역가우스분포에 대한 변형된 엔트로피 기반 적합도 검정

최병진,Choi, Byung-Jin 한국통계학회 2011 응용통계연구 Vol.24 No.2

This paper presents a modified entropy-based test of fit for the inverse Gaussian distribution. The test is based on the entropy difference of the unknown data-generating distribution and the inverse Gaussian distribution. The entropy difference estimator used as the test statistic is obtained by employing Vasicek's sample entropy as an entropy estimator for the data-generating distribution and the uniformly minimum variance unbiased estimator as an entropy estimator for the inverse Gaussian distribution. The critical values of the test statistic empirically determined are provided in a tabular form. Monte Carlo simulations are performed to compare the proposed test with the previous entropy-based test in terms of power. 이 논문에서는 역가우스분포의 적합을 위한 변형된 엔트로피 기반 검정을 제시한다. 이 검정은 자료생성분포와 역가우스분포의 엔트로피 차이에 기초를 두고 있으며 검정통계량은 엔트로피 차이의 추정량을 사용한다. 엔트로피 차이의 추정량은 자료생성분포에 대한 엔트로피 추정량으로 Vasicek의 표본엔트로피와 역가우스분포에 대한 엔트로피 추정량로 균일최소분산불편추정량을 사용하여 얻는다. 모의실험을 통해 얻은 표본크기와 윈도크기에 따른 검정통계량의 기각값들을 표의 형태로 제공한다. 제안한 검정의 검정력 알아보기 위해 여러 대립분포와 표본크기에 대해서 모의실험을 수행하고 기존의 엔트로피 기반 검정과 비교한다.

("동의수세보원(東醫壽世保元)" "병증론(病證論)" 의 '소증(素證)(소병)(素病)'에 대한 고찰

최병진,하기태,최달영,김준기,Choi, Byung-Jin,Ha, Ki-Tae,Choi, Dall-Yeong,Kim, June-Ki 대한동의생리학회 2007 동의생리병리학회지 Vol.21 No.1

${\ulcorner}$Hamsansachon Dongyi Suse Bowon Gabogubon${\lrcorner}$ , discovered in 2000, can give very precious information in order to study the formation and development process of ${\ulcorner}$Dongyi Suse Bowon${\lrcorner}$ ${\ulcorner}$The Dircourse on the Constitutional Symptoms and Disease${\lrcorner}$ . I examined, by comparison, changes in understanding pathology explained in ${\ulcorner}$Dongyi Suse Bowon${\lrcorner}$ ${\ulcorner}$The Discourse on the Constitutional Symptoms and Disease${\lrcorner}$ of Gabobon and Sinchukbon, and consequently tried to define the concept of Dispositional Symptom(Dispositional disease) as below, in a point of view that ‘Dispositional Symptom(Dispositional disease)’ should be the key word in explaining the changes in understanding of pathology. Dispositional Symptom(dispositional disease) is a new concept that was first troduced in the Kyongjabon, not found in the Gabobon, and that played a key role in editing ${\ulcorner}$Dongyi Suse Bowon${\lrcorner}$ ${\ulcorner}$The Discourse on the Constitutional Symptom and Disease${\lrcorner}$ . Dispositional Symptom(dispositional disease) means an innate temperament or a pathological tendency, which is already constructed in the system of an individual, prior to expression of specific diseases and symptoms, and can be a primary basis to tell the susceptibility and developing pattern of a certain disease, to decide how to treat and forecast the prognosis. Sinchukbon inductively categorized symptoms of the dispositional symptom (dispositional disease) into the concept of ‘Eight principles’, or eight standards of diagnosis, such as superficies-interior, cold-heat, and weakness-strength.

