나 가보 제트 만을 이용한 얼굴인식 알고리즘 보다 환경 변화에 덜 민감하고 오 인증률이 저하된 결과를 나타낸 것을 알 수 있다.

• Food Science and Biotechnology
• /
• v.18 no.1
• /
• pp.73-78
• /
• 2009

Processed meatball products were packaged in a passive package without oxygen scavenger as 1 control and 3 active packages of which have PP-based oxygen scavenger master batch materials (OSMB) of 40, 80, and 100%(w/w) in the middle layer and stored at 23 and $30^{\circ}C$ up to 9 months. Quality changes of packaged products were evaluated by measuring the oxygen concentration of the headspace in containers, thiobarbituric acid (TBA), color, and flavor. The oxygen concentration of the package having 100% OSMB was lower than those of 40 and 80%. The color changes and TBA values of the meat ball in the package containing 100% OSMB were the least among the treatments. Using principal component analysis (PCA), the control showed more flavor change than the packages containing oxygen scavenger. As a result, all active packages could extend the shelf life of the meatball products compared with that of the passive package.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.32-35
• /
• 2011

전기역학적 임피던스(electromechanical impedance)를 이용한 구조물 건전성 모니터링(structural health monitoring; SHM) 기술은 구조물의 주요 부재에 압전센서를 부착하여 이로부터 획득한 임피던스 신호의 변화를 관찰함으로써 구조물의 국부적 상태를 실시간으로 진단하는 것이다. 임피던스는 손상뿐만 아니라 외부 온도에도 민감하게 반응하기 때문에 구조물 진단 결과에 상당한 오차를 유발할 수 있으므로 이에 대한 보상을 수행해야 한다. 따라서 본 논문에서는 온도변화가 임피던스 기반 진단 결과에 미치는 영향을 PZT 센서를 사용하여 실험적으로 연구하였다. 리액턴스(reactance)의 주성분 분석(Principal Component Analysis; PCA)을 통해 도출된 첫번째 주성분과 저항(resistance)으로부터 계산된 손상지수 사이의 관계를 분석함으로써, 온도변화에 의해 구별되지 않았던 손상을 보다 확연하게 구별 할 수 있음을 확인하였다.

• Smart Structures and Systems
• /
• v.15 no.3
• /
• pp.751-767
• /
• 2015

A new procedure is proposed for assessing probabilistic condition of structures considering effect of measured data uncertainty. In this procedure, multiple Finite Element (FE) models are identified by using weighting vectors that represent the uncertainty conditions of measured data. The distribution of structural parameters is analysed using a Principal Component Analysis (PCA) in relation to uncertainty conditions, and the identified models are classified into groups according to their similarity by using a K-means method. The condition of a structure is then assessed probabilistically using FE models in the classified groups, each of which represents specific uncertainty condition of measured data. Yeondae bridge, a steel-box girder expressway bridge in Korea, is used as an illustrative example. Probabilistic condition of the bridge is evaluated by the distribution of load rating factors obtained using multiple FE models. The numerical example shows that the proposed method can quantify uncertainty of measured data and subsequently evaluate efficiently the probabilistic condition of bridges.

• Korean Journal of Food Science and Technology
• /
• v.37 no.5
• /
• pp.856-860
• /
• 2005

Electronic-nose system was used to discriminate commercial sesame oils (A-F) extracted from imported seeds. Response (delta $R_{gas}/R_{air}$) of sensors gained from electronic nose was analyzed by principal component analysis (PCA). Flavor pattern of sesame oil A was similar to those of sesame oils B, C, and D. Sesame oils blended with corn oil at the ratio of 95:5, 90:10 and 80:20% (sesame oil/corn oil, w/w) could be discriminated from ouch genuine sesame oil.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.8 no.3 s.22
• /
• 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.

