• The Korean Journal of Applied Statistics
• /
• v.20 no.1
• /
• pp.39-52
• /
• 2007

Crossover trials of new drugs in the treatment of angina pectoris, which frequently use treadmill exercise test for the assessment of its efficacy, produce censored survival times. In this paper we consider analysis approaches for censored survival times from crossover trials. Previously, a stratified Cox model for paired observation and nonparametric methods have been presented as possible analysis methods. On the other hand, the differences of two survival times would produce interval-censored survival times and we propose a Cox model for interval-censored data as n alternative analysis method. Example data is analyzed in order to compare these different methods.

• Proceeding of EDISON Challenge
• /
• 2013.04a
• /
• pp.37-52
• /
• 2013

무어의 법칙에 따르면, 반도체의 집적도 2년마다 2배씩 증가한다고 한다. 무어의 법칙은 지금까지는 집적회로 기술의 발전을 잘 예측했다. 하지만 트랜지스터의 사이즈를 줄일수록 누수전류와 회로의 저항을 조절하기 어렵기 때문에 트랜지스터의 소형화에는 한계가 있다. 우리는 곧 무어의 법칙의 한계를 맞이할 것이다. 그래서 트랜지스터를 더욱 소형화시키기 위해서는 bottom-up analysis가 필요한 시점이다. Top-down analysis가 초기의 커다란 트랜지스터에서 점점 소형화를 시켜 작은 트랜지스터를 만든다는 개념인 반면, Bottom-up analysis는 처음부터 작은 분자를 조작하여 트랜지스터와 같은 성질을 띄도록 만드는 개념이다. 분자가 기억소자로서 이용되려면 저항이 다른 2가지 안정한 상태가 필요하다. 이번 연구에서 나는 기억소자를 디자인 하기 위하여 high spin state와 low spin state 두 가지 안정한 상태를 가지는 spin crossover complex를 이용하기로 했다. 이전의 연구에서 spin crossover 는 전기장을 이용해서도 유도될 수 있다고 확신하였고, 이를 이용해서 기억소자를 디자인하기로 하였다. 이번 연구를 위해서 symmetry를 가지는 octahedral spin crossover complex를 디자인하였고 이를 '기억 분자'라고 명명했다. 그리고 이 분자의 high spin state와 low spin state가 전기장을 이용하여 서로 바뀔 수 있는지 가능성을 DFT with B3LYP functional을 이용해서 비교했다. 그 결과로 전기장을 이용하여 기억분자의 spin crossover을 일으킬 수는 있지만 abnormally strong electric field를 써야 한다는 사실을 알아냈다. 이번 연구를 토대로 추후의 연구를 위해, 기억소자가 되기 위하여 분자가 어떤 특징을 만족시켜야 하는지를 분석했다.

• The Korean Journal of Applied Statistics
• /
• v.29 no.2
• /
• pp.279-289
• /
• 2016

Bioequivalence trials based on higher order crossover designs have recently been conducted for highly variable drugs since the Ministry of Korea Food and Drug Safety (MFDS) added new regulations in 2013 to widen bioequivalence limits for highly variable drugs. However, a statistical discussion of higher order crossover designs have not been discussed yet. This research proposes the statistical inference of bioequivalence based on $3{\times}3$ crossover design and discusses it with the MFDS regulations. An illustrated example is also given.

• Communications for Statistical Applications and Methods
• /
• v.6 no.2
• /
• pp.601-610
• /
• 1999

Crossover design is officially except for special occasions recommended by KFDA and FDA for assessing Bioequivalence between two drugs one for reference and the other for innovator. Such design is regarded as a special case of latin square split-polt or repeated measurement design and its main difference with other designing methods is that each subject in an experiment is exposed two drugs in sequence. Therefore general statistical analysis is not suitable since the model for this experiment includes carryover effect in addition to period and sequence effect. in this paper analysis for crossover model with two drugs and its interpretation are mainly discussed and an example is given for illustration.