QPATR를 이용한 독일어 파생어의 어휘구조 분석 - 통합에 기반한 어휘통사론적 접근 -

최병진,Choi Byung-Jin 한국독어학회 2001 독어학 Vol.3 No.-

In diesem Aufsatz wird versucht, die Wortbildungsstruktur der deutschen Ableitungen zu analysieren und in QPATR zu implementieren. $Daf\"{u}r$ werden die deutschen Ableitungen in morphosyntaktischer Hinsicht betrachtet. Die Wortbildungsstruktur der Ableitungen wird durch Phrasenstrukturregeln mit den detaillierten Unterspezifikationen beschrieben, die durch Unifikation definiert sind. Es wird davon ausgegangen, $da{\ss}\;S\"{a}tze$ durch Phrasenstrukturregeln, die syntaktische Kombinierbarkeit der unmittelbaren Konstituenten definieren, zu analysieren sind. In Wortern sind auch die Regeln $f\"{u}r$ die Erzeugung und Analyse von abgeleiteten $W\"{o}rtern$ zu finden. Die Wortbildungsregln und die Phrasenstrukturregeln von $S\"{a}tzen$ haben $\"{A}hnlichkeit$ von der Form her. $Au{\ss}erdem$ kann man die mophosyntaktischen $Ph\"{a}nomene$ der Kongruenz oder die Selektionsrestriktion nicht nur auf der Satzsyntax, sondern auch auf der Wortsyntax betrachten. D.h. wenn man durch einen Parser mit Hilfe der Phrasenstrukturregeln einen Satz analysieren kann, kann man auch ein Wort aufgrund der Wortbildungsregeln parsen. Im ersten Abschnitt werden die grundlegenden Begriffe der 'unifikationsbasierten Grammatiken', $n\"{a}mlich$ die Begriffe 'Merkmalstruktur', 'Unifikation', und 'Subsumption' $eingef\"{u}hrt$. Im zweiten Abschnitt wird der QPATR - Parser vorgestellt, der aufgrund des 'PATR-II'-Formalismus in $D\"{u}sseldorf$ entwickelt worden ist. Im dritten Abschnitt werden die deutschen abgeleiteten $W\"{o}rter$ durch QPATR analysiert. Bei der Analyse der Worter wird gezeigt, wie die Left-corner-parsing-Strategie funktioniert, und Wie die spezifizierten Informationen durch Unifikation als 'Constraints' die zu kombinierenden unmittelbaren Konstituenten $beschr\"{a}nken$. Zum $Schlu{\ss}$ werden die Ergebnisse der Analyse durch Baumstruktur und Merkmalstruktur $repr\"{a}sentiert$, die durch QPATR automatisch erzeugt werden.

독한 전자사전을 위한 어휘항목의 미시구조에 대한 연구

최병진,Choi Byung-Jin 한국독어학회 2002 독어학 Vol.6 No.-

In diesem Aufsatz wired versucht, eine Mikrostruktur $f\"{u}r$ ein elektronisehes Detusch-Koreanisehes $W\"{o}rterbueh$ zu entwerfen. Bei gedruekten $W\"{o}rterb\"{u}ehern$ sind die lexikographischen Daten und die $W\"{o}rterbuch­strukturen$ mehr oder weniger standardisiert, dagegen bei elektronischen $W\"{o}rterb\"{u}ehern$ strikt formalisiert. Im Laufe der letzten 50 Jahre sind zwar viele gedruekte, jedoch kaum auf Elektronik basierte zweisprachige $W\"{o}rterb\"{u}cher\;f\"{u}r$ Deutseh-Koreanisch ersehienen. Elektronische $W\"{o}rterb\"{u}cher$ haben mehre Vorteile und sind in diesem Informationszeitalter als Hilfsmittel $f\"{u}r$ den Fremdspraeherwerb unabdingbar. Die Festlegung der logischen Struktur des $W\"{o}rterbuehs\;ist\;f\"{u}r\;die\;W\"{o}rterbucharbeit\;unerl\"{a}{\ss}lich$ und $f\"{u}r$ die Herstellung elektronischer $W\"{o}rterb\"{u}cher$ von Bedeutung, wird jedoch in der koreanischen Praxis oft $vemachl\"{a}{\ss}igt$. Daher weisen die meisten koranischen $W\"{o}rterb\"{u}cher$ keine konsistente Form in der Struktur von $W\"{o}rterbuehdefinitionen$ auf. Aus diesen $Gr\"{u}nden$ schlage ich eine formale logisehe Struktur $f\"{u}r$ ein elektronisches Deutsch-Koreanisches $W\"{o}rterbuch$ vor. $Zun\"{a}chst$ werden grundlegende lexikalische Begriffe $eingef\"{u}hrt,\;anschlie{\ss}end$ wird auf die Analyse der lexikalischen $Eintr\"{a}ge\;f\"{u}r$ ein Deutsch-Koreanisches $W\"{o}rterbuch$ eingegangen. In diesem Beitrag wird keine fertige Miktostruktur $pr\"{a}sentiert$, sondern eine Anregung zur weiteren Diskussion zu einer Mikrostruktur gegeben. Als logisehe Struktur $f\"{u}r$ das elektronische Deutsch-Koreanische $W\"{o}rterbuch$ wird eine glattalphabetische Makrostruktur aufgenommen, die Mikrostruktur als semiintegriert. Die lexikographische Arbeit ist $zeitaufw\"{a}ndig$ und braucht viele $Fachkr\"{a}fte$. Deshalb ist die Festlegung einer konsistenten und objektiven Mikrostruktur eine Voraussetzung der $W\"{o}rterbuchherstellung$. Sie regt auch dazu an, die lexikalischen Informationen im Artikel genauer zu analysieren. Erst dadurch wird ein effektives elektronisches $W\"{o}rterbuch\;m\"{o}glich$, das eine Weiterbenutzung der klassifizierten Informationen $unterst\"{u}tzt$.

