• KIEE International Transaction on Systems and Control
• /
• v.12D no.1
• /
• pp.43-50
• /
• 2002

In the recent years neural networks have fulfilled the promise of providing model-free learning controllers for nonlinear systems; however, it is very difficult to guarantee the stability and robustness of neural network control systems. This paper proposes an adaptive neural network control for robot manipulators based on the radial basis function netwo.k (RBFN). The RBFN is a branch of the neural networks and is mathematically tractable. So we adopt the RBFN to approximate nonlinear robot dynamics. The RBFN generates control input signals based on the Lyapunov stability that is often used in the conventional control schemes. The saturation function is also chosen as an auxiliary controller to guarantee the stability and robustness of the control system under the external disturbances and modeling uncertainties.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1386-1388
• /
• 1996

In this paper, a recurrent neural network using polynomial is proposed for electric load forecasting. Since the proposed algorithm is based on the bilinear polynomial, it can model nonlinear systems with much more parsimony than the higher order neural networks based on the Volterra series. The proposed Bilinear Recurrent Neural Network(BLRNN) is compared with Multilayer Perceptron Type Neural Network(MLPNN) for electric load forecasting problems. The results show that the BLRNN is robust and outperforms the MLPNN in terms of forecasting accuracy.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1422-1423
• /
• 2007

This study deals with various neural network algorithms for the on-site partial discharge pattern recognition. For the purpose, the pattern recognition has been carried out on partial discharge data for the typical artificial defect using 9 different neural network models. In order to enhance on-site applicability, artificial defects were installed in the insulation joint box of extra-high voltage xLPE cables and partial discharges were measured by use of the metal foil sensor and a HFCT as a sensor. As the result, it is found out that the accuracy of pattern recognition could be enhanced through the application of the Sigmoid function, the Momentum algorithm and the Genetic algorism on the artificial neural networks. Although Multilayer Perceptron (MLP) algorism showed the best result among 9 neural network algorisms, it is thought that more researches on others would be needed in consideration of on-site application.

• Proceedings of the KIEE Conference
• /
• 1995.07a
• /
• pp.39-41
• /
• 1995

The inherent performance of Ultrasonic Motor(USM) which is on of highlighted a directly-driven positioning servo motor/actuator. In this paper, the speed of control USM based on neural network control. The neural network control can roughly be classified as the direct control and indirect control schemes. An indirect control scheme is adopted for Ultrasonic Motor speed control. A back propagation algorithm is used to train neural network controller. The Simulation results show that this neural network control system can provide good dynamical responses.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2001.05a
• /
• pp.243-248
• /
• 2001

The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Thus, in this paper, an Evolving Neural Network Controller(ENNC) without Error Back Propagation(EBP) is presented. An ENNC is described simply by genetic representation using an encoding strategy for types and slope values of each active functions, biases, weights and so on. By an evolutionary programming which has three genetic operation; selection, crossover and mutation, the predetermine controller is optimally evolved by updating simultaneously the connection patterns and weights of the neural networks. The performances of the proposed ENNC(PENNC) are compared with the ones of conventional optimal controller and the conventional evolving neural network controller(CENNC) through the simulation and experimental results. And we showed that the finally optimized PENNC was very useful in the stabilization control of an IP system.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4060-4066
• /
• 2021

Flow-accelerated corrosion (FAC) of carbon steel piping is a significant problem in nuclear power plants. The basic process of FAC is currently understood relatively well; however, the accuracy of prediction models of the wall-thinning rate under an FAC environment is not reliable. Herein, we propose a methodology to construct pipe wall-thinning rate prediction models using artificial neural networks and a convolutional neural network, which is confined to a straight pipe without geometric changes. Furthermore, a methodology to generate training data is proposed to efficiently train the neural network for the development of a machine learning-based FAC prediction model. Consequently, it is concluded that machine learning can be used to construct pipe wall thinning rate prediction models and optimize the number of training datasets for training the machine learning algorithm. The proposed methodology can be applied to efficiently generate a large dataset from an FAC test to develop a wall thinning rate prediction model for a real situation.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.9
• /
• pp.138-148
• /
• 1996

In moving structures such as robots and feeders of production lines, vibrations may not be ignored. Recently it becomes a big problem to control the vibration in a motion because moving structures are in higher speed, larger size and lighter weight. In this study a nonlinear system was model- led and identified by using neural networks and the vibration in motions was controlled actively by using a neural network controller. To investigate vilidity of this method, an experimental apparatus was made and tested. The model was composed of a DC servomotor, a carrier and a flexible plate. Its motion was measured by a gap sensor and an encoder. Trapezoidal, cycloid and trapecloid type trajectories were used in this exper- riment. Computer simulations and experiments weredone for each trajectory.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.1614-1615
• /
• 2011

It is difficult to differentially diagnose between lung cancer and benign inflammatory lung lesion due to high false positive rate on F-18 FDG-PET. We investigated whether application of artificial neural network to this diagnosis may be helpful. We reviewed the medical records and F-18 FDG PET images of 12 patients, selecting clinical and PET variables such as SUV. For selected variables and confirm, multilayer neural perceptron was applied in crossvalidation method and compared to visual interpretation. Neural network correctly classified the lung lesions in 83%, and reduced greately the false positive rate. However, false negative rate was not influenced. Application of neural network to the differential diagnosis between lung cancer and benigh inflammatory lesion may be helpful. Further studies with more patients are warranted.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.365-373
• /
• 1999

Recently, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as a model construction process. Irrespective of the efficiency of a learning procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network models. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables for neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.