• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.487-496
• /
• 2000

In this paper, the Multi-FNN(Fuzzy-Neural Networks) model is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNN is based on Yamakawa's FNN and uses simplified inference as fuzzy inference method and error back propagation algorithm as learning rules. We use a HCM clustering and Genetic Algorithms(GAs) to identify both the structure and the parameters of a Multi-FNN model. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNN according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. A aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. The aggregate performance index stands for an aggregate objective function with a weighting factor to consider a mutual balance and dependency between approximation and predictive abilities. According to the selection and adjustment of a weighting factor of this aggregate abjective function which depends on the number of data and a certain degree of nonlinearity, we show that it is available and effective to design an optimal Multi-FNN model. To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.456-464
• /
• 1997

We describe a random prcess model that prvides sets of patterms whth prcisely contrlolled within-class varia-bility and between-class distinctions.We used these pattems in a simulation study wity the back-propagation netwoek to chracterize its perfotmance as we varied the process-controlling parameters,the statistical differences between the processes,and the random noise on the patterns.Our results indicated that grneralized statistical difference between the processes genrating the patterns provided a good predictor of the difficulty of the clssi-fication problem. Also we analyzed the performance of the Bayes classifier whith the maximum-likeihood cri-terion and we compared the performance of the neural network to that of the Bayes classifier.We found that the performance of neural network was intermediate between that of the simulated and theoretical Bayes classifier.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.1
• /
• pp.68-76
• /
• 2018

Target prioritization is necessary for a multifunction radar(MFR) to track an important target and manage the resources of the radar platform efficiently. In this paper, we consider an artificial neural network(ANN) model that calculates the priority of the target. Furthermore, we propose a neural network learning algorithm based on the steepest descent method, which is more suitable for target prioritization by combining the conventional gradient descent method. Several simulation results show that the proposed scheme is much more superior to the traditional neural network model from analyzing the training data accuracy and the output priority relevance of the test scenarios.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.181-189
• /
• 2013

In this paper, we introduce the fuzzy neural network based on the individual input space to design the pattern recognizer. The proposed networks configure the network by individually dividing each input space. The premise part of the networks is independently composed of the fuzzy partition of individual input spaces and the consequence part of the networks is represented by polynomial functions. The learning of fuzzy neural networks is realized by adjusting connection weights of the neurons in the consequent part of the fuzzy rules and it follows a back-propagation algorithm. In addition, in order to optimize the parameters of the proposed network, we use real-coded genetic algorithms. Finally, we design the optimized pattern recognizer using the experimental data for pattern recognition.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.3
• /
• pp.53-61
• /
• 2006

This paper is proposed adaptive fuzzy-neuro controller for high performance of induction motor drive. The design of this algorithm based on fuzzy-neural network controller that is implemented using fuzzy control and neural network. This controller uses fuzzy nile as training patterns of a neural network. Also, this controller uses the back-propagation method to adjust the weights between the neurons of neural network in order to minimize the error between the command output and actual output. A model reference adaptive scheme is proposed in which the adaptation mechanism is executed by fuzzy logic based on the error and change of error measured between the motor speed and output of a reference model. The control performance of the adaptive fuzzy-neuro controller is evaluated by analysis for various operating conditions. The results of experiment prove that the proposed control system has strong high performance and robustness to parameter variation, and steady-state accuracy and transient response.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.184-196
• /
• 2021

This paper proposes statistics adaptive linear regression-based object size prediction method for object detection. YOLOv2 and YOLOv3, which are typical deep learning-based object detection algorithms, designed the last layer of a network using statistics adaptive exponential regression model to predict the size of objects. However, an exponential regression model can propagate a high derivative of a loss function into all parameters in a network because of the property of an exponential function. We propose statistics adaptive linear regression layer to ease the gradient exploding problem of the exponential regression model. The proposed statistics adaptive linear regression model is used in the last layer of the network to predict the size of objects with statistics estimated from training dataset. We newly designed the network based on the YOLOv3tiny and it shows the higher performance compared to YOLOv3 tiny on the UFPR-ALPR dataset.

