• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• pp.191-194
• /
• 2001

The ozone forecasting systems have many problems because the mechanism of the ozone concentration is highly complex, nonlinear, and nonstationary. Also, the results of prediction are not a good performance so far, especially in the high-level ozone concentration. This paper describes the modeling method of the ozone prediction system using neuro-fuzzy approaches and fuzzy clustering. The dynamic polynomial neural network (DPNN) based upon a typical algorithm of GMDH (group method of data handling) is a useful method for data analysis, identification of nonlinear complex system, and prediction of a dynamical system.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.52-58
• /
• 2005

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 B
• /
• pp.827-829
• /
• 1999

The identification of nonlinear system using Extended GMDH(EGMDH) is studied in this paper. The proposed EGMDH algorithm is based on GMDH(Group Method of Data handling) method and its structure is similar to Neural Networks. The each node of EGMDH structure utilizes several types of high-order polynomial such as linear, quadratic and cubic, and is connected as various kinds of multi-variable inputs. As the operating condition changes, the parameters of EGMDH will also change, so the proposed scheme by means of the EGMDH method is capable of adapting rapidly to the changing environment. The simulation result shows that the simple nonlinear process can be modeled reasonably well by the proposed method which are simple but efficient.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1995년도 추계학술대회발표논문집; 서울대학교, 서울; 30 Sep. 1995
• /
• pp.387-395
• /
• 1995

롤(Roll)의 주물 가공 시스템의 성능(Performance)분석의 문제는 일반적으로 관련된 많은 요인들 때문에 매우 복잡하다. 롤 제조 시스템의 성능과 관련된 주요 요인으로서 주형(Moulding) 제작, 원재료의 용해, 후처리 및 가공 공정 의 요인들을 들 수 있다. 본 연구에서는 이러한 복잡한 롤의 주물 및 가공공 정상의 요인들로부터 롤 제조 시스템의 불량률을 평가하기 위하여 발견적인 방법인 GMDH(Group Method Data Handling)-Type 모델링 방법을 이용하 였다. 롤 주물 가공 시스템의 성능을 불량률로 두고 이에 주요 영향 요인들 의 입력 Data를 위하여 현장 자료로부터 상하한 값을 구하여, Hyper-Cube 프로그램을 이용하여 필요한 수의 Data를 보완하여 사용하였다. 시스템 성능 과 관련된 인자들을 2개식 가능한 조합을 하고 이들 각각의 조합들에 대하 여 6개항으로 된 예측식으로 회귀분석하고 일정 수준 이상의 결과들만을 다 음 단계의 자료로 사용하였다. GMDH 방법은 매 단계마다 영향이 적은 변 수조합을 제외시키므로 최종 해는 그 정확성이 매우 높다. 본 연구를 위하여 GMDH 알고리즘에 따라 계산할수 있는 전산 프로그램을 개발하여 사용하였 으며, 적용예를 롤 주물제조공정에 응용하여 보였다.. 분석된 자료에 의하면 예측 오차가 매우 적음을 보였다.

• 한국지능시스템학회논문지
• /
• 제11권4호
• /
• pp.336-339
• /
• 2001

오존농도 메커니즘은 매우 복잡하고, 비선형성과 비정상성이 강하기 때문에 오존 예보시스템들은 많은 문제점을 가지고 있다. 특히 고농도 오존에 있어서 예측결과들이 성능이 좋지 않다. 본 논문은 뉴로-퍼지기법과 퍼지 클러스터링을 이용한 오존 예측시스템의 모델링 방법을 설명하고자 한다. GMDH의 전형적인 알고리즘에 기초한 동적 다항식 신경망은 데이터 분석, 비선형적이고 복잡한 시스템의 검증 그리고 동적 시스템의 예측을 위한 유용한 방법이다.

• Computers and Concrete
• /
• 제22권2호
• /
• pp.197-207
• /
• 2018

In the present study, group method of data handling networks (GMDH) are adopted and evaluated for shear strength prediction of both FRP-reinforced concrete members with and without stirrups. Input parameters considered for the GMDH are altogether 12 influential geometrical and mechanical parameters. Two available and very recently collected comprehensive datasets containing 112 and 175 data samples are used to develop new models for two cases with and without shear reinforcement, respectively. The proposed GMDH models are compared with several codes of practice. An artificial neural network (ANN) model and an ANFIS based model are also developed using the same databases to further assessment of GMDH. The accuracy of the developed models is evaluated by statistical error parameters. The results show that the GMDH outperforms other models and successfully can be used as a practical and effective tool for shear strength prediction of members without stirrups ($R^2=0.94$) and with stirrups ($R^2=0.95$). Furthermore, the relative importance and influence of input parameters in the prediction of shear capacity of reinforced concrete members are evaluated through parametric and sensitivity analyses.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.149-151
• /
• 2005

In this paper, we propose the Optimal Polynomial Neural Networks(PNN) for nonlinear process. The PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. Medical Imaging System(MIS) data is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
• /
• pp.791-793
• /
• 2000

The fuzzy inference system is a popular computing framework based on the concepts of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. The advantage of fuzzy approach over traditional ones lies on the fact that fuzzy system does not require a detail mathematical description of the system while modeling. As modeling method. the Group Method of Data Handling(GMDH) is introduced by A.G. Ivakhnenko GMDH is an analysis technique for identifying nonlinear relationships between system's inputs and output. We study a Novel Neuro-Fuzzy Network (NNFN) in this paper. NNFN is a network resulting from the combination of a fuzzy inference system and polynomial neural network(PNN) (7) which is advanced structure of GMDH. Simulation involve a series of synthetic as well as experimental data used across various neurofuzzy systems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 정기총회 및 추계학술대회 논문집 학회본부
• /
• pp.326-328
• /
• 1993

Modelling theory, based on differential equations, is not an adequate tool for solving the problems of complex system. Identification of complex system using GMDH(group method of data handling) is more appropriate for this problems. In this paper, GMDH algorithm is used to identify the nonlinear plant and to design model following nonlinear control system. Simulation for the DC motor show the good performance of model following nonlinear control system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.12-14
• /
• 2005

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) by means of genetically optimized fuzzy polynomial neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms(GAs). The conventional SOFPNNs hinges on an extended Group Method of Data Handling(GMDH) and exploits a fixed fuzzy inference type in each FPN of the SOFPNN as well as considers a fixed number of input nodes located in each layer. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, a collection of the specific subset of input variables, and the number of membership function) and addresses specific aspects of parametric optimization. Therefore, the proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series).