한국산 긴날개박쥐 (Miniopterus schreibersi fuligino년)의 정자변태동안의 소포체와 골지체에 관한 전자현미경적 관찰

최병진,손성원,이정훈,이계일,Choi, Byung-Jin,Son, Sung-Won,Lee, Jung-Hun,Lee, Kae-Il 한국현미경학회 1998 Applied microscopy Vol.28 No.4

The present study was designed in order to observe relationship between the endoplasmic reticulum and the Golgi complex during spermiogenesis of the long-fingered bat (Miniopterus schreibersi fuliginosus). The testes were obtained from adult bats and treated with the prolonged osmification or fixed with ferrocyanide reduced osmiun. In the Golgi phase, The Golgi complex shows an oval shape, and was composed of a cortex and a medullar enclosing acrosome. The Golgi vacuoles with electron-dense granules of crescent shape were fused with each other. The smooth endoplasrnic reticulum was scattered in all the area of the cytoplasm. In the cap phase, The Golgi complex was crescent in shape, and faced to a nucleus. Large and small vesicles were fused with each other, and then fused with a acrosomal vacuole. The rough endoplasmic reticulum was close to the large Golgi vacuole. In the acrosome phase, The Golgi complex was moved to behind of the acrosome face. Small vesicles were fused with an acrosome, and cisternae of the trans-face of Golgi complex was connected with an acrosome in the early acrosome phase. The smooth endoplasmic reticulum was distributed in the cytoplasm. The annulate lamellar was originated from a radial body-annulate lammellae complex. In the maturation phase, The Golgi complex with dilated cistrern appeared in the cytoplasm, and also, annulate lamellar was observed in the cytoplasm. The connection of the annulate lamellar with the cistern of radial body suggests that an annulate lamellar seems to be closely related to radial body. The smooth endoplasmic reticulum was scattered in the cytoplasm in the early Golgi phase, but annulate lamellar-radial body complex which might be a residual and disappearing form of the smooth endoplasmic reticulum appeared in the acrosome phase. The Golgi complex steadily remained in the late maturation phase when the endoplasmic reticulum began to disappear from the cytoplasm: the Golgi complex was still occurred after acrosome formation. The observations obtained in the present study, which was characterized by the presence of the Golgi complex in the late maturation phase, suggests that the Golgi complex may play an important role also even after the acrosome formation.

한국산 박쥐 간장의 미세구조적 고찰

최병진,엄창섭,장병준,박창현,Choi, Byung-Jin,Uhm, Chang-Sub,Chang, Byung-Jun,Park, Chang-Hyun 한국현미경학회 2001 Applied microscopy Vol.31 No.4

한국산 관박쥐과의 관박쥐 (Rhinolophus ferrmmequinum korai)와 애기박쥐과 Myotis속에 속하는 큰발웃수염 박쥐 (Myotis macrodactylus), 물웃수염박쥐 (Myotis daubentonii ussrinesis) 및 관코박쥐 (Murina leucogaster intermedia)의 활동기 간장 조직을 투과전자현미경으로 관찰하여 이들의 미세구조적 특징을 규명하고 이들 간에 존재하는 차이를 비교 고찰하고자 하였다. 관박쥐는 세포질 내에 $10\sim20$개의 크고 둥근 사립체를 가지고 있었으며, 특히 과산화소체가 잘 발달되어 있었다. 큰발웃수염박쥐는 간세포간 사이의 연접복합체, 특히 부착반점이 잘 발달되어 있었다. 디세강과 동굴모세혈관 속은 섬세한 물질로 채워져 있었다. 물웃수염박쥐는 세포질 내에 당원과립을 많이 가지고 있었으며, 디세강과 동양혈관 속은 섬세한 물질로 채워져 있었다. 관코박쥐는 동굴모세혈관에 기저막이 잘 발달되어 있었으며, Kupffer 세포와 Ito 세포는 관찰되지 않았다. 이상의 결과는 같은 시기의 한국산 박쥐의 간장에서도 종에 따라서 미세구조적 차이가 나타남을 보여주는 것으로 이들은 이들의 생활환경과 식이와 관련이 있을 것으로 추정된다. To understand the fine structure of Korean bat livers , the authors investigated the liver of four Korean bats; Rhinolephus ferrumequinum korai, Myotis macrodactylus, Myotis dauhentonii ussrinesis, and Murina leucogaster intermedia by transmission electron microscopy. The hepatocytes of Rhinolophus ferrumequinum korai had large-sized mitochondria and many peroxisomes. In the Myotis macrodactylus, juctional completes, especially desmosomes, were well developed. The Myotis daubentonii ussrinesis had many glycogen particles in the cytoplasm. Also, the space of Disse and sinusoidal spare was filled with amorphous materials. In the Murina leucogaster intemedia, basement membrane was prominent in the sinusoid, and no Kupffer and Ito cells were observed These results suggest the characteristic differences in the liver ultrastructure among Korean bats.

