• 한국측량학회지
• /
• 제34권1호
• /
• pp.91-98
• /
• 2016

지구통계학적인 공간분석의 대표적인 방법인 크리깅(kriging)을 적용하기 위해서는 두 관측점 사이의 거리에 기반한 상관성을 나타내는 공간상관함수의 추정이 우선적으로 이루어져야 한다. 본 연구에서는 다양한 크리깅에 적용할 수 있는 대표적인 상관함수인 semi-variogram, homeogram, covariance function에 대하여 국가지오이드 모델을 기반으로 추정하였다. 경위도 각각 2°의 대상지역 내 통합기준점의 지오이드고를 이용하였으며, 선형모델을 이용하여 공간적인 편향성을 제거하였다. 전체 100개의 샘플 포인트에 대해서 중복되지 않은 두 점 간의 거리를 기준으로 구간을 나누고, 각 함수에 대한 경험적인 값을 계산하였다. 공간상관함수의 경험적인 값은 각각 두 개의 모델에 최소제곱조정 방법으로 피팅한 결과 semi-variogram의 wave 모델 적합도가 가장 높았으며, homeogram과 covariance function은 exponential 모델이 상대적으로 좋은 피팅 결과를 보였다. 본 연구에서 결정한 공간상관함수는 추후 다양한 크리깅 방법을 통해 임의 지점에서의 예측값에 대한 정확도 검증과 이에 대한 평균제곱예측오차(Mean Squared Prediction Error, MSPE)를 계산함으로써 각 함수의 활용성에 대한 추가적인 연구가 수행되어야 한다.

• 대한치과교정학회지
• /
• 제53권3호
• /
• pp.185-193
• /
• 2023

Objective: The growth and development of the mandible strongly depend on modeling changes occurring at its ramus. Here, we investigated covariance patterns between the morphology of the ramus and the rest of the face. Methods: Lateral cephalograms of 159 adults (55 males and 104 females) with no history of orthodontic treatment were collected. Geometric morphometrics with sliding semi-landmarks was used. The covariance between the ramus and face was investigated using a two-block partial least squares analysis (PLS). Sexual dimorphism and allometry were also assessed. Results: Differences in the divergence of the face and anteroposterior relationship of the jaws accounted for 24.1% and 21.6% of shape variation in the sample, respectively. Shape variation was greater in the sagittal plane for males than for females (30.7% vs. 17.4%), whereas variation in the vertical plane was similar for both sexes (23.7% for males and 25.4% for females). Size-related allometric differences between the sexes accounted for the shape variation to a maximum of 6% regarding the face. Regarding the covariation between the shapes of the ramus and the rest of the face, wider and shorter rami were associated with a decreased lower anterior facial height as well as a prognathic mandible and maxilla (PLS 1, 45.5% of the covariance). Additionally, a more posteriorly inclined ramus in the lower region was correlated with a Class II pattern and flat mandibular plane. Conclusions: The width, height, and inclination of the ramus were correlated with facial shape changes in the vertical and sagittal planes.

• Annals of Clinical Neurophysiology
• /
• 제25권2호
• /
• pp.93-102
• /
• 2023

Background: We aimed to identify any differences in the structural covariance network based on structural volume and those in the functional network based on cerebral blood flow between the ipsilateral and contralateral hemispheres of pain in patients with episodic migraine without aura. Methods: We prospectively enrolled 27 patients with migraine without aura, all of whom had unilateral migraine pain. We defined the ipsilateral hemisphere as the side of migraine pain. We measured structural volumes on three-dimensional T1-weighted images and cerebral blood flow using arterial spin labeling magnetic resonance imaging. We then analyzed the structural covariance network based on structural volume and the functional network based on cerebral blood flow using graph theory. Results: There were no significant differences in structural volume or cerebral blood flow between the ipsilateral and contralateral hemispheres. However, there were significant differences between the hemispheres in the structural covariance network and the functional network. In the structural covariance network, the betweenness centrality of the thalamus was lower in the ipsilateral hemisphere than in the contralateral hemisphere. In the functional network, the betweenness centrality of the anterior cingulate and paracingulate gyrus was lower in the ipsilateral hemisphere than in the contralateral hemisphere, while that of the opercular part of the inferior frontal gyrus was higher in the former hemisphere. Conclusions: The present findings indicate that there are significant differences in the structural covariance network and the functional network between the ipsilateral and contralateral hemispheres of pain in patients with episodic migraine without aura.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.1
• /
• pp.485-489
• /
• 2006

In last decades, several linearization methods for the AOA measurements have been proposed, for example, Gauss-Newton method and closed-form solution. Gauss-Newton method can achieve high accuracy, but the convergence of the iterative process is not always ensured if the initial guess is not accurate enough. Closed-form solution provides a non-iterative solution and it is less computational. It does not suffer from convergence problem, but estimation error is somewhat larger. This paper proposes a self-tuning weighted least square AOA algorithm that is a modified version of the conventional closed-form solution. In order to estimate the error covariance matrix as a weight, two-step estimation technique is used. Simulation results show that the proposed method has smaller positioning error compared to the existing methods.

