• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.174-176
• /
• 2022

In this paper, we present a mobile application for 'personalized customized learning' for children with articulation disorders using an artificial intelligence (AI) algorithm. A dataset (Data Set) to analyze, judge, and predict the learner's articulation situation and degree. In particular, we designed a prototype model by looking at how AI can be improved and advanced compared to existing applications from the UX/UI (GUI) aspect. So far, the focus has been on visual experience, but now it is an important time to process data and provide a UX/UI (GUI) experience to users. The UX/UI (GUI) of the proposed mobile application was to be provided according to the learner's articulation level and situation by using CRNN (Convolution Recurrent Neural Network) of DeepLearning and Auto Encoder GPT-3 (Generative Pretrained Transformer). The use of artificial intelligence algorithms will provide a learning environment with a high degree of perfection to children with articulation disorders, thereby enhancing the learning effect. I hope that you do not have any fear or discomfort in conversation by improving the perfection of articulation with 'personalized and customized learning'.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.9
• /
• pp.1708-1714
• /
• 2011

AT feeding system of the electric railway system is installed every about 10km at between the feeder and catenary in parallel and the mid-point of the transformer is connected to the rail The supply voltage of this system is doubled than rolling stock voltage. So the voltage drop is smaller than usual. And the other merit of this system is the decreasing inductive disturbance to the communication line because of the reduced current in rail which runs reversed in a point of view of rolling stock. Also, ATP(Auto Transformer Post) is installed to reduce the voltage drop and to mitigate the inductive disturbance, but still now the proper distance between the ATP and AT feeding system is not established which ranges from 2 to 10[km]. The stable result of simulation(which is set that the end of the line AT is installed) to the voltage drop and inductive disturbance can not analyzes the effect to the supply system due to the ATP. This paper analyzes the effect to the system depending on the location of ATP by forecasting the voltage drop and inductive disturbance.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.579-586
• /
• 2021

Time series forecasting refers to predicting future time information based on past time information. Accurately predicting future information is crucial because it is used for establishing strategies or making policy decisions in various fields. Recently, a transformer model has been mainly studied for a time series prediction model. However, the existing transformer model has a limitation in that it has an auto-regressive structure in which the output result is input again when the prediction sequence is output. This limitation causes a problem in that accuracy is lowered when predicting a distant time point. This paper proposes a sequential decoding model focusing on the style transformation technique to handle these problems and make more precise time series forecasting. The proposed model has a structure in which the contents of past data are extracted from the transformer-encoder and reflected in the style-based decoder to generate the predictive sequence. Unlike the decoder structure of the conventional auto-regressive transformer, this structure has the advantage of being able to more accurately predict information from a distant view because the prediction sequence is output all at once. As a result of conducting a prediction experiment with various time series datasets with different data characteristics, it was shown that the model presented in this paper has better prediction accuracy than other existing time series prediction models.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.6
• /
• pp.220-229
• /
• 2004

The AC railway system is quite differing from the general electric power system because it is single- phase and intermittently heavy loads. Thus, inevitably power quality problems are occurred in the AC railway system, i.e. voltage regulation voltage sags, voltage imbalance, and harmonic distortion. Recently, the power quality of the AC railway system becoming a hot issue because it is affect the control and safety of high-speed traction. In addition it is also affect the power quality of the electric power system. In this paper, single-phase Unified Power Quality Conditioner(UPQS) for the AC railway system is proposed to compensate the voltage sags and harmonic distortion. The configurations and control schemes of the proposed single-phase UPQC are presented. The effectiveness of the proposed single-phase UPQC application is verified by the PSCAD/EMTDC simulation works. It can be shown that the application of UPQC in the AC railway system is very useful to compensate the voltage sags and harmonic distortion from the results of related simulation works.

• Proceedings of the KIEE Conference
• /
• 2001.11b
• /
• pp.333-335
• /
• 2001

In this paper, an algorithm for fault location in Auto Transformer(AT) Feeding Railway system is presented. If a fault occurs at the AT feeding circuits of electrical railway system, it is very important to find fault location and to remove it immediately for the purpose of ensuring safety for transportation. Because the characteristics of reactance-distance are not linear, only using one terminal signals to give fault distance is difficult. In this paper, first, using the KVL, 4 voltage equation are obtained. Secondly, eliminating voltage a distance equation which consists of currents at rail and line parameters including mutual effects.

• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.1226-1228
• /
• 2001

In this paper, the modified simulation algorithms of the Auto Transformer (AT) feeding electric train were proposed. To obtain terminal voltage of train by using equivalent circuit of the AT feeding system, the iterative method is proposed for which determine the train voltages. The train voltages are iteratively calculated from the system voltage drop and line impedance. In the case study, the proposed method is verified from actual operation data of the Kwa-Chon line. Also it is verified that the proposed method can be extent to the multi-train simulation tool. The terminal voltage of the multi-train can be calculated by using superposition principle and it is easily applied to the proposed method. Therefore, the proposed method can be a solution for the complexity of the circuit analysis in the existing methods.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.51 no.4
• /
• pp.174-179
• /
• 2002

In this paper, the modified simulation algorithms of the Auto Transformer (AT) feeding electric train system were proposed. To obtain terminal voltage of train by using equivalent circuit or the AT feeding system, the iterative method is proposed for which determine the train voltages. The train voltages are iteratively calculated from the system voltage drop and line impedance. In the carte study, the proposed method is verified from actual operation data of the Kwa-Chon line. Also it is verified that the proposed method can be extent to the multi-train simulation tool. The terminal voltage of the multi-train can be calculated by using superposition principle and it is easily applied to the proposed method. Therefore, the proposed method can be a solution for the complexity of the circuit analysis in the existing methods.

• Proceedings of the KIEE Conference
• /
• 2001.04a
• /
• pp.449-451
• /
• 2001

This study presents a study on modified algorithm to operating train simulation of AT feeding systems. In this study equivalent impedance is constructed by $Z_c,\;Z_r,\;Z_f,\;Z_{cr},\;Z_{rf},\;Z_{fc}$. The train current flows through the all auto-transformer corresponding to track impedance. To calculate train voltage from analyzing the railway systems, the algorithm is based on the K. C. L, K. V. L, superposition and circuit separation method. Multi-train's voltages are determined by calculating the catenary voltage at each train's position and adding up these train's voltage drop. Case studies use a field operational data, show that the proposed method is easily applied.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.12
• /
• pp.1723-1728
• /
• 2018

In order to investigate the voltage drop compensation effect of AT for domestic railway vehicle base, the parameters of AT voltage drop of railroad car base are Z3 (Impedance of feeder line), Xn ( Distance from railroad vehicle to AT to SS), and Dn (distance between both ATs of railway vehicle).In addition, when installed in a SSP for a railway vehicle base, there is no AT and feeder line in the railway vehicle base except for the SSP for the main line and the SSP for the railway vehicle base, so that if zero or ignored, the AC single-phase two- It can be confirmed that it becomes a form.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.868-869
• /
• 2008

An automatic excitation characteristics measurement system for the protective relaying current transformer(CT) with accuracy of about 1 % has been developed. The system can be used up to 2 kV and 10 A at power frequency. The developed system can calculate the voltage and current at knee points of $30^{\circ}$ and $45^{\circ}$ tangents in accordance with IEEE standard by the interpolation in log scale. The excitation curve of the CT is plotted in auto-scale simultaneously with measuring rms voltage and current at the secondary of the CT.