• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권1호
• /
• pp.40-49
• /
• 2004

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN), discuss a comprehensive design methodology and carry out a series of numeric experiments. The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized network, and to be much more flexible and preferable neural network than the conventional SOPNN. In order to generate the structurally optimized SOPNN, GA-based design procedure at each stage (layer) of SOPNN leads to the selection of preferred nodes (or PNs) with optimal parameters- such as the number of input variables, input variables, and the order of the polynomial-available within SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. A detailed design procedure is discussed in detail. To evaluate the performance of the GA-based SOPNN, the model is experimented with using two time series data (gas furnace and NOx emission process data of gas turbine power plant). A comparative analysis shows that the proposed GA-based SOPNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1659-1663
• /
• 1991

A new control design methodology is presented here which is based on a nonlinear time-series reference model. It is indicated by highly nonlinear simulations that such designs successfully stabilize troublesome aircraft maneuvers undergoing large changes in angle of attack as well as large electric power transients due to line faults. In both applications, the nonlinear controller was significantly better than the corresponding linear adaptive controller. For the electric power network, a flexible a.c. transmission system (FACTS) with series capacitor power feedback control is studied. A bilinear auto-regressive moving average (BARMA) reference model is identified from system data and the feedback control manipulated according to a desired reference state. The control is optimized according to a predictive one-step quadratic performance index (J). A similar algorithm is derived for control of rapid changes in aircraft angle of attack over a normally unstable flight regime. In the latter case, however, a generalization of a bilinear time-series model reference includes quadratic and cubic terms in angle of attack. These applications are typical of the numerous plants for which nonlinear adaptive control has the potential to provide significant performance improvements. For aircraft control, significant maneuverability gains can provide safer transportation under large windshear disturbances as well as tactical advantages. For FACTS, there is the potential for significant increase in admissible electric power transmission over available transmission lines along with energy conservation. Electric power systems are inherently nonlinear for significant transient variations from synchronism such as may result for large fault disturbances. In such cases, traditional linear controllers may not stabilize the swing (in rotor angle) without inefficient energy wasting strategies to shed loads, etc. Fortunately, the advent of power electronics (e.g., high-speed thyristors) admits the possibility of adaptive control by means of FACTS. Line admittance manipulation seems to be an effective means to achieve stabilization and high efficiency for such FACTS. This results in parametric (or multiplicative) control of a highly nonlinear plant.

• International Journal of Concrete Structures and Materials
• /
• 제9권2호
• /
• pp.159-172
• /
• 2015

Estimation of the residual strength of corroded reinforced concrete beams has been studied from experimental and theoretical perspectives. The former is arduous as it involves casting beams of various sizes, which are then subjected to various degrees of corrosion damage. The latter are static; hence cannot be generalized as new coefficients need to be re-generated for new cases. This calls for dynamic models that are adaptive to new cases and offer efficient generalization capability. Computational intelligence techniques have been applied in Construction Engineering modeling problems. However, these techniques have not been adequately applied to the problem addressed in this paper. This study extends the empirical model proposed by Azad et al. (Mag Concr Res 62(6):405-414, 2010), which considered all the adverse effects of corrosion on steel. We proposed four artificial neural networks (ANN) models to predict the residual flexural strength of corroded RC beams using the same data from Azad et al. (2010). We employed two modes of prediction: through the correction factor ($C_f$) and through the residual strength ($M_{res}$). For each mode, we studied the effect of fixed and random data stratification on the performance of the models. The results of the ANN models were found to be in good agreement with experimental values. When compared with the results of Azad et al. (2010), the ANN model with randomized data stratification gave a $C_f$-based prediction with up to 49 % improvement in correlation coefficient and 92 % error reduction. This confirms the reliability of ANN over the empirical models.