• 한국광학회지
• /
• 제30권3호
• /
• pp.87-93
• /
• 2019

대기를 매개로 사용하는 광학 시스템에서 대기의 난류가 빛의 위상에 미치는 영향을 모사하기 위하여 위상판이 널리 사용된다. 본 논문에서는 위상판을 생성하는 3가지 방법을 정확성과 위상판 생성 시간 측면에서 비교 분석한다. 비교에 사용된 샘플 기반 위상판 생성 방법은 FFT, 저조파, 공분산 행렬 방법이다. 공분산 행렬 방법으로 생성된 위상판의 경우 구조 함수 값이 이론치에 매우 가까웠으며, 위상판 생성 시간도 다른 두 방법보다 크게 오래 걸리지 않았다.

• 대기
• /
• 제26권3호
• /
• pp.483-492
• /
• 2016

We have examined the random error of eddy covariance (EC) measurements on the basis of two-tower approach during daytime. Two EC towers were placed on the grassland with different vegetation density near Gumi-weir. We calculated the random error using three different methods. The first method (M1) is two-tower method suggested by Hollinger and Richardson (2005) where random error is based on differences between simultaneous flux measurements from two towers in very similar environmental conditions. The second one (M2) is suggested by Kessomkiat et al. (2013), which is extended procedure to estimate random error of EC data for two towers in more heterogeneous environmental conditions. They removed systematic flux difference due to the energy balance deficit and evaporative fraction difference between two sites before determining the random error of fluxes using M1 method. Here, we introduce the third method (M3) where we additionally removed systematic flux difference due to available energy difference between two sites. Compared to M1 and M2 methods, application of M3 method results in more symmetric random error distribution. The magnitude of estimated random error is smallest when using M3 method because application of M3 method results in the least systematic flux difference between two sites among three methods. An empirical formula of random error is developed as a function of flux magnitude, wind speed and measurement height for use in single tower sites near Nakdong River. This study suggests that correcting available energy difference between two sites is also required for calculating the random error of EC data from two towers at heterogeneous site where vegetation density is low.

• 한국군사과학기술학회지
• /
• 제24권5호
• /
• pp.492-502
• /
• 2021

In electronic warfare, source enumeration and direction-of-arrival estimation are important. The source enumeration method based on eigenvalues of covariance matrix from received is one of the most used methods. However, there are some drawbacks such as accuracy less than 100 % at high SNR, poor performance at low SNR and reduction of maximum number of estimating sources. We suggested new method based on eigenvalues gaps, which is named AREG(Accumulated Ratio of Eigenvalues Gaps). Meanwhile, FGML(Fast Gridless Maximum Likelihood) which reconstructs the covariance matrix was suggested by Wu et al., and it improves performance of the existing source enumeration methods without modification of algorithms. In this paper, first, we combine AREG with FGML to improve the performance. Second, we compare the performance of source enumeration and direction-of-arrival estimation methods in Rayleigh fading. Third, we suggest new method named REG(Ratio of Eigenvalues Gaps) to reduce performance degradation in Rayleigh Fading environment of AREG.

• 응용통계연구
• /
• 제35권2호
• /
• pp.285-298
• /
• 2022

연속 수축 사전분포는 spike and slab 사전분포와 더불어, 희박 회귀계수 벡터 또는 공분산 행렬에 대한 베이지안 추론을 위해 널리 사용되고 있다. 특히 고차원 상황에서, 연속 수축 사전분포는 spike and slab 사전분포에 비해 매우 작은 모수공간을 가짐으로써 계산적인 이점을 가진다. 하지만 연속 수축 사전분포는 정확히 0인 값을 생성하지 않기 때문에, 이를 이용한 변수 선택이 자연스럽지 않다는 문제가 있다. 비록 연속 수축 사전분포에 기반한 변수 선택 방법들이 개발되어 있기는 하지만, 이들에 대한 포괄적인 비교연구는 거의 진행되어 있지 않다. 본 논문에서는, 연속 수축 사전분포에 기반한 두 가지의 변수 선택 방법들을 비교하려 한다. 첫 번째 방법은 신용구간에 기반한 변수 선택, 두 번째 방법은 최근 Li와 Pati (2017)가 개발한 sequential 2-means 알고리듬이다. 두 방법에 대한 간략한 소개를 한 뒤, 다양한 모의실험 상황에서 자료를 생성하여 두 방법들의 성능을 비교하였다. 끝으로, 모의실험으로부터 발견한 몇 가지 사실들을 기술하고, 이로부터 몇 가지 제안을 하며 논문을 마치려 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.775-792
• /
• 2015

Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.

• Journal of Information Processing Systems
• /
• 제13권2호
• /
• pp.400-416
• /
• 2017

Music emotion is an important component in the field of music information retrieval and computational musicology. This paper proposes an approach for automatic emotion classification, based on rough set (RS) theory. In the proposed approach, four different sets of music features are extracted, representing dynamics, rhythm, spectral, and harmony. From the features, five different statistical parameters are considered as attributes, including up to the $4^{th}$ order central moments of each feature, and covariance components of mutual ones. The large number of attributes is controlled by RS-based approach, in which superfluous features are removed, to obtain indispensable ones. In addition, RS-based approach makes it possible to visualize which attributes play a significant role in the generated rules, and also determine the strength of each rule for classification. The experiments have been performed to find out which audio features and which of the different statistical parameters derived from them are important for emotion classification. Also, the resulting indispensable attributes and the usefulness of covariance components have been discussed. The overall classification accuracy with all statistical parameters has recorded comparatively better than currently existing methods on a pair of datasets.