• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.655-664
• /
• 2015

A nonresponse adjusted raking ratio estimator that consists of weighting adjustment using estimated response probability and raking procedure is often used to reduce the nonresponse bias and keep the calibration property of the estimator. We investigated asymptotic properties of nonresponse adjusted raking ratio estimator and proposed a variance estimator. A simulation study is used to examine the performance of suggested estimators.

• Communications for Statistical Applications and Methods
• /
• 제11권2호
• /
• pp.419-433
• /
• 2004

We suggest the modified computing algorithm for raking ratio estimation under the assumption that the population total is partially known, and the sample total is completely known about survey variable in contingency table. We show that the proposed estimation procedure is useful to estimate the population cell count in this situation through an empirical study.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.471-476
• /
• 1993

In this paper we proposed the digital implementation of an $H^{\infty}$-optimal controller using lifting technique and $H^{\infty}$-control theory. The discrete controller is obtained through iterative adjustment of sampling time and weighting function, which can ber performed by computing the L$_{2}$-induced input to output norm of the sampled-data system with bandlimited exogenous input. The resulting sampled-data bandlimited exogenous input. The resulting sampled-data system is stable and the performance including inter-sampling behaviour of the hybrid system can be also optimized.d.

• 한국조사연구학회:학술대회논문집
• /
• 한국조사연구학회 2007년도 추계학술대회 발표논문집
• /
• pp.213-230
• /
• 2007

Although the response model has been frequently applied to nonresponse weighting adjustment or imputation, the estimation under callbacks has been relatively underdeveloped in the response model. The estimation method using the response probability is developed under callbacks. A replication method for the estimation of the variance of the proposed estimation is also developed. Since the true response probability is usually unknown, we study the estimation of the response probability. Finally, we propose an estimator under callbacks using the ratio imputation as well as the response probability. The simulation study illustrates our techniques.

• 보건행정학회지
• /
• 제9권1호
• /
• pp.156-177
• /
• 1999

The current method of rate adjustment for inflation is based on the evaluation of the financial performance of hospitals. The method has the disadvantage such as too complicated, expensive process as well as low reliability. This study, therefore, develops the 'Korean Medical Insurance Economic Index(MIEI)' as a new model for the rate adjustment with the use of the macro economic indices. In addition, we calculate the 1992∼1998 rate adjustment with the MIEI, and examines the validity of the MIEI by comparing with the conventional method. Medical costs are classified into nine categories : physician salaries, nurse·pharmacist·medical technician salaries, assistants & others salaries, material cost(by imports), material cost(by domestics), depreciation & rent paid(by imports), depreciation & rent paid(by domestics), power utilities, other administrative costs. Then the category weight which is the ratio of category in the total cost is calculated. Macro economic indices are selected for each cost category in order to reflect the concept of the each cost category and inflation during the year of 1992∼1998. Finally MIEI which integrate all category according to the category weight and selected macro indices is calculated. The mean of hospital MIEI which weighting by amount paid by insurers was cacluated. The result from the application of empirical data to the MIEI model is very similar to that of the current method. Furthermore, this method is very simple and also easy to get social consensus. This MIEI model can be replaced the current method based on the analysis of the financial performance for the adjustment of medical fees.

• 한국산학기술학회논문지
• /
• 제19권2호
• /
• pp.608-616
• /
• 2018

일반적으로 비선형 시스템은 1차와 2차 시스템의 곱의 형태로 선형화되며, 시스템의 근은 1차 시스템의 근과 2차 시스템의 중근, 서로 다른 두 실근, 복소근으로 구성된다. 그리고 LQ(Linear Quadratic) 제어는 성능지수함수를 최소화하는 제어법칙을 설계하는 방법으로 시스템의 안정성을 보장하는 장점과 가중행렬 조정으로 시스템의 근의 위치를 조정하는 극배치 기능이 있다. 가중행렬에 의해 LQ 제어는 시스템의 근의 위치를 임의로 이동시킬 수 있지만 시행착오 방법으로 가중행렬을 설정하는 어려움이 있다. 이것은 해밀토니안(Hamiltonian) 시스템의 특성방정식을 이용하여 해결 할 수 있다. 또한 제어가중행렬이 상수의 대칭행렬이면 제어법칙을 반복적으로 적용하여 시스템의 여러 근을 원하는 폐루프 근으로 이동시킬 수 있다. 이 논문은 해밀토니안 시스템의 특성방정식을 이용하여 조단 블록을 갖는 시스템의 중근을 두 실근으로 이동시키는 상태가중행렬과 제어법칙을 계산하는 방법을 제시한다. 삼각함수로 표현된 상태가중행렬로 해밀토니안 시스템의 특성방정식을 구한다. 그리고 이동된 두 실근이 특성방정식의 근이라는 조건에서 중근과 상태가중행렬의 관계식(${\rho},\;{\theta}$)을 유도한다. 상태가중행렬이 양의 반한정행렬이 될 조건에서 중근의 이동범위를 구한다. 그리하여 이동범위에서 선택한 두 실근을 관계식에 대입하여 상태가중행렬과 제어법칙을 계산한다. 제안한 방법을 간단한 3차 시스템의 예제에 적용해본다.