• 응용통계연구
• /
• 제33권4호
• /
• pp.421-437
• /
• 2020

본 논문은 최근에 널리 사용되고 있는 R 프로그램으로 출산율, 사망률, 국제이동률을 예측하고 이들 결과를 Leslie 행렬에 대입해 인구추계 산출하는 방법을 소개한다. 특히 Kaneko (2003)가 제안한 출산율의 일반화로그감마모형, Li 등 (2013)의 사망률 LC-ER 모형, Ramsay와 Silverman (2005)가 제안한 국제이동률의 함수적데이터모형을 시현할 수 있도록 하였다. 최근 R로 구현된 대표적인 인구추계 패키지로 demography, bayesPop가 소개되고 있으나, 이는 Human Mortality Database (HMD), Human Fertility Database (HFD)에 업로드된 자료에 한에서만 분석이 가능하고 기타 데이터를 적용하기 위해서는 자료 변경과 수정이 요구된다. 특히 우리나라의 경우 HMD에 단기 간의 자료로만 제공되어 있어 이 패키기를 적용하기에는 한계점이 있다. 이에 본 논문은 이런 실정과 한국의 저출산, 고령화, 내국인, 외국인 국제이동률 상이패턴을 반영할 수 있는 R 프로그램을 소개하고, 2117년까지의 인구추계를 도출하였다.

• 대한수학교육학회지:학교수학
• /
• 제15권4호
• /
• pp.785-799
• /
• 2013

본 연구는 수학적 모델링 수업이 수학 영재 학생들에게 문제해결의 기회를 제공하고 수학적 모델링 활동을 통해 다양한 수학적 사고력을 발전시킬 수 있다는 가정 하에 중학교 3학년 수학 영재 학생들을 위한 수학적 모델링 교수 학습 자료를 개발하였다. 개발된 교수 학습 자료를 적용하여 사례연구를 통해 수학적 모델링의 단계별 활동과정을 살펴보고 각 단계에서 어떠한 수학적 사고능력이 나타나는지 분석하였다. 수학적 모델링 과정에서 다양한 수학적 사고능력이 나타났는데 문제를 이해하는 실세계 탐구과정에서는 정보의 조직화 능력이, 상황모델을 개발하는 과정에서는 직관적 통찰능력, 공간화/시각화 능력, 수학적 추론 능력, 반성적 사고 능력이 나타났다. 수학모델 개발과정에서는 수학적 추상화 능력, 공간화/시각화 능력, 수학적 추론 능력, 반성적 사고가 나타났으며 모델적용 과정에서는 일반화 및 적용 능력과 반성적 사고가 나타났다. 모델링 수업이 진행됨에 따라 반성적 사고능력이 더 많이 나타나는 것을 확인할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제4권2호
• /
• pp.1-7
• /
• 1999

WWW은 기존의 인터넷이 단순 문자 자료 중심의 데이타 교환을 멀티미디어화 하기 위한 프로토콜이며, 자료들을 하이퍼텍스트 형태로 저장함으로써 초보자들도 쉽게 원하는 자료를 찾고, 접근할 수 있도록 되어있다. 이러한 WWW의 멀티미디어 데이타의 검색 및 접근의 용이성은 음란물 데이타가 보편화, 멀티미디어화 되는데 결정적인 역활을 하였으며, 음란물의 상업화를 가능케 하는 사회적 문제를 야기하였다. 한편, 이러한 문제를 해결하기 위해 음란물을 제공하는 사이트를 효율적으로 차단하기 연구가 활발하게 진행되고 있다. 본 논문에서는 이러한 음란물을 제공하는 사이트를 효율적으로 검색하여, 미성년자의 음란성 사이트접근을 차단하기 위한 기법을 제시하고 이를 구현하였다. 제안된 기법은 링크를 기반으로 정보 검색 기능을 수행하며, 가장 정확한 결과를 보여 주는 것으로 알려진 확률 모델과 비교한 결과 제안된 모델(Link-Based Model)이 확률 모델보다 평균 재현율과 정확율에서 12%와 8% 성능이 우수하였다. 특히 텍스트 이외의 데이타와 적은 링크를 가진 문서들을 검색하는데 크게 효율성이 향상되었다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권1호
• /
• pp.94-99
• /
• 2015