• Proceedings of the Polymer Society of Korea Conference
• /
• 2006.10a
• /
• pp.320-320
• /
• 2006

The authors report the synthesis and radical ring-crossover polymerization of macrocycles with radically exchangeable dynamic covalent bonds. The macrocyclic compounds with alkoxyamine units were designed and synthesized by condensation from alkoxyamine-based diol and the corresponding acid chlorides in the presence of pyridine under high-dilution condition. The macrocycles can thermally polymerize by intermolecular radical crossover reaction. Furthermore, the poly(alkoxyamine)s depolymerized to the monomers principally by the intramolecular radical exchange process under high-dilution conditions.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.203-205
• /
• 1999

The unit commitment is an important problem of production scheduling which determines the generating unit to in service(on/off) during scheduling period, to meet system demand and reserve requirement at minimum cost. This paper presents an box type crossover to improve searching ability of GA, to solve unit commitment problem. Satisfactory results are obtained by GA with the proposed crossover operator.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.1
• /
• pp.245-257
• /
• 2006

A modified Anderson and Hauck(1983) test for analyzing a two-sequence two-period crossover design in bioequivalence trials is proposed when some observations at the second period are missing. It is based on the maximum likelihood estimators of average bioequivalence model and designed for handling missing at random(MAR) situation. The performance of the proposed test is compared to other tests using Monte Carlo simulations.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.5
• /
• pp.545-552
• /
• 1999

The Maintenance scheduling is one of the mid-term scheduling problems systems. There have been many methods for this problem, but there is no effective way to treat all the generators simultaneously. In this paper, we apply a genetic algorithm(GA) to the maintenance scheduling problem. We proposed new crossover operators(BOX type crossover) to improve searching ability of GA. Satisfactory results are obtained by GA with the proposed corssover operators.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.3
• /
• pp.15-34
• /
• 1994

This paper considers the genetic algorithms(GAs) for the mixed model assembly line sequencing(MMALS) in which the objective is to minimize the overall line length. To apply the GAs to the MMALS, the representation, selection, genetic sequencing operators, and genetic parameters are studied. Especially, the existing sequencing binary operators such as partially map crossover(PMX), cycle crossover(CX), and order crossover (OX) are modified to be suitable for the MMALS, and a new sequencing binary operator called immediate successor relationship crossover (ISR) is introduced. These binary operators mentioned above and/or unary operators such as swap, insertion, inversion, displacement, and splice are compared to find operators which work well in the MMALS. Experimental results indicate that 1) among the binary operators ISR operator is the best, followed by the modified OX, and the modified PMX, with the modified CX being the worst, 2) among the unary operators inversion operator is the best, followed by displacement, swap, and insertion, with splice being the worst, and 3) in general, the unary operators perform better than the binary operators for the MMALS.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.341-344
• /
• 2007

본 논문에서는 계층적 공정 경쟁 개념을 병렬 유전자 알고리즘에 적용하여 계층적 공정 경쟁 기반 병렬유전자 알고리즘 (Hierarchical Fair Competition Genetic Algorithm: HFCGA)을 구현하였을 뿐만 아니라 실수코딩 유전자 알고리즘(Real-Coded Genetic Algorithm: RCGA)에서 좋은 성능을 갖는 산술교배(Arithmetic crossover), 수정된 단순교배(modified simple crossover) 그리고 UNDX(unimodal normal distribution crossover)등의 다양한 교배연산자들을 적용, 분석함으로써 개선된 병렬 유전자 알고리즘을 제안하였다. UNDX연산자는 다수의 부모(multiple parents)를 이용하여 부모들의 기하학적 중심(geometric center)에 근접하게 정규분포를 이루며 생성된다. 본 논문은 UNDX를 이용한 HFCGA모델을 구현하고 함수파라미터 최적화 문제에 많이 쓰이는 함수들에 적용시킴으로써 그 성능의 우수성을 증명 한다.