역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정

최병진,Choi, Byung-Jin 한국통계학회 2011 응용통계연구 Vol.24 No.6

본 논문에서는 위치와 척도모수가 모두 알려지지 않은 역가우스분포에 대한 적합도 검정으로 기존에 개발된 엔트로피 기반 검정을 확장한 쿨백-라이블러 정보 기반 적합도 검정을 소개한다. 역가우스분포에 대한 단순 또는 복합 영가설을 검정하기 위한 4가지 형태의 검정통계량을 제시하고 검정통계량의 계산에 사용할 표본크기에 따른 윈도크기와 기각값을 모의실험을 통해 결정하여 표의 형태로 제공한다. 검정력 분석을 위해 수행한 모의실험의 결과에서 위치와 척도모수가 모두 알려진 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 모든 대립분포와 표본크기에서 EDF 검정들보다 좋은 검정력을 가지는 것으로 나타난다. 위치모수 또는 척도모수만 알려진 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 모든 대립분포에 대해서 표본크기가 커짐에 따라 검정력이 증가하는 경향을 보인다. 위치와 척도모수가 모두 알려지지 않은 역가우스분포에 대한 쿨백-라이블러 정보 기반 적합도 검정은 대체적으로 엔트로피 기반 검정과 비슷한 수준의 검정력을 보이는 것으로 나타나고 이 결과를 통해서 두 검정은 동일함을 확인할 수 있다. The entropy-based test of fit for the inverse Gaussian distribution presented by Mudholkar and Tian(2002) can only be applied to the composite hypothesis that a sample is drawn from an inverse Gaussian distribution with both the location and scale parameters unknown. In application, however, a researcher may want a test of fit either for an inverse Gaussian distribution with one parameter known or for an inverse Gaussian distribution with both the two partameters known. In this paper, we introduce tests of fit for the inverse Gaussian distribution based on the Kullback-Leibler information as an extension of the entropy-based test. A window size should be chosen to implement the proposed tests. By means of Monte Carlo simulations, window sizes are determined for a wide range of sample sizes and the corresponding critical values of the test statistics are estimated. The results of power analysis for various alternatives report that the Kullback-Leibler information-based goodness-of-fit tests have good power.

로그정규분포의 엔트로피에 대한 두 모수적 추정량의 비교

최병진,Choi, Byung-Jin 한국통계학회 2011 Communications for statistical applications and me Vol.18 No.5

본 논문에서는 로그정규분포의 엔트로피에 대한 모수적 추정량으로 최소분산비편향추정량과 최대가능도추정량을 제시하고 성질을 비교한다. 각 추정량의 분산을 유도해서 일치성을 밝히고 최대가능도 추정량의 편향이 추정에 미치는 영향을 분석한다. 델타근사방법을 이용해서 얻은 추정량의 분포를 제시하고 적합도 평가를 통한 유도한 분포의 확증을 위해서 모의실험을 수행한다. 평균제곱오차에 의한 상대적 효율성에 대한 조사를 통해 두 추정량의 성능을 비교한다. 모의실험의 결과에서 최소분산비편향추정량은 최대가능도 추정량보다 더 좋은 효율을 보이는 것으로 나타나며, 특히 표본크기와 분산이 동시에 작아짐에 따라 효율이 점점 높아지게 되어 월등히 나은 성능을 발휘함을 볼 수 있다. This paper proposes two parametric entropy estimators, the minimum variance unbiased estimator and the maximum likelihood estimator, for the lognormal distribution for a comparison of the properties of the two estimators. The variances of both estimators are derived. The influence of the bias of the maximum likelihood estimator on estimation is analytically revealed. The distributions of the proposed estimators obtained by the delta approximation method are also presented. Performance comparisons are made with the two estimators. The following observations are made from the results. The MSE efficacy of the minimum variance unbiased estimator appears consistently high and increases rapidly as the sample size and variance, n and ${\sigma}^2$, become simultaneously small. To conclude, the minimum variance unbiased estimator outperforms the maximum likelihood estimator.

