• Journal of the Korean Society for Railway
• /
• v.12 no.1
• /
• pp.45-54
• /
• 2009

TETRA(Terrestrial Trunked Radio) is the standard of D-TRS(Digital Trunked Radio System) developed by the ETSI(European Telecommunications Standards Institute). Currently, TETRA has been selected as Electric Power IT Wireless Backbone Network. Traditional distribution automation system has used the wireless network of Mobile Service Provider using CDMA(Code-Division Multiple Access) and WCDMA(Wideband CDMA) modem. Therefore, the development of gateway platform is indispensable according to the change to TETRA network. In this paper, we propose an embedded Linux-based Gateway platform for transmitting Industrial Electric Power IT protocol using TETRA network.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.459-460
• /
• 2001

In this paper, we analyze algorithms for diagnosing of VEP(visual evoked potential) signal. We used wavelet transform for the preprocessing of VEP signal data and back propagation neural network for the pattern recognition. We used several wavelets to study their effects and efficiency in the preprocessing of VEP. The diagnosis system led to good results. We obtained the noise reduced and compressed signal with the wavelet transform of the training VEP signal. So it is possible to train the neural network faster and exact diagnosis processing is possible in the neural network. From the experimental results, we know that the discrimination ability of the neural network is changed by the type of basis vector and the proposed system is good to the diagnosis of VEP.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.414-415
• /
• 2008

In this paper, we consider the development methodology of wireless monitoring system for a distribution transformer. The master/ slave devices are installed in the power distribution feeder and measure the current state of pole or ground transformers. After measuring, the devices send the measurement data to operating room through the wireless network such as RF and CDMA so that the power distribution supervisor can prevent a distribution transformer damaging caused by overloads and imbalance of loads.

• 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.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.164-165
• /
• 1999

• Proceedings of the Korea Electromagnetic Engineering Society Conference
• /
• 2002.11a
• /
• pp.366-369
• /
• 2002

Two artificial neural networks (ANN) are used to model the electric coupling probe in the combline resonators. One is used to analyze and synthesize the electric probe, and the other is used to correct errors between the results of the analysis and the synthesis ANNs and the fabrication results. The ANNs for the analysis and the synthesis of the electric probe are trained using the physical dimensions of the electric probe and the corresponding coupling bandwidth which is obtained using the finite element method. The ANNs for the error correction are trained using a very small set of the measurement results. Once trained, the ANN models provide the correct result approaching the accuracy of the measurement. The results from the ANN models show fairly good agreement with those of the measurement and they can be used as good initial design values.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.813-816
• /
• 1995

The shape and width of fuzzy membership function has an effect on performance of fuzzy controller. In this paper, neuro-fuzzy controller is proposed to improve the control performance of fuzzy controller. It has membership function, that is adapt to plant constant by using trained neural network. This neural network has been trained with back propagation algorithm. To show the effectiveness of proposed neuro-fuzzy controller with adaptive membership function, it is applied to plant (dead time + 1st order) with various plant constant.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.147-148
• /
• 2008

현재의 자동차 전제제어 시스템에서 적용하고 있는 On-board Diagnostic system(OBD)-ll의 Diagnostic Control Network를 구성하고 있는 Keyword2000과 CAN프로토콜을 통합하여 한 시스템이 구현하고, 이에 따른 통합된 서비스를 제공하는 OBD 시스템 개발내용을 소개한다.

• Bulletin of the Korean Chemical Society
• /
• v.27 no.8
• /
• pp.1145-1148
• /
• 2006

Excitability is one of the basic and fundamental mechanisms utilized for signal transmission in living organisms. With reference to the condition by Marek and the condition by Schneider, we found a condition in which excitability with similar shapes can appear by chemical and electric perturbation. Our condition is constructed with 3 chemical channels and 1 electric channel, and can be used as a condition for a chemical spiking neuron and as a unit of a chemical spiking neural network.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2000.04a
• /
• pp.71-74
• /
• 2000

The equi-potential lines designed in the electric field are introduced to find the preform shape in axisymmetric hot forging. The equi-potential lines generated between two conductors of different voltages show similar trends of the minimum work paths between the undeformed shape and the deformed shape. Base on this similarity the equi-potential lines obtained by arrangement of the initial and final shapes are utilized for the design of preform and then the artificial neural network is used to find the range of initial volume and potential value of the electric field.