• Communications for Statistical Applications and Methods
• /
• 제28권2호
• /
• pp.189-204
• /
• 2021

In a regression analysis, a single best model is usually selected among several candidate models. However, it is often useful to combine several candidate models to achieve better performance, especially, in the prediction viewpoint. Model combining methods such as stacking and Bayesian model averaging (BMA) have been suggested from the perspective of averaging candidate models. When the candidate models include a true model, it is expected that BMA generally gives better performance than stacking. On the other hand, when candidate models do not include the true model, it is known that stacking outperforms BMA. Since stacking and BMA approaches have different properties, it is difficult to determine which method is more appropriate under other situations. In particular, it is not easy to find research papers that compare stacking and BMA when regression model assumptions are violated. Therefore, in the paper, we compare the performance among model averaging methods as well as a single best model in the linear regression analysis when standard linear regression assumptions are violated. Simulations were conducted to compare model averaging methods with the linear regression when data include outliers and data do not include them. We also compared them when data include errors from a non-normal distribution. The model averaging methods were applied to the water pollution data, which have a strong multicollinearity among variables. Simulation studies showed that the stacking method tends to give better performance than BMA or standard linear regression analysis (including the stepwise selection method) in the sense of risks (see (3.1)) or prediction error (see (3.2)) when typical linear regression assumptions are violated.

• 전기학회논문지
• /
• 제57권4호
• /
• pp.729-734
• /
• 2008

Vibroarthrographic(VAG) signals, emitted by human knee joints, are non-stationary and multi-component in nature and time-frequency distributions(TFD) provide powerful means to analyze such signals. The objective of this paper is to classify VAG signals, generated during joint movement, into two groups(normal and patient group) using the characteristic parameters extracted by time-frequency transform, and to evaluate the classification accuracy. Noise within TFD was reduced by singular value decomposition and back-propagation neural network(BPNN) was used for classifying VAG signals. The characteristic parameters consist of the energy parameter, energy spread parameter, frequency parameter, frequency spread parameter by Wigner-Ville distribution and the amplitude of frequency distribution, the mean and the median frequency by fast Fourier transform. Totally 1408 segments(normal 1031, patient 377) were used for training and evaluating BPNN. As a result, the average value of the classification accuracy was 92.3(standard deviation ${\pm}0.9$)%. The proposed method was independent of clinical information, and showed good potential for non-invasive diagnosis and monitoring of joint disorders such as osteoarthritis and chondromalacia patella.

• 한국통신학회논문지
• /
• 제25권3A호
• /
• pp.334-341
• /
• 2000

This paper presents an analysis of the capacity, the interference of adjacent cells of a CDMA cellular system, depending on the soft handoff region and log-normal shadowing. The optimum soft handoff region is chosen by using Erlang capacity. It is shown that when the soft handoff region increases, the Erlang capacity increase due to a reduction of the interference power of adjacent cells. But if the region is increased above a certain value, there is no improvement in the system’s capacity. Furthermore as the standard deviation of the log-normal shadowing's normal distribution factor increases, the soft handoff region has to be increased linearly to achieve the same Erlang capacity.

• Journal of the Korean Data and Information Science Society
• /
• 제27권4호
• /
• pp.959-967
• /
• 2016

자산의 수익에 대한 분포 가정은 파생 상품의 가치 평가에 매우 중요한 역할을 한다. Elberlein과 Keller (1995)는 오랜 기간에 걸친 주식 자료를 바탕으로 혼합 자산의 분포에 대한 다양한 검정을 수행한 결과, 정규성 가정이 만족되지 않음을 확인한 바 있으며, 일반화 쌍곡분포가 보다 현실을 잘 반영하는 모형임을 확인하였다. 또한, Hu와 Kercheval (2007)은 6년간의 S&P500 지수의 분석에서 정규분포는 VaR (value at risk)을 과소 추정하는 반면, 일반화 쌍곡분포는 잘 적합함을 확인하였다. 일반화 쌍곡분포는, Barndorff-Nielsen (1977)이 처음 소개한 분포로, 첨도가 큰 특징을 가지는 금융 자료의 적합에 유용한 분포이다. 본 연구에서는 일반화 쌍곡분포를 모분포로 하는 선형 포트폴리오의 위험측도를 추정한다. 위험측도로는 VaR과 ES (expected shortfall)를 고려하였으며, 추정 방법으로는 안장점근사를 사용하였다. 안장점근사는 소표본에서도 정확한 근사를 제공하는 근사법으로 알려져 있다. 모의실험을 통해 위험측도에 대한 안장점근사의 정도가 매우 우수함을 확인하였다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2012년도 추계 학술논문 발표대회
• /
• pp.23-25
• /
• 2012

Because Self-Adhesive Waterproofing sheet has good constructability, it has been widely used. Also Self-Adhesive Waterproofing sheet is researched based on variety of materials and various of forms. However, producers have recognized about only pass KS quality standard. So, Self-Adhesive waterproofing sheet has been limited about improvement of performance. Therefore, in this research, proposed guideline of Self-Adhesive Waterproofing sheet for disinterested performance grade using probability theory and quality management theory.

