• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1730-1731
• /
• 2007

In this paper, we present a direct adaptive control method using neural networks for the control of nonlinear systems. The weights of neural networks are trained by an adaptive backpropagation algorithm based on Lyapunov stability theory. We develop the parameter update-laws using the neural network input and the error between the desired output and the output of nonlinear plant to update the weights of a neural network in the sense that Lyapunove stability theory. Beside the output tracking error is asymptotically converged to zero.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2001.05a
• /
• pp.45-51
• /
• 2001

The daily inflow is apparently one of nonlinear and complicated phenomena. The nonlinear and complexity make it difficult to model the prediction of daily flow, but attractive to try the neural networks approach which contains inherently nonlinear schemes. The study focuses on developing the forecasting models of daily inflows to a large dam site using neural networks. In order to reduce the error caused by high or low outliers, the back propagation algorithm which is one of neural network structures is modified by combining a regression algorithm. The study indicates that continuous forecasting of a reservoir inflow in real time is possible through the use of modified neural network models. The positive effect of the modification using tole regression scheme in BP algorithm is showed in the low and high ends of inflows.

• Journal of the Korean Society of Mechanical Technology
• /
• v.20 no.6
• /
• pp.872-878
• /
• 2018

Steam tables including superheated, saturated and compressed region were simultaneously modeled using the neural networks. Pressure and temperature were used as two inputs for superheated and compressed region. On the other hand Pressure and dryness fraction were two inputs for saturated region. The outputs were specific volume, specific enthalpy and specific entropy. The neural network model were compared with the linear interpolation model in terms of the percentage relative errors. The criterion of judgement was selected with the percentage relative error of 1%. In conclusion the neural networks showed better results than the interpolation method for all data of superheated and compressed region and specific volume of saturated region, but similar for specific enthalpy and entropy of saturated region.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.316-319
• /
• 2014

People's interests in coffee are increasing with the expansion of coffee market. In this trend, people's taste becomes more luxurious and coffee bean's quality is considered to be very important. Currently, bean defects are mainly detected by experienced specialists. In this paper, a detection system of bean defects using machine learning is presented. This system concentrates on detecting two main defect types : bean's shape and insect damage. Convolutional Neural Networks are used for machine learning. The neural networks are comprised of two neural networks. The first neural network detects defects in the bean's shape, and the second one detects the bean's insect damage. The development of this system could be a starting point for automated coffee bean defects detection. Later, further research is needed to detect other bean defect types.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1669-1679
• /
• 1996

In this paper, we address the problem of how to replace huffers in multimedia database systems with time-varying skewed data access. The access pattern in the multimedia database system to support audio-on-demand and video-on-demand services is generally skewed with a few popular objects. In addition the access pattem of the skewed objects has a time-varying property. In such situations, our analysis indicates that conventional LRU(least Recently Used) and LFU(Least Frequently Used) schemes for buffer replacement algorithm(ABRN:Adaptive Buffer Replacement using Neural suited. We propose a new buffer replacement algorithm(ABRN:Adaptive Buffer Replacement using Neural Networks)using a neural network for multimedia database systems with time-varying skewed data access. The major role of our neural network classifies multimedia objects into two classes:a hot set frequently accessed with great popularity and a cold set randomly accessed with low populsrity. For the classification, the inter-arrival time values of sample objects are employed to train the neural network.Our algorithm partitions buffers into two regions to combine the best roperties of LRU and LFU.One region, which contains the 핫셋 objects, is managed by LFU replacement and the other region , which contains the cold set objects , is managed by LRUreplacement.We performed simulation experiments in an actual environment with time-varying skewed data accsee to compare our algorithm to LRU, LFU, and LRU-k which is a variation of LRU. Simulation resuults indicate that our proposed algorthm provides better performance as compared to the other algorithms. Good performance of the neural network-based replacement scheme means that this new approach can be also suited as an alternative to the existing page replacement and prefetching algorithms in virtual memory systems.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Environmental Engineering Research
• /
• v.21 no.4
• /
• pp.333-340
• /
• 2016

An Artificial Neural Network including a Radial Basis Function (RBF) and a Time Delay Neural Network (TDNN) was used to predict total dissolved solid (TDS) in the river Zayanderud. Water quality parameters in the river for ten years, 2001-2010, were prepared from data monitored by the Isfahan Regional Water Authority. A factor analysis was applied to select the inputs of water quality parameters, which obtained total hardness, bicarbonate, chloride and calcium. Input data to the neural networks were pH, $Na^+$, $Mg^{2+}$, Carbonate ($CO{_3}^{-2}$), $HCO{_3}^{-1}$, $Cl^-$, $Ca^{2+}$ and Total hardness. For learning process 5-fold cross validation were applied. In the best situation, the TDNN contained 2 hidden layers of 15 neurons in each of the layers and the RBF had one hidden layer with 100 neurons. The Mean Squared Error and the Mean Bias Error for the TDNN during the training process were 0.0006 and 0.0603 and for the RBF neural network the mentioned errors were 0.0001 and 0.0006, respectively. In the RBF, the coefficient of determination ($R^2$) and the index of agreement (IA) between the observed data and predicted data were 0.997 and 0.999, respectively. In the TDNN, the $R^2$ and the IA between the actual and predicted data were 0.957 and 0.985, respectively. The results of sensitivity illustrated that $Ca^{2+}$ and $SO{_4}^{2-}$ parameters had the highest effect on the TDS prediction.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.8
• /
• pp.33-39
• /
• 2005

The maximum output torque and power developed by the machine is ultimately depended on the allowable inverter current rating and maximum voltage which the inverter can supply to the machine. Therefore, considering the limited voltage and current capacities, it is desirable to consider a control method which yields the best possible torque per ampere. In this paper, we propose fuzzy neural network(FNN) controller that combines a fuzzy control and the neural network for high performance control of induction motor drive. This controller composes antecedence of the fuzzy rules and consequence by a clustering method and a multi-layer neural networks. This controller is compounding of advantages that robust control of a fuzzy control and high-adaptive control of the neural networks. Also, this paper is proposed control of maximum torque per ampere(MTPA) of induction moor. This strategy is reposed which is simple in structure and has the honest goal of minimizing the stator current magnitude for given load torque. The performance of the proposed induction motor drive with maximum torque control using FNN controller is verified by analysis results at dynamic operation conditions.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.371-380
• /
• 2022

Convolutional neural networks are widely used to manipulate data arranged in a grid, such as images. A general convolutional neural network consists of a convolutional layers and a fully connected layers, and each layer contains a nonlinear activation functions. This paper proposes a combined parametric activation function to improve the performance of convolutional neural networks. The combined parametric activation function is created by adding the parametric activation functions to which parameters that convert the scale and location of the activation function are applied. Various nonlinear intervals can be created according to parameters that convert multiple scales and locations, and parameters can be learned in the direction of minimizing the loss function calculated by the given input data. As a result of testing the performance of the convolutional neural network using the combined parametric activation function on the MNIST, Fashion MNIST, CIFAR10 and CIFAR100 classification problems, it was confirmed that it had better performance than other activation functions.