• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.215-220
• /
• 1998

In order to optimize fuzzy model, we use the optimal algorithm with a hybrid type in the identification of premise parameters and standard least square method in the identification of consequence parameters of a fuzzy model. The hybrid optimal identification algorithm is carried out using a genetic algorithm and improved complex method. Also, the performance index with weighting factor is proposed to achieve a balance between the insults of performance for the training and testing data. Several numerical examples are used to evaluate the performance of the proposed model.

• 한국지능시스템학회논문지
• /
• 제9권5호
• /
• pp.555-565
• /
• 1999

복잡하고 비선형적인 시스템의 규칙베이스 퍼지모델링을 위하여 퍼지시스템의 최적 동정알고리즘을 연구한다. 비선형 시스템은 퍼지모델의 입력변수와 퍼지 입력공간 분할에 의한 구조동정과 파라미터 동정을 통해 표현된다. 본 논문에서 규칙베이스 퍼지모델링은 비선형 시스템을 위해 퍼지추론방법과 두 종류의 최적화 이론의 결합에 의한 하이브리드 구졸를 이용하여 시스템 구조와 파라미터동정을 수행한다. 퍼지모델의 추론방법은 간략추론 및 선형추론에 의한다. 제안된 하이브리드 최적 동정 알고리즘은 유전자 알고리즘과 개선된 콤플렉스 방법을 이용한다. 여기서 유전자 알고리즘은 전반부 퍼지규칙의 멤버쉽함수의 초기 파라미터들을 결정하기 위해 사용되고 강력한 자동동조 알고리즘인 개선된 콤플렉스 방법은 정교한 파라미터들을 얻기 위해 수행된다. 따라서 최적 퍼지모델을 위해 전반부 파라미터 동정에는 하이브리드형의 최적 알고리즘을 이용하고 후반부 동정에는 최소자승법을 이용한다. 또한 학습과 테스트 데이터에 의해 생성된 퍼지모델의 성능결과 사이의 상호균형을 얻기 위해 하중계수를 가지는 합성 성능지수를 제안한다. 제안된 모델의 성능평가를 위해 두가지 수치적 예를이용한다.

• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.1292-1298
• /
• 2017

In this paper, we represent a nonlinear identification of electronic brake pedal behavior in the brake-by-wire (BBW) system based on hybrid group method of data handling (GMDH) and genetic algorithm (GA). A GMDH is a kind of multi-layer network with a structure that is determined through training and which can express nonlinear dynamics as a mathematical model. The GA is used in the GMDH, enabling each neuron to search for its optimal set of connections with the preceding layer. The results obtained with this hybrid approach were compared with different nonlinear system identification methods. The experimental results showed that the hybrid approach performs better than the other methods in terms of root mean square error (RMSE) and correlation coefficients. The hybrid GMDH/GA approach was effective for modeling and predicting the brake pedal system under random braking conditions.

• Structural Engineering and Mechanics
• /
• 제65권6호
• /
• pp.707-719
• /
• 2018

In this article, a new method is introduced to improve the local search capability of meta-heuristic algorithms using the projection of the path on the border of constraints. In a mathematical point of view, the Gradient Projection Method is applied through a new approach, while the imposed limitations are removed. Accordingly, the gradient vector is replaced with a new meta-heuristic based vector. Besides, the active constraint identification algorithm, and the projection method are changed into less complex approaches. As a result, if a constraint is violated by an agent, a new path will be suggested to correct the direction of the agent's movement. The presented procedure includes three main steps: (1) the identification of the active constraint, (2) the neighboring point determination, and (3) the new direction and step length. Moreover, this method can be applied to some meta-heuristic algorithms. It increases the chance of convergence in the final phase of the search process, especially when the number of the violations of the constraints increases. The method is applied jointly with the authors' newly developed meta-heuristic algorithm, entitled Star Graph. The capability of the resulted hybrid method is examined using the optimal design of truss and frame structures. Eventually, the comparison of the results with other meta-heuristics of the literature shows that the hybrid method is successful in the global as well as local search.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1293-1302
• /
• 1999

