• 대한산업공학회지
• /
• 제24권1호
• /
• pp.23-35
• /
• 1998

This article presents a network flow analysis to form flexible machine cells with minimum intercellular part moves and a neural network model to form part families. The operational sequences and production quantity of the part, and the number of cells and the cell size are taken into considerations for a 0-1 quadratic programming formulation and a network flow based solution procedure is developed. After designing the machine cells, a neural network approach for the integration of part families and the automatic assignment of new parts to the existing cells is proposed. A multi-layer backpropagation network with one hidden layer is used. Experimental results with varying number of neurons in hidden layer to evaluate the role of hidden neurons in the network learning performance are also presented. The comprehensive methodology developed in this article is appropriate for solving large-scale industrial applications without building the knowledge-based expert rule for the cellular manufacturing environment.

• 대한산업공학회지
• /
• 제23권2호
• /
• pp.371-383
• /
• 1997

This paper propose a fuzzy regression method using fuzzy neural networks when a membership value is attached to each input-output pair. First, a method of linear fuzzy regression analysis is described by interpreting the reliability of each input-output pair as its membership values. Next, an architecture of fuzzy neural networks with fuzzy weights and fuzzy biases is shown. The fuzzy neural network maps a crisp input vector to a fuzzy output. A cost function is defined using the fuzzy output from the fuzzy neural network and the corresponding target output with a membership value. A learning algorithm is derived from the cost function. The derived learning algorithm trains the fuzzy neural network so that the level set of the fuzzy output includes the target output. Last, the proposed method is illustrated by computer simulations on numerical examples.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권5호
• /
• pp.289-294
• /
• 2002

다층신경회로망 구조의 재구성은 회로망의 일반화 능력이나 효율성의 관점에서 중요한 문제로 연구되어왔다. 본 논문에서는 신경회로망에 학습된 은닉 지식들을 추출하여 조합함으로써 신경회로망의 구조를 재구성하는 새로운 방법을 제안한다. 먼저, 각 노드별로 학습된 대표적인 지역 규칙을 추출하여 각 노드의 불필요한 연결구조들을 제거한 후, 이들의 논리적인 조합을 통하여 중복 또는 상충되는 노드와 연결구조를 제거한다. 이렇게 학습된 지식을 분석하여 노드와 연결구조를 재구성한 신경회로망은 처음의 신경회로망에 비하여 월등히 감소된 구조 복잡도를 가지며 일반적으로 더 우수한 일반화 능력을 가지게 됨을 실험결과로서 제시하였다.

• International Journal of Precision Engineering and Manufacturing
• /
• 제4권2호
• /
• pp.49-56
• /
• 2003

As semi-solid forging (SSF) is compared with conventional casting such as gravity die-casting and squeeze casting, the product without inner defects can be obtained from semi-solid forming and globular microstructure as well. Generally, SSF consists of reheating, forging, and ejecting processes. In the reheating process, the materials are heated up to the temperature between the solidus and liquidus line at which the materials exists in the form of liquid-solid mixture. The process variables such as reheating time, reheating temperature, reheating holding time, and induction heating power has large effect on the quality of the reheated billets. It is difficult to consider all the variables at the same time for predicting the quality. In this paper, Taguchi method, regression analysis and neural network were applied to analyze the relationship between processing conditions and solid fraction. A356 alloy was used for the present study, and the learning data were extracted from the reheating experiments. Results by neural network were in good agreement with those by experiment. Polynominal regression analysis was formulated using the test data from neural network. Optimum processing condition was calculated to minimize the grain size and solid fraction standard deviation or to maximize the specimen temperature average. Discussion is given about reheating process of row material and results are presented with regard to accurate process variables fur proper solid fraction, specimen temperature and grain size.

• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.1060-1071
• /
• 2014

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.524-532
• /
• 2015

All data created in BigData times is included potentially meaning and correlation in data. A variety of data during a day in all society sectors has become created and stored. Research areas in analysis and grasp meaning between data is proceeding briskly. Especially, accuracy of meaning prediction and data imbalance problem between data for analysis is part in course of something important in data analysis field. In this paper, we proposed data prediction model based on data weights and neural network using R for meaning analysis between data. Proposed data prediction model is composed of classification model and analysis model. Classification model is working as weights application of normal distribution and optimum independent variable selection of multiple regression analysis. Analysis model role is increased prediction accuracy of output variable through neural network. Performance evaluation result, we were confirmed superiority of prediction model so that performance of result prediction through primitive data was measured 87.475% by proposed data prediction model.

• 대한기계학회논문집A
• /
• 제33권8호
• /
• pp.753-759
• /
• 2009

Feed-forward neural networks have been widely used as function approximation tools in the context of global approximate optimization. In the present study, a wavelet neural network (WNN) which is based on wavelet transform theory is suggested as an alternative to a traditional back-propagation neural network (BPN). The basic theory of wavelet neural network is briefly described, and approximation performance is tested using a nonlinear multimodal function and a composite rotor blade analysis problem. Laplacian of Gaussian function, Mexican function, and Morlet function are considered during the construction of WNN architectures. In addition, approximation results from WNN are compared with those from BPN.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.224-228
• /
• 2000

In this paper, the kinematics of the new type of parallel manipulator is studied, and neural network is applied to solve the forward kinematics problem. The parallel manipulator, called a Stewart platform, has an easy and unique solution about the inverse kinematics, however the forward kinematics is difficult to get the solution because of the lack of an efficient algorithm due to its highly nonlinearity. This paper proposes the neural network scheme as an alternative Newton-Raphson method. The neural network is found to improve its accuracy by adjusting the offset of the result obtained.

• 한국경영과학회지
• /
• 제38권1호
• /
• pp.139-152
• /
• 2013

The purpose of this study is to claim the validity of tuning the architecture of neural network models for multi-class classification. A neural network model for multi-class classification is basically constructed by building a series of neural network models for binary classification. Building a neural network model, we are required to set the values of parameters such as number of hidden nodes and weight decay parameter in advance, which draws special attention as the performance of the model can be quite different by the values of the parameters. For better performance of the model, it is absolutely necessary to have a prior process of tuning the parameters every time the neural network model is built. Nonetheless, previous studies have not mentioned the necessity of the tuning process or proved its validity. In this study, we claim that we should tune the parameters every time we build the neural network model for multi-class classification. Through empirical analysis using wine data, we show that the performance of the model with the tuned parameters is superior to those of untuned models.

• Advances in environmental research
• /
• 제4권4호
• /
• pp.219-231
• /
• 2015

In recent years, raising air pollutants has become as a big concern, especially in metropolitan cities such as Tehran. Therefore, forecasting the level of pollutants plays a significant role in air quality management. One of the forecasting tools that can be used is an artificial neural network which is able to model the complicated process of air pollution. In this study, we applied two different methods of artificial neural networks, the Multilayer Perceptron (MLP) and Radial Basis Function (RBF), to predict the hourly air concentrations of toluene in Tehran. Hourly temperature, wind speed, humidity and $NO_x$ were selected as inputs. Both methods had acceptable results; however, the RBF neural network produced better results. The coefficient of determination ($R^2$) between the observed and predicted data was 0.9642 and 0.99 for MLP and RBF neural networks, respectively. The results of the mean bias errors (MBE) were 0.00 and -0.014 for RBF and MLP, respectively which indicate the adequacy of the models. The index of agreement (IA) between the observed and predicted data was 0.999 and 0.994 in the RBF and the MLP, respectively which indicates the efficiency of the models. Finally, sensitivity analysis related to the MLP neural network determined that temperature was the most significant factor in air concentration of toluene in Tehran which may be due to the volatile nature of toluene.