• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.210-213
• /
• 1999

Anyone observes that information processing in animal brains is depended on neural networks. On the other hand, engineering models for the neural networks are well known now, and they have been studied, and learning facility is found in the model. We are sure there is a potential in order to create a non Neuman-machine in the engineering models. We studied iteration forms including the engineering neural network models, taking a first step for the creation.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.725-730
• /
• 1994

A sodium chloride crystallizer shows oscillatory and nonlinear characteristics under its nucleating and growing process. Because these characteristics vary with operational condition, we can't control the product crystal size exactly with a PID controller or a sequence controller. Then, we make a model with threefold neural networks for the laboratory equipment that is a jet mixing crystallizer. We try to control the product crystal size with its neuro-model, and we reach the conclusion that our neuro-model is applicable to the practical crystallizer.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.313-316
• /
• 2004

Model selection is the process that sets up the regularization parameter in the support vector machine or regularization network by using the external methods such as general cross validation or L-curve criterion. This paper suggests that the regularization parameter can be obtained simultaneously within the learning process of neural networks without resort to separate selection methods. In this paper, extended kernel method is introduced. The relationship between regularization parameter and the bias term in the extended kernel is established. Experimental results show the effectiveness of the new model selection method.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.369-378
• /
• 2006

This Study focuses on the binary forecast of occurrence of heavy snow in Honam area based on the MOS(model output statistic) method. For our study daily amount of snow cover at 17 stations during the cold season (November to March) in 2001 to 2005 and Corresponding 45 RDAPS outputs are used. Logistic regression model and neural networks are applied to predict the probability of occurrence of Heavy snow. Based on the distribution of estimated probabilities, optimal thresholds are determined via true shill score. According to the results of comparison the logistic regression model is recommended.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.658-668
• /
• 2020

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to end-device service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

• Nuclear Engineering and Technology
• /
• v.51 no.3
• /
• pp.723-730
• /
• 2019

Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.314-324
• /
• 2020

Due to the nonlinearity and environmental uncertainties, the design of the ship's steering controller is a long-term challenge. The purpose of this study is to design an intelligent autopilot based on Extended Kalman Filter (EKF) trained Radial Basis Function Neural Network (RBFNN) control algorithm. The newly developed free running model scaled surface vessel was employed to execute the motion control experiments. After describing the design of the EKF trained RBFNN autopilot, the performances of the proposed control system were investigated by conducting experiments using the physical model on lake and simulations using the corresponding mathematical model. The results demonstrate that the developed control system is feasible to be used for the ship's motion control in the presences of environmental disturbances. Moreover, in comparison with the Back-Propagation (BP) neural networks and Proportional-Derivative (PD) based control methods, the EKF RBFNN based control method shows better performance regarding course keeping and trajectory tracking.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.1 no.1
• /
• pp.82-91
• /
• 1998

This paper presents a neural networks based approach for the problem of sensor failure detection and accommodation for ship without physical redundancy in the sensors. The designed model consists of two neural networks. The first neural network is responsible for the failure detection and the second neural network is responsible for the failure identification and accommodation. On the yaw rate sensor of ship, simulation results indicates that the proposed method can be useful as failure detector and sensor estimator.

• Journal of the Korean Geographical Society
• /
• v.46 no.3
• /
• pp.319-330
• /
• 2011

In this study, a soil moisture estimation model was proposed using the ground observation data of soil moisture, precipitation, surface temperature, MODIS NDVI and artificial neural networks. The model was calibrated and verified on the Yongdam dam watershed which has reliable ground soil moisture networks. The test statistics of calibration sites, Jucheon, Bugui, Sangjeon, showed that the correlation coefficients between observations and estimations are about 0.9353 and RMSE is about 1.4957%. Also that of the verification site, Cheoncheon2, showed that the correlation coefficient is about 0.8215 and RMSE is about 4.2077%. The soil moisture estimation model was applied to estimate the spatial distribution of soil moisture in the Yongdam dam watershed and results showed improved spatial soil moisture distribution since the model used satellite information of NDVI and artificial neural networks which can represent the nonlinear relationships between data well. The model should be useful to estimate wide range soil moisture information.

• Asian Journal of Atmospheric Environment
• /
• v.10 no.2
• /
• pp.67-79
• /
• 2016

The forecasting of air pollution is an important and popular topic in environmental engineering. Due to health impacts caused by unacceptable particulate matter (PM) levels, it has become one of the greatest concerns in metropolitan cities like Karaj City in Iran. In this study, the concentration of $PM_{2.5}$ was predicted by applying a multilayer percepteron (MLP) neural network, a radial basis function (RBF) neural network and a Markov chain model. Two months of hourly data including temperature, NO, $NO_2$, $NO_x$, CO, $SO_2$ and $PM_{10}$ were used as inputs to the artificial neural networks. From 1,488 data, 1,300 of data was used to train the models and the rest of the data were applied to test the models. The results of using artificial neural networks indicated that the models performed well in predicting $PM_{2.5}$ concentrations. The application of a Markov chain described the probable occurrences of unhealthy hours. The MLP neural network with two hidden layers including 19 neurons in the first layer and 16 neurons in the second layer provided the best results. The coefficient of determination ($R^2$), Index of Agreement (IA) and Efficiency (E) between the observed and the predicted data using an MLP neural network were 0.92, 0.93 and 0.981, respectively. In the MLP neural network, the MBE was 0.0546 which indicates the adequacy of the model. In the RBF neural network, increasing the number of neurons to 1,488 caused the RMSE to decline from 7.88 to 0.00 and caused $R^2$ to reach 0.93. In the Markov chain model the absolute error was 0.014 which indicated an acceptable accuracy and precision. We concluded the probability of occurrence state duration and transition of $PM_{2.5}$ pollution is predictable using a Markov chain method.