• Proceedings of the KSR Conference
• /
• 2004.06a
• /
• pp.1342-1346
• /
• 2004

Recently, the load increasement and regenerative system of electrified railway system make a difficult to distinguish between the load current and fault current and it need a new intelligent protection system. The failure of traction system cause collapse of the other systems from high tension current. The over current from abnormal situation produces high tension current flow, high temperature are, voltage instability and current cutting, and break down railway systems. Protective system of traction system playa role of which detect and isolate failure points. In this paper, we proposed intelligent algorithm for discriminating normal and abnormal situation instead of the system being operated abnormally.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1944-1947
• /
• 2003

In this paper, we propose a dynamic-based compression system by creating mosaic background and transmitting the change information. A dynamic mosaic of the background is progressively integrated in a single image using the camera motion information. For the camera motion estimation, we calculate affine motion parameters for each frame sequentially with respect to its previous frame. The camera motion is robustly estimated on the background by discriminating between background and foreground regions. The modified block-based motion estimation is used to separate the back-ground region.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• Proceedings of the KIEE Conference
• /
• 1993.07b
• /
• pp.566-568
• /
• 1993

A measuring technique for the fast transient high voltage is under development by use of laser source in order to substitute for the conventional measuring system which could bring about several technical inconveniences. At this moment, this work is aimed to construct a compact measuring system with the use of Pockels cell and specially designed voltage divider. This system is likely to enable us to measure the lightening impulse voltages at the level of 30kV, 50kV and 70kV. Throughout this work, qualified measuring devices are required to be developed for discriminating different kinds of noise from which the system should be protected.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.13 no.5
• /
• pp.30-34
• /
• 1976

A system that can discriminate monosyliables automatically from sequential input of Korean character's data without space codes is proposed. Korean characters are synthesized by two to seven elements out of twenty four basic elements. Three thousands Korean characters are formalized into thirty character forms discriminates monosyllable automatically by detecting seven form features and character length. In this result, this system, compared with the input method with space codes which have been used to separate each syllable, can save about 25% of the memory capacity of computer and improves about 30% of the processing speed of Korean characters.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2362-2367
• /
• 2005

This paper reports a technique for discriminating double talk and echo path change using the stochastic characteristics of power change for an adaptive noise canceller. The causes of rapid error increasing are double talk and echo path change. When the echo path is changed, the system corrects the impulse response in order to reduce the error. However, in the case of double talk, the system has to suspend the updating impulse response in order to maintain the quality of the voice signal. In the conventional system, it was difficult to discriminate between the two situations. In this research, the stochastic characteristics of the voice power change in the double talk period were experimentally verified to be different from the power change during echo path changing. Based on the results, a new double talk detection method is proposed.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.11a
• /
• pp.9-14
• /
• 2003

The major reason that spatial data warehousing has attracted a great deal of attention in business GIS in recent years is due to the wide availability of huge amounts of spatial data and the imminent need for turning such data into useful geographic information. Therefore, this research has been focused on designing and implementing the pilot tested system for spatial decision making. The purpose of the system is to predict targeted marketing area by discriminating the customers by using both transaction quantity and the number of customer using credit card in department store. Focused on the analysis methodology, the case study is aiming to use GIS and clustering for knowledge discovery. The system is a key section of the research of multi-dimensional and spatio-temporal analysis in the internet environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.405-405
• /
• 2000

We designed the artificial olfactory sensing system (Electronic Nose) using MOS type sensor array fur recognizing and analyzing odour. The response of individual sensors of sensor array, each processing a slightly different response towards the sample volatiles, can provide enough information to discriminate between sample odours. In this paper, we applied clustering algorithm for dimension reduction, such as linear projection mapping (PCA method), nonlinear mapping (Sammon mapping method) and the combination of PCA and Sammon mapping having a better discriminating ability. The odours used are VOC (Volatile chemical compound) and Toxic gases.

• Journal of Sensor Science and Technology
• /
• v.13 no.3
• /
• pp.199-206
• /
• 2004

Epileptic seizures result from a temporary electrical disturbance of the brain. In this paper, a method of discriminating EEG for diagnoses of temporal lobe epilepsy is proposed. The proposed method for classification of epilepsy and sleep EEG is based on the wavelet transform and the fuzzy c-means. The magnitude and mean of wavelet coefficients for each EEG band are applied to the cluster of the FCM classifier. The proposed system show a little more accurate diagnosis for EEG by analysis of frequency for Wavelet and the success rate of 95% classification using FCM. From the simulation results by the implemented system, we demonstrated this research can be reduce doctor's labors and realize quantitative diagnosis of EEG.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1180-1185
• /
• 2009

Spasticity is a velocity-dependent stretch reflex disorder of the body motor system developing after the injury of the central nervous system, in which certain muscles are continuously contracted involuntarily. Conventional methods such as the modified Ashworth scale, Spasm frequency scale, pendulum test and isokinetic dynamometer had some disadvantages: limitation in discriminating the increase of resistance, immovable and expensive device, not enough study parameters. Therefore, it is necessary to introduce clinically more useful instrument, which can produce objective data and are more convenient on spasticity measurement. Spasticity measuring methods were reviewed and a new measuring instrument was designed and introduced. The new measuring system is a portable spasticity-measurement system, which encompass various scopes of spasticity-related human signals such as electrophysiologic, kinematic and biomechanical data. Our device was designed in order to measure the joint angle, angular velocity, electromyographic signals and force. We suggest that this new system can diagnose the spasticity of the muscles, objectively.