쿨백-라이블러 판별정보에 기반을 둔 정규성 검정의 개선

최병진,Choi, Byung-Jin 한국통계학회 2007 응용통계연구 Vol.20 No.1

Arizono와 Ohta(1989)에 의해 소개된 정규성 검정은 쿨백-라이블러 판별정보를 이용하고 있으며, 검정통계량의 유도에 기반이 되는 판별정보의 추정량을 얻기 위해 Vasicek(1976)의 표본엔트로피와 분산의 최대가능도 추정량을 사용했다. 그런데 두 추정량은 편향성을 가지게 되므로 보다 정확한 판별정보의 추정을 위해 비편향 추정량을 사용하는 것이 바람직하다. 본 논문에서는 편향을 수정한 엔트로피 추정량과 분산의 균일최소분산비편향 추정량을 사용하여 판별정보의 추정량을 구하고 이로부터 유도되는 검정통계량을 사용하는 개선된 정규성 검정을 제시한다. 제안한 검정의 특성을 규명하고 검정력 비교를 위해서 모의실험을 수행한다. A test for normality introduced by Arizono and Ohta(1989) is based on fullback-Leibler discrimination information. The test statistic is derived from the discrimination information estimated using sample entropy of Vasicek(1976) and the maximum likelihood estimator of the variance. However, these estimators are biased and so it is reasonable to make use of unbiased estimators to accurately estimate the discrimination information. In this paper, Arizono-Ohta test for normality is improved. The derived test statistic is based on the bias-corrected entropy estimator and the uniformly minimum variance unbiased estimator of the variance. The properties of the improved KL test are investigated and Monte Carlo simulation is performed for power comparison.

번역 교육을 위한 대안사전 개발의 방법론적 고찰

최병진,Choi Byung-Jin 한국독어학회 2004 독어학 Vol.9 No.-

Ziel diesel Albeit ist os, Lexkion zu erstellen, das nicht nur der menschlichen $\"{U}bersetzung$, sondern auch der $nat\"{u}rlichsprachlichen$ Verarbeitung dienen soll. Um eine automatische maschinelle $\"{U}bersetzung$ $durchf\"{u}hren$ zu iassen, braucht man noch ein umfangreiches Wissen in Lunguistik und Informatik. Bei der Verarabeitung, aufgrund derer ein Wort oder eine Phrase aus der Ausgangssprache durch ein passendes $\"{A}quivalent$ der Zielsprache $\"{u}berstzt$ wird, sollte man auch auf die kuiturellen Hintergrunde $R\"{u}cksicht$ nehmen. $W\"{a}hrend$ des $\"{U}bersetzens$ versuchen $\"{U}bersetzer$ odor Dolmetscher, zweisprachige $W\"{o}rterbucher$ zu konsultieren, urn die angemessensten $\"{A}quivalente$ der Zielsprache zu finden. In vielen $F\"{a}llen$ aber macht man die Erfahrung, dass solche $Bem\"{u}hungen$ vergeblich sind In dieser Albeit wird $zun\"{a}chst$ das parallele Korpus (Koreanisch-Deutsch) untersucht, um das Desiderat der $herk\"{o}mmlichen$ $W\"{o}rterb\"{u}cher$ festzustelien. In den parallenen Koreanisch-Deutsch Korpora wird die $W\"{o}lter$ oder Phrasen der Ausgangssprache mit denen der Zielsprache verglichen und auf diesel Grundlage eine Liste von $M\"{a}ngeln$ erstellt. Die Ergebnisse diesel Untersuchung sollten nicht nur auf die menschliche $\"{U}bersetzung$, sondern auch auf die $nat\"{u}rlichsprachliche$ Verarbeitung angewendet werden, damit die Effizienz der $\"{U}bersetzung$ nock erheht wird. $Au{\ss}erdem$ soll die weitere Untersuchung mit den Korpora auch $f\"{u}r$ den Fremdsprachenunterricht $Anwendungsm\"{o}glichkeiten bieten.