• Industrial Engineering and Management Systems
• /
• 제15권1호
• /
• pp.110-121
• /
• 2016

With the growing interest in skincare and maintenance, there are increasing numbers of studies on the classification of skin type and the factors influencing each type. This study presents a novel methodology by using data mining, for the determination of the relationships between skin type, lifestyle, and patterns of cosmetic utilization. Eight skin-specific factors, which are moisture, sebum in U-zone (both cheeks), sebum in T-zone (forehead, nose, and chin), pore, melanin, wrinkle, acne, hemoglobin, were measured in 1,246 subjects living in South Korea, in conjunction with a questionnaire survey analyzing their lifestyles and pattern of cosmetic utilization. Using various multivariate statistical methods and data mining techniques, we classified the skin types based on the skin-specific values, determined the relationship between skin type and lifestyle, and accordingly sorted the subjects into clusters. Logistic regression analysis revealed gender-related differences in the skin; therefore, separate analyses were performed for males and females. Using the Gaussian Mixture Modeling (GMM) technique, we classified the subjects based on skin type (two male and four female). Using the ANOVA and decision tree techniques, we attempted to characterize the relationship between each skin type and the lifestyles of the subjects. Menstruation, eating habits, stress, and smoking were identified as the major factors affecting the skin.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.365-371
• /
• 2011

최근에 발행되는 대부분의 지폐는 UV(ultra violet)조명에 반응하는 UV패턴을 포함한다. 본 논문은 지폐검사를 위하여 지폐 내부에 존재하는 UV패턴을 자동으로 추출하는 방법을 제안한다. UV조명을 이용하여 촬영한 영상을 전 처리 과정을 통하여 입력데이터로 변환시킨 후, 가우시안 혼합 모형과 split-and merge EM(SMEM)알고리즘을 적용하여 영상을 몇 개의 영역으로 분리시킨다. 영역 분리된 영상 중 원하는 패턴을 추출하기 위하여, 공분산 벡터의 넓이와 가중치를 이용하는 방법을 새로이 제안한다. 다양한 지폐에 대한 실험을 통하여 제안방법의 유용성을 보인다.

• 전자공학회논문지
• /
• 제50권2호
• /
• pp.185-192
• /
• 2013

본 논문에서는 MFCC를 이용한 GMM 기반의 음성과 혼합 신호 분류 알고리즘을 MPEG의 표준 코덱인 USAC에 적용하였다. 효과적인 패턴 인식을 위해 GMM을 이용하였고, EM알고리즘을 사용하여 최적의 GMM 파라미터를 추출하였다. 제안하는 분류 알고리즘은 두 가지 중요한 부분으로 나뉜다. 첫째는 GMM을 통해 최적의 파라미터를 추출하는 것 이고, 두 번째는 MFCC 값을 이용한 패턴인식을 통해 음성/혼합 신호를 분류하였다. 제안된 알고리즘의 성능을 평가한 결과 MFCC를 이용한 GMM 기반의 제안된 방법이 기존 USAC의 방법보다 우수한 음성/혼합 신호 분류 성능을 보였다.

• 한국게임학회 논문지
• /
• 제6권1호
• /
• pp.3-10
• /
• 2006

게임에서 레벨 디자인 (Level Design)과 캐릭터간의 밸런스는 게임의 흥미를 결정하는 매우 중요한 요소이며, 레벨 디자이너에 의해 결정 된다. 기존의 게임에서는 플레이어가 가장 큰 재미를 느낄 수 있는 캐릭터의 공격 패턴과 속성은 정적으로 정해졌으며 스크립트 형식으로 표현됐다. 이와 같이 정적으로 정해진 레벨에 따라 진행되면 플레이어가 쉽게 적응하게 되고, 플레이어의 학습능력에 따라 레벨 디자이너가 의도했던 밸런스가 깨질 수 있었다. 이런 문제점을 해결하기 위해 본 논문에서는 게임 도중에 플레이어의 대응 패턴을 GMM(Gaussian Mixture Model)으로 모델링하고 분석하여 레벨 디자이너가 의도했던 레벨과 재미를 느낄 수 있는 환경을 제공하는 방법을 제안한다. 제안한 방법을 실제 2D슈팅게임에 적용하여 플레이어의 패턴을 분석한 결과와 동적 레벨 디자인의 결과를 보인다.

• The Journal of the Acoustical Society of Korea
• /
• 제26권3E호
• /
• pp.80-86
• /
• 2007

In this paper, we utilize generalized warped filterbanks to improve the performance of speaker recognition systems. At first, the performance of speaker identification systems is analyzed by varying the type of warped filterbanks. Based on the results that the error pattern of recognition system is different depending on the type of filterbank used, we combine the likelihood values of the statistical models that consist of the features extracting from multiple warped filterbanks. Simulation results with TIMIT and NTIMIT database verify that the proposed system shows relative improvement of identification rate by 31.47% and 15.14% comparing it to the conventional system.