• Journal of Korea Water Resources Association
• /
• v.33 no.2
• /
• pp.247-262
• /
• 2000

In this paper, the WSANN(Water Stage Analysis with Neural Network) model was presented so as to predict flood water stage at Jindong which has been the major stream gauging station in Nakdong river basin. The WSANN model used the improved backpropagation training algorithm which was complemented by the momentum method, improvement of initial condition and adaptive-learning rate and the data which were used for this study were classified into training and testing data sets. An empirical equation was derived to determine optimal hidden layer node between the hidden layer node and threshold iteration number. And, the calibration of the WSANN model was performed by the four training data sets. As a result of calibration, the WSANN22 and WSANN32 model were selected for the optimal models which would be used for model verification. The model verification was carried out so as to evaluate model fitness with the two-untrained testing data sets. And, flood water stages were reasonably predicted through the results of statistical analysis. As results of this study, further research activities are needed for the construction of a real-time warning of the impending flood and for the control of flood water stage with neural network method in river basin. basin.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.349-356
• /
• 2005

Artificial Organism-used application areas are expanding at a break-neck speed with a view to getting things done in a dynamic and Informal environment. A use of general programming or traditional hi methods as the representation of Artificial Organism behavior knowledge in these areas can cause problems related to frequent modifications and bad response in an unpredictable situation. Strategies aimed at solving these problems in a machine-learning fashion includes Genetic Programming and Evolving Neural Networks. But the learning method of Artificial-Organism is not good yet, and can't represent life in the environment. With this in mind, this research is designed to come up with a new behavior evolution model. The model represents behavior knowledge with Classification Rules and Enhanced Backpropation Neural Networks and discriminate the denomination. To evaluate the model, the researcher applied it to problems with the competition of Artificial-Organism in the Simulator and compared with other system. The survey shows that the model prevails in terms of the speed and Qualify of learning. The model is characterized by the simultaneous learning of classification rules and neural networks represented on chromosomes with the help of Genetic Algorithm and the consolidation of learning ability caused by the hybrid processing of the classification rules and Enhanced Backpropagation Neural Network.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.179-183
• /
• 2009

본 연구에서는 GCM 기후변화 전망 시나리오를 이용하여 유역단위의 기후변화를 추정하였다. 원시 GCM 시나리오를 지역화 시키기 위해서 인공신경망 모형을 사용하였다. GCM에서 모의되는 강수플럭스, 해면기압, 지표면 근처에서의 일 평균온도, 지표면으로부터 발생하는 잠열플럭스 등과 같은 22개의 변수는 인공신경망의 잠재적 예측인자로 사용되었으며, AWS에서 관측된 강수량과 온도는 예측변수로 사용되었다. 원시 GCM 데이터는 CCCma(Canadian Centre for Climate Modeling and Analysis)에서 제공되는 CGCM3.1/T63 20C3M 시나리오를 사용하였으며, 인공신경망 학습과정에서 사용된 기준시나리오(reference scenario)자료의 기간은 1997년부터 2000년까지의 데이터를 사용하였다. 인공신경망을 학습을 통하여 결정된 각 층사이의 가중치를 이용하여 이산화탄소 배출농도를 가정하여 생성된 CGCM3.1/T63 SRES B1 기후변화시나리오(project scenario)를 인공신경망의 입력값으로 하여 미래의 기온과 강수변화를 전망하였다. 신경망의 학습효과를 높이기 위하여 기온과 강수에 대한 평균 및 누적기간을 각각 일단위와 월단위로 설정하였다. 본 연구에서 사용된 인공신경망은 3층 퍼셉트론(다층 퍼셉트론)을 사용하였으며, 학습방법으로는 역전파알고리즘(back-propagation algorithm)을 이용하였다. 민감도분석을 통하여 선택된 예측인자는 소양강댐유역(1011, 1012소유역)에서의 인공신경망 예측인자로 활용되었으며, 2001년부터 2100년까지의 일 평균온도와 일 강수량의 변화경향을 추정하였다. 1011유역, 1012유역에서는 여름철의 온도변화경향이 겨울철에 비하여 높게 나타났다. 일 평균온도의 통계분석 결과 평균예측오차가 가장 적게 나타나는 지역은 1001유역으로 -0.08로 평균예측오차가 가장 적게 나타났으며, 인공신경망기법을 이용하여 스케일 상세화된 일 평균온도와 관측된 일 평균온도가 얼마나 잘 일치하는지를 확인할 수 있는 1012유역에서 CORR이 0.74로 가장 높게 나타났다.