• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.2
• /
• pp.1059-1065
• /
• 2014

Wind turbine system can obtain the maximum wind energy using torque control under the rated wind speed, and wind turbine power is controlled as the rated power using pitch control over the rated wind speed. In this paper, we present a method for wind turbine pitch controller using neural networks. The purpose of the pitch control is to control generator speed and power in the above rated wind speed. To improve the neural network pitch controller, the difference between a rated and current speed of generator has been used for another input of neural networks as well as wind speed. Error back-propagation algorithm is used for training the neural network pitch controller and simulation and Matlab/Simulink is used for verifying that this system is controlled well.

• Proceedings of the KSME Conference
• /
• 2001.11a
• /
• pp.821-826
• /
• 2001

Out of all metal-cutting processes, the hole-making process is the most widely used. It is estimated to be more than 30% of the total metal-cutting process. It is therefore desirable to monitor and detect drill wear during the hole-drilling process. One important aspect in controlling the drilling process is monitoring drill wear status. Accordingly, this paper deals with Basic system and Online system. Basic system comprised of spindle rotational speed, feed rates, thrust, torque and flank wear measured tool microscope. Online system comprised of spindle rotational speed, feed rates, AE signal, flank wear area measured computer vision. On-line monitoring system does not need to stop the process to inspect drill wear. Backpropagation neural networks (BPNs) were used for on-line detection of drill wear. This paper deals with an on-line drill wear monitoring system to fit the detection of the abnormal tool state.

• Journal of Advanced Navigation Technology
• /
• v.13 no.6
• /
• pp.901-906
• /
• 2009

This paper proposes a call admission control(CAC) method for wireless networks, which is based on the upper bound of a possibility distribution of handoff calls dropping rates. The possibility distribution is estimated in a fuzzy inference and a learning algorithm in neural network. The learning algorithm is considered for tuning the membership functions(then parts)of fuzzy rules for the inference. The fuzzy inference method is based on a weighted average of fuzzy sets. The proposed method can avoid estimating excessively large handoff calls dropping rates, and makes possibile self-compensation in real time for the case where the estimated values are smaller than real values. So this method makes secure CAC, thereby guaranteeing the allowed CDR. From simulation studies we show that the estimation performance for the upper bound of call dropping rate is good, and then handoff call dropping rates in CAC are able to be sustained below user's desired value.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.784-787
• /
• 2006

In this paper, we propose a method for nonlinear grapheme segmentation in Korean printed character type classification. The characters are subdivided into six types based on character type information. The feature vector is consist of mesh features, vertical projection features and horizontal projection features which are extracted from gray-level images. We classify characters into 6 types using Back propagation. Character segmentation regions are determined based on character type information. Then, an optimal nonlinear grapheme segmentation path is found using multi-stage graph search algorithm. As the result, a proposed methodology is proper to classify character type and to find nonlinear char segmentation paths.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.380-384
• /
• 2007

MLP(Multi-Layer Perceptron)를 이용한 학습은 간단한 구조에도 비선형 분류가 가능하다는 장점을 가지고 있다. 하지만 오류역전파 알고리즘을 사용함으로써 시간의 소모가 크고 원치 않는 결과값으로의 수렴가능성을 배제할 수 없다는 단점을 가지고 있다. 이는 초기설정의 의존도가 높기 때문에 발생하는 문제들로 좋은 결과값에 근접한 곳으로 초기화가 이루어지면 좋은 학습 성능을 보이지만 반대로 좋은 결과값으로부터 멀리 떨어진 곳으로 신경망의 초기화가 이루어지면 학습 성능이 현저히 낮아지는 현상을 보인다. 본 논문에서는 MLP 전체의 층을 대상으로 하는 본 학습이 이루어지기 전에 RBM(Restricted Boltzmann Machine)을 이용, 층간 선행학습을 행하고 그 결과로 얻어지는 가중치와 바이어스를 본 MLP 학습의 초기화 데이터로 사용하는 개선 MLP 학습 알고리즘을 제안한다. 이 방법을 사용함으로써 MLP 학습 속도향상은 물론 원치 않는 지역해로의 수렴까지 방지할 수 있어 전체적인 학습 성능향상이 가능하게 된다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.471-476
• /
• 2010

In this paper, we propose an effective method that recognizes the vehicle license plate using RGB color information and back-propagation neural network algorithm. First, the image of the vehicle license plate is adjusted by the Mean of Blue values in the vehicle plate and two candidate areas of Red and Green region are classified by calculating the differences of pixel values and the final Green area is searched by back-propagation algorithm. Second, our method detects the area of the vehicle plate using the frequence of the horizontal and the vertical histogram. Finally, each of codes are detected by an edge detection algorithm and are recognized by error back-propagation algorithm. In order to evaluate the performance of our proposed extraction and recognition method, we have run experiments on a new car plates. Experimental results showed that the proposed license plate extraction is better than that of existing HSI information model and the overall recognition was effective.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6B
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.8
• /
• pp.67-75
• /
• 2004

The landslide is one of the most significant natural disasters, which cause a lot of loss of human lives and properties. The landslides in natural slopes generally occur by complicated problems such as soil properties, topography, and geology. Artificial Neural Network (ANN) model is efficient computing technique that is widely used to solve complicated problems in many research fields. In this paper, the ANN model with application of error back propagation method was proposed for estimation of landslide hazard in natural slope. This model can evaluate the possibility of landslide hazard with two different approaches: one considering only soil properties; the other considering soil properties, topography, and geology. In order to evaluate reasonably the landslide hazard, the SlideEval (Ver, 1.0) program was developed using the ANN model. The evaluation of slope stability using the ANN model shows a high accuracy. Especially, the prediction of landslides using the ANN model gives more stable and accurate results in the case of considering such factors as soil, topographic and geological properties together. As a result of comparison with the statistical analysis(Korea Institute of Geosciences and Mineral Resources, 2003), the analysis using the ANN model is approximately equal to the statistical analysis. Therefore, the SlideEval (Ver. 1.0) program using ANN model can predict landslides hazard and estimate the slope stability.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.1021-1024
• /
• 2001

Out of all metal-cutting processes, the hole-making process is the most widely used. It is estimated to be more than 30% of the total metal-cutting process. It is therefore desirable to monitor and detect drill wear during the hole-drilling process. In this paper, the vision system of the sensing methods of drill flank wear on the basis of image processing is used to detect the wear pattern by non-contact and direct method and get the reliable wear information about drill. In image processing of acquired image, median filter is applied for noise removal. The vision flank wear area of the drill was measured. Backpropagation neural networks (BPns) were used for no-line detection of drill wear. The neural network consisted of three layers: input, hidden and output. The input vectors comprised of spindle rotational speed, feed rates, vision flank wear, thrust and torque signals. The output was the drill wear state which was either usable or failure. Drilling experiments with various spindle rotational speed and feed rates were carried out. The learning process was peformed effectively by utilizing backpropagation. The detection of the abnormal states using BPNs achieved 96.4% reliability even when the spindle rotational speed and feedrate were changed.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.