• 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.

• 소성∙가공
• /
• 제14권6호
• /
• pp.570-576
• /
• 2005

Powder Injection Molding(PIM) has recently been recognized as an advanced manufacturing technology for low-cost mass production of metal or ceramic parts of complicated geometry With this regards, design technology of dental scaler tip PIM mold, which has complex shape and small core pin (diameter=0.6mm), with the help of computer-aided analysis of powder injection molding process was developed. Computer-aided analysis for dental scaler tip mold was implemented by finite element method with non-Newtonian fluid, modified Cross model viscosity, PvT data of powder/binder mixture. Compter-aided analysis results, such as filling pattern, weldline formation, air vent position prediction were compared with experimental result, and eventually have been shown good agreement. The core pin (diameter=0.6mm) deflection analysis of dental scaler tip PIM mold during PIM filling process was also investigated before mold fabrication.

• 한국환경보건학회지
• /
• 제23권2호
• /
• pp.35-43
• /
• 1997

A study on the effect of the biodegradability of the composting bulking agent in the swine manurecomposting was carried out in a batch system. The purpose of this study is to prove the effect of the biodegradability of the composting-bulking agent on the efficiency of the composting. In this study, it is the lignins: Klason-Lignin in the volatile solid that the index of the biodegradability of the composting-material mixes which are pig manure-rice straw pig manure-sawdusts pig manuremixture of rice and ricestraw (2:1) pig manure-mixture of rice and sawdust (1:1). It was carried out in the same condition (moisture contents, air supply rate, C/N ratio, initial input weight, porosity-structure) except the biodegradability of the raw material mixes. One of the results from this study is that the biodegradability of the bulking agent in the sense of the VS lignin content is not an insignificant factor in composting reaction. The less contents of the lignin in VS, the more efficiencies of the cornposting reaction in use of these parameters for the degree of the reaction: temperature, the trends of the ash contents, the change pattern of the C/N ratio. Under some assumptions, it is able to induce rough model on the relation of the VS lignin contents with the efficiency of the degradability. In this model, the biodegradability of the bulking agent is not an insignificant factor however, it is flexible within some degrees of range.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.981-984
• /
• 2010

우리는 본 연구에서 학습방법으로서 연속음성을 초성, 중성, 종성의 음소단위로 분할하기 위하여 인공 신경회로망의 하나인 SVMs을 사용하였으며 분할한 음소단위의 음성으로 연속음성인식에 적용하여 그 성능을 살펴보았다. 음소경계는 단 구간에서의 최대 주파수를 가진 알고리듬에 의하여 결정되며 또한 음성인식처리는 CHMM에 의하여 이루어지며 목측에 의한 분할결과와도 비교하여 살펴보았다. 시뮬레이션 결과로부터 초성의 분할성능에서 제안한 SVMs를 적용한 결과가 GMMs보다 효율적인을 알 수 있었다.

• Geomechanics and Engineering
• /
• 제24권3호
• /
• pp.267-280
• /
• 2021

The research presented in this paper deals with dynamic stability analysis of the graphene nanoplatelets (GPLs) reinforced composite spinning disk. The presented small-scaled structure is simulated as a disk covered by viscoelastic substrate which is two-parametric. The centrifugal and Coriolis impacts due to the spinning are taken into account. The stresses and strains would be obtained using the first-order-shear-deformable-theory (FSDT). For Poisson ratio, as well as various amounts of mass densities, the mixture rule is employed, while a modified Halpin-Tsai model is inserted for achieving the elasticity module. The structure's boundary conditions (BCs) are obtained employing GPLs reinforced composite (GPLRC) spinning disk's governing equations applying principle of Hamilton which is based on minimum energy and ultimately have been solved employing numerical approach called generalized-differential quadrature-method (GDQM). Spinning disk's dynamic properties with different boundary conditions (BCs) are explained due to the curves drawn by Matlab software. Also, the simply-supported boundary conditions is applied to edges 𝜃=𝜋/2, and 𝜃=3𝜋/2, while, cantilever, respectively, is analyzed in R=R_i, and R₀. The final results reveal that the GPLs' weight fraction, viscoelastic substrate, various GPLs' pattern, and rotational velocity have a dramatic influence on the amplitude, and vibration behavior of a GPLRC rotating cantilevered disk. As an applicable result in related industries, the spinning velocity impact on the frequency is more effective in the higher radius ratio's amounts.