• Annual Conference of KIPS
• /
• 2001.04a
• /
• pp.147-150
• /
• 2001

컴퓨터의 보편화와 멀티미디어의 발전으로 많은 인공지능의 분야들이 실생활에 응용되고 있다. 이 중에서 얼굴인식은 최근에 연구가 활발한 분야 중에 하나이며 다른 생체인식과는 달리 기계 장치에 신체의 일부를 접촉하지 않고 사람을 확인할 수 있다. 이러한 이유로 향후 생체인식 중 얼굴인식이 차지하는 비중은 커질 것으로 예상되고, 멀티미디어 보안 시스템 등에서 많은 응용이 기대되고 있다. 본 논문에서 정확한 사용자 인증을 위하여 기존의 주성분 분석(PCA; Principal Component Analysis)이 가지고 있는 단점인 조명에 영향을 많이 받는 것을 보완하기 위해, 다양한 조명에 안정적인 가보 함수를 같이 사용하였다. 주성분 분석만을 이용하는 것보다 사용자 인증의 성공률을 향상시킬 수 있음을 알 수 있었다.

• International Journal of Oral Biology
• /
• v.43 no.2
• /
• pp.101-111
• /
• 2018

Understanding the classification of malocclusion is a crucial issue in Orthodontics. It can also help us to diagnose, treat, and understand malocclusion to establish a standard for definite class of patients. Principal component analysis (PCA) and k-means algorithms have been emerging as data analytic methods for cephalometric measurements, due to their intuitive concepts and application potentials. This study analyzed the macro- and meso-scale classification structure and feature basis vectors of 1020 (415 male, 605 female; mean age, 25 years) orthodontic patients using statistical preprocessing, PCA, random matrix theory (RMT) and k-means algorithms. RMT results show that 7 principal components (PCs) are significant standard in the extraction of features. Using k-means algorithms, 3 and 6 clusters were identified and the axes of PC1~3 were determined to be significant for patient classification. Macro-scale classification denotes skeletal Class I, II, III and PC1 means anteroposterior discrepancy of the maxilla and mandible and mandibular position. PC2 and PC3 means vertical pattern and maxillary position respectively; they played significant roles in the meso-scale classification. In conclusion, the typical patient profile (TPP) of each class showed that the data-based classification corresponds with the clinical classification of orthodontic patients. This data-based study can provide insight into the development of new diagnostic classifications.

• Journal of KIISE
• /
• v.44 no.4
• /
• pp.392-398
• /
• 2017

The point-cloud representation of an object is performed by scanning a space through a laser scanner that is extracting a set of points, and the points are then integrated into the same coordinate system through a registration. The set of the completed registration-integrated point clouds is classified into meaningful regions, shapes, and noises through a mathematical analysis. In this paper, the aim is the matching of a curved area like a cylinder shape in 3D point-cloud data. The matching procedure is the attainment of the center and radius data through the extraction of the cylinder-shape candidates from the sphere that is fitted through the RANdom Sample Consensus (RANSAC) in the point cloud, and completion requires the matching of the curved region with the Catmull-Rom spline from the extracted center-point data using the Principal Component Analysis (PCA). Not only is the proposed method expected to derive a fast estimation result via linear and curved cylinder estimations after a center-axis estimation without constraint and segmentation, but it should also increase the work efficiency of reverse engineering.

• Horticultural Science & Technology
• /
• v.29 no.3
• /
• pp.201-210
• /
• 2011

This experiment was conducted to investigate physical and chemical characteristics by volume fractions of root media using peatmoss, perlite, and vermiculite, along with effects on the growth of pot chrysanthemums (Dendranthema ${\times}$ grandiflorum 'Vemini') in a C-channel mat irrigation system. To evaluate the physico-chemical properties of 20 root media, the bulk density, particle density, total pore space, pore space, ash content, organic matter, pH, and electrical conductivity were measured and data were analyzed using principal component analysis (PCA). PCA scores revealed that physico-chemical properties changed by the blending of peatmoss, perlite, and vermiculite. The 20 root media were divided into three main groups by hierarchical cluster analysis. At the end of the experiment, the pH and EC of the root media were measured from media divided into four layers. The pH of root media without plants showed a strong linear relationship and the pH of root media with plants increased exponentially. The change of EC in the root medium was indicated as a hyperbolic curve. Plant growth characteristics according to growth in the 20 root media were analyzed by PCA. It was found that the mixing ratios of the root media affected plant growth characteristics. Therefore, mixing ratio is an important factor for pot-plant production in a subirrigation system.