• Communications for Statistical Applications and Methods
• /
• 제17권1호
• /
• pp.55-66
• /
• 2010

본 연구에서는 2007년에 실시한 17대 대통령 선거를 위한 NI Korea의 인터넷 패널조사와 KBS의 대선 패널 전화여론조사 결과를 토대로 인터넷조사와 전화조사의 차이를 비교하고, 인터넷조사의 활용 가능성을 검토해 보고자 한다. 인터넷조사는 조사대상자가 인터넷 사용자로 제한됨에 따라 발생하는 포함오차와 조사 참여 의사를 갖는 사람들만을 조사에 참여시킴으로써 발생하는 선택편향 등으로 인해 흔히 표본의 대표성이 문제점으로 지적되고 있다. 이런 문제점을 해결하기 위해 인터넷 사용자 표본이 전체 유권자 표본을 설명 할 수 있도록 성향점수(Propensity score)를 사용하여 가중치를 보정하는 방안을 제시한다. 17대 대선 자료를 기초로 한 사례분석을 통해, 적절한 성향점수보정 기법을 적용하는 경우 인터넷조사를 선거예측에 활용하는것이 가능하다는 결론을 얻을 수 있었다.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.101-110
• /
• 2003

This paper introduces an identification method for nonlinear models in the form of rule-based Fuzzy-Neural Networks (FNN). In this study, the development of the rule-based fuzzy neural networks focuses on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The FNN modeling and identification environment realizes parameter identification through synergistic usage of clustering techniques, genetic optimization and a complex search method. We use a HCM (Hard C-Means) clustering algorithm to determine initial apexes of the membership functions of the information granules used in this fuzzy model. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are then adjusted using the identification algorithm of a GA hybrid scheme. The proposed GA hybrid scheme effectively combines the GA with the improved com-plex method to guarantee both global optimization and local convergence. An aggregate objective function (performance index) with a weighting factor is introduced to achieve a sound balance between approximation and generalization of the model. According to the selection and adjustment of the weighting factor of this objective function, we reveal how to design a model having sound approximation and generalization abilities. The proposed model is experimented with using several time series data (gas furnace, sewage treatment process, and NOx emission process data from gas turbine power plants).

• 패션비즈니스
• /
• 제20권3호
• /
• pp.119-132
• /
• 2016

Weighting of silk fabrics have long been practiced in silk fabric trading based on the primary consideration of price-weight, and secondary one of quality improvement in handle, luster, and drape properties. Recent trend of practicing weighting of silk fabrics is, however, focused on the improvement of the handle, luster, drape, and other properties. During the finishing processes of synthetic fiber, nylon, comprising amide structure, include the use of tannic acid, especially in the dyeing. A multitude of studies are being implemented in terms of improving fastness to washing, fastness to light of dyed nylon product, or the light fastness of nylon 6 itself. In this study, the effects of various tannic acid treatments on the physical properties related to the handle of nylon 6 and silk fabrics are examined and reviewed. The effects of treatment condition of the tannic acid, e.g., the concentration of the aqueous tannic acid solution, treatment time, and temperature were investigated. As the concentration of the aqueous solution of tannic acid increased, the bending rigidity values of the silk and nylon 6 fabrics increased. The treated fabrics felt stiff to the touch. Within the mild conditions of bending employed in the bending measurement of KES, nylon 6 treated fabric specimen exhibited a trend of improvement of bending resiliency within the range of small bending deformation. The weight of treated fabrics have all increased. The air-permeability values decreased as the treatment concentration increased. However, the decrease tendency of air permeability values may be alleviated by adjusting the fabric count during the tentering or expanding processes, either by tension adjustment or heat treatment. Optimum conditions of the treatment for nylon 6 are 1.25% tannic acid concentration, bath temperature of $85^{\circ}C$, pH 3.1, and those for silk fabric treatment are 1.25% tannic acid concentration, bath temperature of $85^{\circ}C$, pH 3.1. The treatment conditions will lead to the improvement in the properties of fabrics for summer.

• Journal of information and communication convergence engineering
• /
• 제20권1호
• /
• pp.22-30
• /
• 2022

The reinforcement learning algorithm has proven its potential in solving sequential decision-making problems under uncertainties, such as finding paths to route data packets in wireless sensor networks. With reinforcement learning, the computation of the optimum path requires careful definition of the so-called reward function, which is defined as a linear function that aggregates multiple objective functions into a single objective to compute a numerical value (reward) to be maximized. In a typical defined linear reward function, the multiple objectives to be optimized are integrated in the form of a weighted sum with fixed weighting factors for all learning agents. This study proposes a reinforcement learning -based routing protocol for wireless sensor network, where different learning agents prioritize different objective goals by assigning weighting factors to the aggregated objectives of the reward function. We assign appropriate weighting factors to the objectives in the reward function of a sensor node according to its hop-count distance to the sink node. We expect this approach to enhance the effectiveness of multi-objective reinforcement learning for wireless sensor networks with a balanced trade-off among competing parameters. Furthermore, we propose SDN (Software Defined Networks) architecture with multiple controllers for constant network monitoring to allow learning agents to adapt according to the dynamics of the network conditions. Simulation results show that our proposed scheme enhances the performance of wireless sensor network under varied conditions, such as the node density and traffic intensity, with a good trade-off among competing performance metrics.