• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권5호
• /
• pp.583-592
• /
• 2000

본 논문에서는 독립성분분석을 이용한 음성의 특징 벡터 변환방법을 제안한다. 제안한 방법은 여러 환경에서 수집된 음성신호의 켑스트럼 벡터를 다수의 특징 함수들의 선형결합으로 가정하고, 독립성분분석을 이용하여 분리된 켑스트럼 벡터를 학습과 인식에 사용한다. 변환된 벡터 영역에서는 반복적으로 나타나는 화자의 특징 정보는 강조되고 임의로 나타나는 채널 왜곡은 억제되는 효과를 볼 수 있다. 제안된 방법의 유효성을 검증하기 위해 실제 전화음성으로 문장독립형 화자식별 실험을 수행하였으며, 결과를 통해 독립성분분석을 이용한 특징벡터의 변환이 채널 환경 변화에 대해 보다 강인함을 보였다.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.17-25
• /
• 2015

For blind source separation of convolutive mixtures, FDICA(Frequency Domain Independent Component Analysis) algorithms are generally used. Since FDICA algorithm such as Sawada FDICA, IVA(Independent Vector Analysis) works on the frequency bin basis with a natural gradient descent method, it takes much time to converge. In this paper, we propose a new method to improve convergence speed in FDICA algorithm. The proposed method reduces the number of iteration drastically in the process of natural gradient descent method by applying a weighted inner product constraint of unmixing matrix. Experimental results have shown that the proposed method achieved large improvement of convergence speed without degrading the separation performance of the baseline algorithms.

• 농촌계획
• /
• 제28권1호
• /
• pp.57-69
• /
• 2022

Crop classification is very important for estimating crop yield and figuring out accurate cultivation area. The purpose of this study is to classify crops harvested in fall in Idam-ri, Goesan-gun, Chungcheongbuk-do by using unmanned aerial vehicle (UAV) images and support vector machine (SVM) model. The study proceeded in the order of image acquisition, variable extraction, model building, and evaluation. First, RGB and multispectral image were acquired on September 13, 2021. Independent variables which were applied to Farm-Map, consisted gray level co-occurrence matrix (GLCM)-based texture characteristics by using RGB images, and multispectral reflectance data. The crop classification model was built using texture characteristics and reflectance data, and finally, accuracy evaluation was performed using the error matrix. As a result of the study, the classification model consisted of four types to compare the classification accuracy according to the combination of independent variables. The result of four types of model analysis, recursive feature elimination (RFE) model showed the highest accuracy with an overall accuracy (OA) of 88.64%, Kappa coefficient of 0.84. UAV-based RGB and multispectral images effectively classified cabbage, rice and soybean when the SVM model was applied. The results of this study provided capacity usefully in classifying crops using single-period images. These technologies are expected to improve the accuracy and efficiency of crop cultivation area surveys by supplementing additional data learning, and to provide basic data for estimating crop yields.

• 대한전자공학회논문지SP
• /
• 제44권6호
• /
• pp.16-23
• /
• 2007

개인 인증 방법 중 하나인 생체인식(Biometrics)은 개인 생체정보의 수가 한정되어 있기 때문에 생체정보의 도난 시 프라이버시 침해라는 문제를 가진다. 이 문제를 해결하기 위해 등장한 개념이 가변 생체인식(Changeable biometrics)이다. 가변 생체 인식은 생체정보가 훼손당했을 경우 새로운 생체정보로 대체하기 어렵다는 생체인식의 가장 큰 단점을 보완하기 위한 방법으로 원 생체정보가 아닌 변환된 생체정보로 개인을 인증한다. 이 논문에서는 가변 생체인식 가운데 얼굴인식을 위한 가변 생체인식에 대해 제안한다. 기존에 알려진 얼굴인식의 방법 가운데 하나인 외형 기반 기법(Appearance-based method) 중 독립성분 분석(Independent Component Analysis)의 계수(coefficient)를 변형하는 방법을 제안한다. 제안된 얼굴 생체정보 생성 방법은 계수의 일부분을 가우시안 분포(Gaussian distribution)에 따른 임의의 값으로 치환한 후 계수의 순서를 임의로 변경하여 무수히 많은 가변 얼굴 정보를 생성할 수 있도록 하였고 서로 다르게 변경된 계수들을 서로 합성함으로써 비가역성(Non-invertibility)을 만족시키려고 시도했다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2000년도 봄 학술발표회논문집
• /
• pp.85-91
• /
• 2000

The smallest value of the load when the equilibrium condition becomes to be unstable is defined as the buckling load. The primary objective of this paper is to analyse stability boundaries for star dome under combined loads and is to investigate the iteration diagram under the independent loading parameter In numerical procedure of the geometrically nonlinear problems, Arc Length Method and Newton-Raphson iteration method is used to find accurate critical point(bifurcation point and limit point). In this paper independent loading vector is combined as proportional value and star dome was used as numerical analysis model to find stability boundary among load parameters and many other models as multi-star dome and arches were studied. Through this study we can find the type of buckling mode and the value of buckling load.