• 한국지리정보학회지
• /
• 제19권1호
• /
• pp.12-29
• /
• 2016

본 연구에서는 합리적인 개발과 생태계의 보전을 위한 산지구분 조정을 위해 운영되고 있는 산지특성평가제도를 위한 평가 지표의 개선방안을 제시하였다. 현행 산지특성평가에서는 지표간의 중복성이 검토되지 않아 자료수집에 대한 효율성이 떨어지고, 지자체의 산림유형 및 개발여건을 고려하지 않고 산지의 등급을 산정하기 위한 각 지표의 중요도를 동등하게 적용함으로써 보전산지의 지정 해제에 대한 지역간의 편차를 유발하고 있다. 따라서 본 연구에서는 39개 시군을 대상으로 지표간 상관분석을 통해 영급과 상관성이 높은 경급을 제거하여 지표의 통계적 중복성을 제거하였고, 지역별 산림환경특성을 반영할 수 있도록 산지의 등급은 표준정규분포를 이용하여 산지유역유형별 특성에 따라 보전성향 및 해제성향의 비율이 할당될 수 있도록 하였다. 경급을 제외하고 9개의 지표를 이용하여 산지특성평가를 실시한 결과를 경급을 포함한 10개의 지표를 이용하여 산지특성평가를 실시한 결과와 비교했을 때, 전체적으로 등급별 필지수의 변화는 A등급을 제외하고 다른 등급에서 발생하였으나 변화 필지수 및 면적은 크지 않은 것으로 분석되었다. 또한 산지유역 유형별 산지특성평가 점수를 분석한 결과 도시형 및 도시주변형은 산야형, 주요산줄기인접형 및 해안도서형보다 점수가 낮게 평가되어 상대적으로 해제성향이 높게 나타났다. 이를 바탕으로 표준정규분포 방법을 적용함으로써 A, B 등급으로 판정되는 경향이 증가하고 C, E 등급이 감소함으로써 보전성향으로 평가될 수 있는 잠재력이 증가하는 것으로 분석되었다. 따라서 본 연구에서는 각 산지유역유형별 평균값과 표준편차를 이용하여 표준정규화를 수행함으로써 지역간 보전 해제성향 필지수의 불균형을 해소할 수 있는 방안을 제시하였다.

• 대한기계학회논문집A
• /
• 제34권9호
• /
• pp.1305-1310
• /
• 2010

복잡한 시스템 계의 설계정보를 효과적으로 추출하기 위해서 형상최적설계가 수행되는 경우, 일반적으로 유한요소해석 기법과 D-최적배열을 이용한 실험계획법이 연동된 반응표면모델을 구성하고 여기에 최적설계기법이 적용된다. 그러나, 설계변수에 형상공차와 같은 변동성이 존재하면 최적해의 강건성 확보를 위하여 설계변수의 형상공차를 확률론적인 변동성으로 고려한 추가적인 강건설계가 필요하다. 본 연구에서는 계산시간이 많이 소요되는 유한요소해석에 의한 강건설계문제에 설계변수의 표준정규분포를 고려한 반응표면모델을 구축하여 최적설계를 수행하므로서 손쉽게 강건최적값을 구하는 방법을 제안하였다. 승용차용 브레이크 디스크에 제안된 방법을 적용하여 열변형과 중량을 최소화하는 설계변수의 강건최적해를 구하고, 몬테카를로 시뮬레이션 추정결과와 비교하여 이의 적합성을 검증하였다.

• 천문학회지
• /
• 제29권spc1호
• /
• pp.123-124
• /
• 1996

Snapshots of eight SA and standard fields from low to high galactic latitudes were made using the KPNO 0.9m 2K $\times$ 2K CCD with a limiting magnitude from 19 to 22.5. The purpose of this study is to determine the vertical distribution of stars with respect to Galactic latitude and z-distance in comparison with the model simulation between intermediate population to the 'thick disk' component of scale height of a few kpc. Comparison of the preliminary results between observed and model simulation for 3 of the S fields shows good agreement both in V-mag and B- V color distributions. A bimodal distribution in B- V at high galactic latitude seems to be represented by a halo and 'thick disk' dwarf in the blue and by a normal disk dwarf population in the red.

• 동력기계공학회지
• /
• 제5권4호
• /
• pp.11-17
• /
• 2001

Micronization of sensor is a trend of the silicon sensor development with regard to a piezoresistive silicon pressure sensor, the size of the pressure sensor diaphragm have become smaller year by year, and a microaccelerometer with a size less than $200{\sim}300{\mu}m$ has been realized, In this paper, we study some of the bonding processes of SCS(single crystal silicon) insulator wafer for the microaccelerometer. and their subsequent processes which might affect thermal loads. The finite element method(FEM) has been a standard numerical modeling technique extensively utilized in micro structural engineering discipline for design of SCS insulator wafers. Successful temperature distribution analysis and design of the SCS insulator wafers based on the tunneling current concept using microaccelerometer depend on the knowledge about normal mechanical properties of the SCS and $SiO_2$ layer and their control through manufacturing processes.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.270-273
• /
• 2007

In this paper, a SAR-despeck1ing approach of adaptive iteration based a Bayesian model using the lognormal distribution for image intensity and a Gibbs random field (GRF) for image texture is proposed for noise removal of the images that are corrupted by multiplicative speckle noise. When the image intensity is logarithmically transformed, the speckle noise is approximately Gaussian additive noise, and it tends to a normal probability much faster than the intensity distribution. The MRF is incorporated into digital image analysis by viewing pixel types as states of molecules in a lattice-like physical system. The iterative approach based on MRF is very effective for the inner areas of regions in the observed scene, but may result in yielding false reconstruction around the boundaries due to using wrong information of adjacent regions with different characteristics. The proposed method suggests an adaptive approach using variable parameters depending on the location of reconstructed area, that is, how near to the boundary. The proximity of boundary is estimated by the statistics based on edge value, standard deviation, entropy, and the 4th moment of intensity distribution.