비모수 베이스 통계학, 확률적 표집에 기반한 추론 등이 기계학습의 주요 패러다임으로 등장하면서 디리슐레(Dirichlet) 분포는 최근 다양한 그래프 모형 곳곳에 등장하고 있다. 디리슐레 분포는 일변수 감마 분포를 벡터 분포로 확장한 형태의 하나이다. 본 논문에서는 감마 분포를 갖는 임의의 자연수 X를 K개의 자연수의 합으로 임의 분할 할 때 각 부분의 크기 비율을 디리슐레 분포에서 표집하는 방법을 제안한다. 일반적으로 디리슐레 분포는 연속적인 (K-1)-단체(simplex) 위에 정의 되지만 자연수로 분할하는 표본은 자연수라는 조건 때문에 단체 내부의 이산 그리드 점에만 정의된다. 본 논문에서는 단체 위의 그리드 상의 이웃 점들의 확률 분포로부터 마르코프연쇄 몬테 칼로(MCMC) 제안 분포를 정의하고 일련의 표본들의 마르코프 연쇄를 구현하는 알고리듬을 제안한다. 본 방법은 마르코프 모델, HMM 및 준-HMM 등에서 각 상태별 시간 지속 분포를 표현하는데 활용 가능하다. 나아가 최근 제안된 전역-지역(global-local) 상태지속 분포를 동시에 모형화하는 감마-디리슐레 HMM에도 응용가능하다.

• International Journal of Control, Automation, and Systems
• /
• 제2권4호
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• International Journal of Concrete Structures and Materials
• /
• 제11권1호
• /
• pp.135-149
• /
• 2017

The prediction of the actual ultimate capacity of confined concrete columns requires partial confinement utilization under eccentric loading. This is attributed to the reduction in compression zone compared to columns under pure axial compression. Modern codes and standards are introducing the need to perform extreme event analysis under static loads. There has been a number of studies that focused on the analysis and testing of concentric columns. On the other hand, the augmentation of compressive strength due to partial confinement has not been treated before. The higher eccentricity causes smaller confined concrete region in compression yielding smaller increase in strength of concrete. Accordingly, the ultimate eccentric confined strength is gradually reduced from the fully confined value $f_{cc}$ (at zero eccentricity) to the unconfined value $f^{\prime}_c$ (at infinite eccentricity) as a function of the ratio of compression area to total area of each eccentricity. This approach is used to implement an adaptive Mander model for analyzing eccentrically loaded columns. Generalization of the 3D moment of area approach is implemented based on proportional loading, fiber model and the secant stiffness approach, in an incremental-iterative numerical procedure to achieve the equilibrium path of $P-{\varepsilon}$ and $M-{\varphi}$ response up to failure. This numerical analysis is adapted to assess the confining effect in rectangular columns confined with conventional lateral steel. This analysis is validated against experimental data found in the literature showing good correlation to the partial confinement model while rendering the full confinement treatment unsafe.

• 전기학회논문지
• /
• 제58권2호
• /
• pp.399-406
• /
• 2009

In this study, Polynomial Radial Basis Function Neural Network(pRBFNN) based on Fuzzy Inference System is designed and its parameters such as learning rate, momentum coefficient, and distributed weight (width of RBF) are optimized by means of Particle Swarm Optimization. The proposed model can be expressed as three functional module that consists of condition part, conclusion part, and inference part in the viewpoint of fuzzy rule formed in 'If-then'. In the condition part of pRBFNN as a fuzzy rule, input space is partitioned by defining kernel functions (RBFs). Here, the structure of kernel functions, namely, RBF is generated from HCM clustering algorithm. We use Gaussian type and Inverse multiquadratic type as a RBF. Besides these types of RBF, Conic RBF is also proposed and used as a kernel function. Also, in order to reflect the characteristic of dataset when partitioning input space, we consider the width of RBF defined by standard deviation of dataset. In the conclusion part, the connection weights of pRBFNN are represented as a polynomial which is the extended structure of the general RBF neural network with constant as a connection weights. Finally, the output of model is decided by the fuzzy inference of the inference part of pRBFNN. In order to evaluate the proposed model, nonlinear function with 2 inputs, waster water dataset and gas furnace time series dataset are used and the results of pRBFNN are compared with some previous models. Approximation as well as generalization abilities are discussed with these results.