• Reproductive and Developmental Biology
• /
• 제30권4호
• /
• pp.229-234
• /
• 2006

We have generated transgenic mice that expressed mouse extracellular superoxide dismutase (EC-SOD) in their skin. In particular, the expression plasmid DNA containing human keratin K14 promoter was used to direct the keratinocyte-specific transcription of the transgene. To compare intron-dependent and intron-independent gene expression, we constructed two vectors. The vector B, which contains the rabbit -globin intron 2, was not effective for mouse EC-SOD overexpression. The EC-SOD transcript was detected in the skin, as determined by Northern blot analysis. Furthermore, EC-SOD protein was detected in the skin tissue, as demonstrated by Western blot analysis. To evaluate the expression levels of EC-SOD in various tissues, we purified EC-SOD from the skin, lungs, brain, kidneys, livers, and spleen of transgenic mice and measured its activities. EC-SOD activities in the transgenic mice skin were approximately 7 fold higher than in wild-type mice. These results suggest that the mouse overexpressing vector not only induces keratinocyte-specific expression of EC-SOD, but also expresses successfully functional EC-SOD. Thus, these transgenic mice appeared to be useful for the expression of the EC-SOD gene and subsequent analysis of various skin changes, such as erythema, inflamation, photoaging, and skin tumors.

• The Journal of Asian Finance, Economics and Business
• /
• 제5권4호
• /
• pp.85-94
• /
• 2018

The cultural industry is treated as the sunrise industry in modern society. It has taken an increasing role in promoting the economic growth. Due to this, this paper attempts to explore the dynamic relationship between cultural industry and the economic growth. On the grounds of Cobb-Douglas production function, the cultural industry is regarded as a determinant such as the labor input and the capital input to impact the economic growth. Meanwhile, the quarterly datum form 2000-Q1 to 2017-Q4 are employed to perform an empirical analysis via the vector error correction model. The GDP is treated as an independent variable. The input of capital, the input of labor and the total input of cultural industry are treated as dependent variables. Furthermore, a menu of statistical approaches such as the co-integration test and the impulse response function will be used to testify the dynamic relationship between cultural industry and economic growth. Via the Johansen co-integration test, the results report that the cultural industry has a obviously positive effect on economic growth. Through the vector error correction estimation, the results also report that the cultural industry also has a significantly positive effect on economic growth, but less than that of the Johansen co-integration test. This paper provides a view that the cultural industry is a kind of a determinant to promote the economic growth. Therefore, the China's government should pay much attention to the cultural industry construction.

• 한국측량학회지
• /
• 제9권1호
• /
• pp.97-107
• /
• 1991

본 연구에서는 리모트센싱과 GIS의 장점을 살려 하나의 시스템에서 여러 기능을 복합적으로 이용하기 위한 리모트센싱과 GIS의 통합을 시도한 것이다. 래스터와 벡터 데이타의 동시 통합 출력을 위한 중복 알고리즘을 개발하였으며, 리모트센싱과 GIS의 통합결과를 시험적용하기 위하여 인공위성 화상 데이타와 지형도 벡터 그래픽 데이타를 정확하게 통합시켰다. 실제 적용에서는 리모트센싱과 GIS의 주요 적용분야의 주제별 적용에 대한 데이타 모집과 중복 그리고 좌표계 변환을 통하여 대상지역에 다각적으로 적용할 수 있는 기법을 시도함으로써 벡터와 래스터의 중복의 효용성을 입증하고 복합적인 현안분석을 통해서 리모트센싱과 GIS의 복합적용을 위한 새로운 적용 기법을 제시하였다.

• Nuclear Engineering and Technology
• /
• 제41권9호
• /
• pp.1181-1190
• /
• 2009

Knowing more about the Local Power Density (LPD) at the hottest part of a nuclear reactor core can provide more important information than knowledge of the LPD at any other position. The LPD at the hottest part needs to be estimated accurately in order to prevent the fuel rod from melting in a nuclear reactor. Support Vector Machines (SVMs) have successfully been applied in classification and regression problems. Therefore, in this paper, the power peaking factor, which is defined as the highest LPD to the average power density in a reactor core, was estimated by SVMs which use numerous measured signals of the reactor coolant system. The SVM models were developed by using a training data set and validated by an independent test data set. The SVM models' uncertainty was analyzed by using 100 sampled training data sets and verification data sets. The prediction intervals were very small, which means that the predicted values were very accurate. The predicted values were then applied to the first fuel cycle of the Yonggwang Nuclear Power Plant Unit 3. The root mean squared error was approximately 0.15%, which is accurate enough for use in LPD monitoring and for core protection that uses LPD estimation.

• 재활복지공학회논문지
• /
• 제10권3호
• /
• pp.221-228
• /
• 2016

본 논문에서는 EEG 신호 기반 기기 또는 소프트웨어를 사용하기 위해 사용자가 본인의 EEG 신호 정확도를 확인하고, 훈련을 통하여 자신의 EEG 신호 정확도를 향상시킬 수 있는 시뮬레이션 소프트웨어를 제안한다. 실험 데이터로는 풍경사진을 보며 편안한 상태에서 발생되는 신호와 수학문제를 풀며 집중 시에 발생되는 신호를 사용한다. 입력되는 EEG 신호는 독립 성분 분석(Independent Component Analysis, ICA)을 적용하여 잡음을 최소화하고 대역 통과 필터(Band Pass Filter)를 통하여 베타파(${\beta}$, 14-30Hz)만을 취득한다. 취득한 베타파 대역 데이터에서 제곱평균제곱근(Root Mean Square, RMS) 알고리즘을 통하여 특징 정보를 추출하고 지지 벡터 머신(Support Vector Machine, SVM)에 적용하여 분류한다. 분류된 결과는 사용자가 바로 확인할 수 있으며 훈련 전 피험자의 평균 정확도는 79.21%이었던 반면, 연속적인 훈련으로 최고 91.67%의 정확도를 보였다. 이처럼 본 논문에서 개발한 시뮬레이션 소프트웨어는 사용자가 직접 자신의 EEG 신호 정확도를 향상키기는 훈련을 통하여 정확도 향상이 가능하고, EEG 신호 기반으로 이루어진 BCI 시스템의 효율적인 사용을 기대할 수 있다.