• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.313-323
• /
• 2003

For the growth curve model with arbitrary covariance structure, known as unstructured covariance matrix, the problems of detecting outliers are discussed in this paper. In order to detect outliers in the growth curve model, the test statistics using U-distribution is established. After detecting outliers in growth curve model, we test homo and/or hetero-geneous covariance matrices using PSR Quasi-Bayes Criterion. For illustration, one numerical example is discussed, which compares between before and after outlier deleting.

• 전자공학회논문지SC
• /
• 제49권1호
• /
• pp.74-79
• /
• 2012

위상배열레이더를 이용한 추적의 성능을 지수화하기 위해서 각도예측 오차공분산행렬의 함수를 이용한 정량화 방법에 대해 검토하였다. 특히, 이 오차공분산행렬의 함수로 최대고유값과 대각합을 이용하여 정량화하는 경우에 대해 안테나 빔조향 손실을 반영한 표적탐지확률을 기준으로 정량화의 일관성을 수치실험을 통해 검토하였다. 이를 통해 추적성능을 표적탐지확률로 기준하는 경우, 대각합이 최대고유값 보다 더 일관성을 갖는 정량화 함수임을 확인하였다.

• Korean Journal of Mathematics
• /
• 제27권2호
• /
• pp.375-415
• /
• 2019

We study spaces of continuous-function-valued functions that have the property that composition with evaluation functionals induce $weak^*$ to norm continuous maps to ${\ell}^p$ space ($p{\in}(1,\;{\infty})$). Versions of $H{\ddot{o}}lder^{\prime}s$ inequality and Riesz representation theorem are proved to hold on these spaces. We prove a version of Dixmier's theorem for spaces of function-valued matrix operators on these spaces, and an analogue of the trace formula for operators on Hilbert spaces. When the function space is taken to be the complex field, the spaces are just the ${\ell}^p$ spaces and the well-known classical theorems follow from our results.

• 한국국방경영분석학회지
• /
• 제14권1호
• /
• pp.42-52
• /
• 1988

Many programmers start debugging by reading the faulty program from start to bottom without investigating carefully the erroneous program. Expert programmers, however, trace backward from a particular variable in a specific statement to identify all possible sources of influence on the value of variable (program slice). Weiser proposed a slicing algorithm (method) that is complex, iterative and still in modification [3,4]. This paper presents a method to generate a program slice by use of matrix computation which represents all possible slices of the program. The matrix representation of a program is soundly based on the graph theory of data dependency.

• 한국국방경영분석학회지
• /
• 제13권2호
• /
• pp.42-52
• /
• 1987

Many programmers start debugging by reading the faulty program from start to bottom without investigating carefully the erroneous program. Expert programmers, however, trace backward from a particular variable in a specific statement to identify all possible sources of influence on the value of variable (program slice). Weiser proposed a slicing algorithm (method) that is complex, iterative and still in modification [3,4]. This paper presents a method to generate a program slice by use of matrix computation which represents all possible slices of the program. The matrix representation of a program is soundly based on the graph theory of data dependency.

• 한국방사성폐기물학회:학술대회논문집
• /
• 한국방사성폐기물학회 2004년도 Proceedings of the 4th Korea-China Joint Workshop on Nuclear Waste Management
• /
• pp.182-190
• /
• 2004

An unique extraction chromatographic column (TOA: Tri-n-octylamine on Teflon powder) with a two-stage sample loading was prepared to separate Np and Pu from the environmental matrix. Np and Pu were efficiently retained in 4 M $HNO_3$ medium on the column and easily eluted with 0.02 M oxalic acid in 0.16 M HNO$_3$at $95^{\circ}C$. The separated solutions were free from most of the matrix elements and were aspirated into the ICP-MS directly. The decontamination factor for 238U is more than 104. The instrumental detection limit for 237Np was 0.46 pg mL-l ($1.2{\times}10_{-5}$Bq mL-l), and for 239Pu was 0.48 pg mL-l ($1.1{\times}10_{-3}$ Bq mL-l). The feasibility for the determination of both elements was proved by analysing IAEA-135 reference samples, the measured values agreed with the recommended reference value.