In this paper, an on-line process scheme is presented for implementation of a intelligent on-line modeling of nonlinear complex system. The proposed on-line process scheme is composed of FNN-based model algorithm and PLC-based simulator, Here, an adaptive fuzzy-neural networks and HCM(Hard C-Means) clustering method are used as an intelligent identification algorithm for on-line modeling. The adaptive fuzzy-neural networks consists of two distinct modifiable sturctures such as the premise and the consequence part. The parameters of two structures are adapted by a combined hybrid learning algorithm of gradient decent method and least square method. Also we design an interface S/W between PLC(Proguammable Logic Controller) and main PC computer, and construct a monitoring and control simulator for real process system. Accordingly the on-line identification algorithm and interface S/W are used to obtain the on-line FNN model structure and to accomplish the on-line modeling. And using some I/O data gathered partly in the field(plant), computer simulation is carried out to evaluate the performance of FNN model structure generated by the on-line identification algorithm. This simulation results show that the proposed technique can produce the optimal fuzzy model with higher accuracy and feasibility than other works achieved previously.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2314-2316
• /
• 2000

In the construction of successful fuzzy models and/or controllers for nonlinear systems, identification of a good fuzzy Neural inference system is an important yet difficult problem, which is traditionally accomplished by trial and error process. In this paper, we propose a systematic identification procedure for complex multi-input single- output nonlinear systems with DNA coding method.DNA coding method is optimization algorithm based on biological DNA as are conventional genetic algothms (GAs). We also propose a new coding method for applying the DNA coding method to the identification of fuzzy Neural models. To acquire optimal TS fuzzy model with higher accuracy and economical size, we use the DNA coding method to optimize the parameters and the number of fuzzy inference system.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.261-273
• /
• 2022

Over the last decade, the scientific community has been actively developing technologies for automated software bug fixes called Automated Program Repair (APR). Several APR techniques have recently been proposed to effectively address multiple classroom programming errors. However, little attention has been paid to the advances in effective APR techniques for software bugs that are widely occurring during the software life cycle maintenance phase. To further enhance the concept of software testing and debugging, we recommend an optimized automated software repair approach based on hybrid technology (OAPR-HOML'1). The first contribution of the proposed OAPR-HOML'1 technique is to introduce an improved grasshopper optimization (IGO) algorithm for fault location identification in the given test projects. Then, we illustrate an opposition learning based artificial neural network (OL-ANN) technique to select AST node-level transformation schemas to create the sketches which provide automated program repair for those faulty projects. Finally, the OAPR-HOML'1 is evaluated using Defects4J benchmark and the performance is compared with the modern technologies number of bugs fixed, accuracy, precession, recall and F-measure.

• Geomechanics and Engineering
• /
• 제15권6호
• /
• pp.1207-1217
• /
• 2018

Geomechanics parameters are critical to numerical simulation, stability analysis, design and construction of geotechnical engineering. Due to the limitations of laboratory and in situ experiments, back analysis is widely used in geomechancis and geotechnical engineering. In this study, a hybrid back analysis method, that coupling numerical simulation, response surface (RS) and relevance vector machine (RVM), was proposed and applied to identify geomechanics parameters from hydraulic fracturing. RVM was adapted to approximate complex functional relationships between geomechanics parameters and borehole pressure through coupling with response surface method and numerical method. Artificial bee colony (ABC) algorithm was used to search the geomechanics parameters as optimal method in back analysis. The proposed method was verified by a numerical example. Based on the geomechanics parameters identified by hybrid back analysis, the computed borehole pressure agreed closely with the monitored borehole pressure. It showed that RVM presented well the relationship between geomechanics parameters and borehole pressure, and the proposed method can characterized the geomechanics parameters reasonably. Further, the parameters of hybrid back analysis were analyzed and discussed. It showed that the hybrid back analysis is feasible, effective, robust and has a good global searching performance. The proposed method provides a significant way to identify geomechanics parameters from hydraulic fracturing.