• Communications for Statistical Applications and Methods
• /
• 제29권6호
• /
• pp.721-733
• /
• 2022

In this paper we compare parameter estimation by Grassmann manifold optimization and sequential candidate set algorithm in a structured principal fitted component (PFC) model. The structured PFC model extends the form of the covariance matrix of a random error to relieve the limits that occur due to too simple form of the matrix. However, unlike other PFC models, structured PFC model does not have a closed form for parameter estimation in dimension reduction which signals the need of numerical computation. The numerical computation can be done through Grassmann manifold optimization and sequential candidate set algorithm. We conducted numerical studies to compare the two methods by computing the results of sequential dimension testing and trace correlation values where we can compare the performance in determining dimension and estimating the basis. We could conclude that Grassmann manifold optimization outperforms sequential candidate set algorithm in dimension determination, while sequential candidate set algorithm is better in basis estimation when conducting dimension reduction. We also applied the methods in real data which derived the same result.

• The Korean Journal of Physiology and Pharmacology
• /
• 제20권1호
• /
• pp.1-8
• /
• 2016

Damage in the periphery or spinal cord induces maladaptive plastic changes along the somatosensory nervous system from the periphery to the cortex, often leading to chronic pain. Although the role of neural circuit remodeling and structural synaptic plasticity in the 'pain matrix' cortices in chronic pain has been thought as a secondary epiphenomenon to altered nociceptive signaling in the spinal cord, progress in whole brain imaging studies on human patients and animal models has suggested a possibility that plastic changes in cortical neural circuits may actively contribute to chronic pain symptoms. Furthermore, recent development in two-photon microscopy and fluorescence labeling techniques have enabled us to longitudinally trace the structural and functional changes in local circuits, single neurons and even individual synapses in the brain of living animals. These technical advances has started to reveal that cortical structural remodeling following tissue or nerve damage could rapidly occur within days, which are temporally correlated with functional plasticity of cortical circuits as well as the development and maintenance of chronic pain behavior, thereby modifying the previous concept that it takes much longer periods (e.g. months or years). In this review, we discuss the relation of neural circuit plasticity in the 'pain matrix' cortices, such as the anterior cingulate cortex, prefrontal cortex and primary somatosensory cortex, with chronic pain. We also introduce how to apply long-term in vivo two-photon imaging approaches for the study of pathophysiological mechanisms of chronic pain.

• 분석과학
• /
• 제13권3호
• /
• pp.297-303
• /
• 2000

저니토 시료 중의 미량 Cd, Cu, Pb, Ni, Zn 등의 분석을 위해 동위원소희석 질량분석법을 이용하였다. 시료는 마이크로파 혼합산(질산, 불산, 과염소산) 분해법을 이용하여 용해하였다. Ammonium pyrrolidenedithiocarbamate(APDC) 용매 추출법을 이용하여 알칼리 및 알칼리 토금속을 분리한 다음 Pb를 측정하고, 나머지 원소들은 이 용액에 $NH_4OH$ 첨가 후 원심 분리하여 Fe, Sn, Ti 등을 제거한 다음 측정하였다. 측정원소의 회수율은 다소 떨어지나 동중원소 방해를 일으키는 매질원소를 효율적으로 제거할 수 있었다. 2종의 저니토 인증표준물질 중의 미량원소 분석에 이 방법을 적용한 결과 인증값과 잘 일치하는 측정 결과를 얻을 수 있었다.

• 방송공학회논문지
• /
• 제17권2호
• /
• pp.388-399
• /
• 2012

본 논문에서는 지역 특징 추출 방법 중 하나인 SURF를 개선시켜 모바일 환경에 적합한 특징 추출 및 정합 방법에 대하여 기술한다. 모바일 환경에서 최적의 성능을 내기 위해 크게 세 가지 방법을 제안한다. 첫 번째는 SURF 기술자의 차원을 축소시키는 방법이다. 기존의 64차원과 여러 차원의 기술자들의 성능을 비교 분석한다. 두 번째로 고속 헤시안 검출기에서 헤시안 행렬의 대각합을 통해 계산되는 라플라시안 부호를 사용하여 정합 성능을 높인다. 즉, 부호가 같으면 같은 특성의 특징점으로 여겨 정합하고 그렇지 않으면 정합하지 않는다. 세 번째는 특징점간의 거리 측정 시 사용하는 거리 비율을 실험하고, 실험을 통해 얻어진 거리 비율을 사용하여 정합의 성능을 높였다. 마지막으로, 기존의 시스템과 제안한 시스템의 성능을 비교하여 제안한 시스템의 성능 향상을 검증하고, 제안한 시스템이 비교적 정합률의 성능 저하 없이 응답속도를 크게 개선함을 보였다.