• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

• Proceedings of the KIPE Conference
• /
• 2017.07a
• /
• pp.435-436
• /
• 2017

This papaer is study on thermal analysis of the active-front-end(AFE) rectifier for solid-state-transformer(SST) applications. finite element analysis simulation model is combined by switching component model, power diode and heat-sink model. thermal model is calculated by computer program and feedback the result. using simulation result analysis switching loss and compare to thermal diffusion of the heat in the model for steady-state operation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.397-400
• /
• 2021

To solve the problem that existing computing methods cannot adequately represent the semantic features of sentences, Siamese TRAT, a semantic feature extraction model based on Transformer encoder is proposed. The transformer model is used to fully extract the semantic information within sentences and carry out deep semantic coding for sentences. In addition, the interactive attention mechanism is introduced to extract the similar features of the association between two sentences, which makes the model better at capturing the important semantic information inside the sentence. As a result, it improves the semantic understanding and generalization ability of the model. The experimental results show that the proposed model can improve the accuracy significantly for the semantic similarity calculation task of English and Chinese, and is more effective than the existing methods.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.12 no.2
• /
• pp.1-8
• /
• 2008

Friction pendulum system is developed to prevent the damage of transformer, which is the most important among the electric power facilities, due to the earthquake and its seismic capacity is verified through the shaking table test. The applicability of friction pendulum system is confirmed as test results of compressive capacity test and friction test. Especially, as a result of shaking table test with a large scale transformer model, friction pendulum system gives to the reduction of maximum response acceleration by 30% at anchorage of transformer and 59% at the top of porcelain bushing comparing with the existing anchorage type. In addition to the reduction of maximum response acceleration, natural frequency of transformer is shifted to long period due to the friction pendulum system. In case that friction pendulum system is applied to the transformer, the damage of transformer can be prevented effectively under the earthquake.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.7
• /
• pp.84-93
• /
• 2007

The pole transformer is one of the most important facility to insure the stability of electric power supply. which distributes electricity to customers directly. However there are a lot of defects which are caused by manufacturing fails(in 3 years) or deterioration (in 13 years), so we need a more improved transformer which insures quality. This thesis talks about the development of the new-type transformer using the hybrid insulation that is durable thermally, mechanically, and electrically. It would show how to lay out and produce the transformer using the hybrid insulation. And finally we are sure that we could increase the utilization rate of a transformer by 160% as compared with its own capacity through the overload test. Also, we carried out the examination about the short-circuit and insulation with a 100[kVA] model transformer, so that we expound the analysis of magnetic-mechanical forces intensity and the measure for improving short-circuit efficiency.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.610-615
• /
• 2015

In order to study and obtain the mathematical relation between the electrification degree of transformer oil flow and the electrostatic current, a small amount of data about the electrification degree of oil flow and the corresponding electrostatic current is studied by linear regression method and grey model method. The results show that the linear correlation between the electrification degree and the electrostatic current was not good, and the relation between the electrification degree of oil flow and electrostatic current (i) could be expressed as ${\rho}(0)=0.2049\;i^{(0)}+169.4419$ according to grey model GM (0, 2) when the electrification degree of oil flow is represented by the charge number generated from transformer oil per unit volume, namely the charge density (${\rho}$).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3943-3959
• /
• 2022

People are constantly exposed to stress and anxiety environment, which could contribute to a variety of psychological and physical health problems. Therefore, it is particularly important to identify psychological stress in time and to find a feasible and universal method of stress reduction. This research investigated the influence of different music, such as relaxation music and natural rhythm music, on stress relief based on Electroencephalogram signals. Mental arithmetic test was implemented to create a stressful environment. 23 participants performed the mental arithmetic test with and without music respectively, while their Electroencephalogram signal was recorded. The effect of music on stress relief was verified through stress test questionnaires, including Trait Anxiety Inventory (STAI-6) and Self-Stress Assessment. There was a significant change in the stress test questionnaire values with and without music according to paired t-test (p<0.01). Furthermore, a model based on Transformer for stress level classification from Electroencephalogram signal was proposed. Experimental results showed that the method of listening to relaxation music and natural rhythm music achieved the effect of reducing psychological stress and the proposed model yielded a promising accuracy in classifying the Electroencephalogram signal of mental stress.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.356-362
• /
• 2004

Using multi wrapped copper by polyimide film for HTS transformer, the breakdown and V-t characteristics of two type models for turn-to-turn, one is point contact model, the other is surface contact model, were investigated under ac and impulse voltage at 77 K. A material that is Polyimide film (Kapton) 0.025 mm thickness is used for multi wrapping of the electrode. Statistical analysis of the results using Weibull distribution to examine the wrapping number effects on V-t characteristics under at voltage as well as breakdown voltage under ac and impulse voltage in $LN_2$ was carried. Also, survival analysis was performed according to the Kaplan-Meier method. The breakdown voltages for surface contact model are lower than that of the point contact model, because the contact area of surface contact model is wider than that of point contact model. At the same time, the shape parameter of the point contact model is a little bit larger than the of the surface contact model. The time to breakdown tn is decreased as the applied voltage is increased, and the lifetime indices slightly are increased as the number of layers is increased. According to the increasing applied voltage and decreasing wrapping number, the survival probability is increased.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.2
• /
• pp.865-873
• /
• 2017

Converter transformer is the key equipment of high voltage direct current transmission system. The solid suspending particles originating from the process of installation and operation of converter transformer have significant influence on the insulation performance of transformer oil, especially in presence of DC component in applied voltage. Under high electric field, the particles easily lead to partial discharge and breakdown of insulating oil. This paper investigated copper particle effect on the breakdown voltage of transformer oil at combined AC and DC voltage. A simulation model with single copper particle was established to interpret the particle effect on the breakdown strength of insulating oil. The experimental and simulation results showed that the particles distort the electric field. The breakdown voltage of insulating oil contaminated with copper particle decreases with the increase of particle number, and the breakdown voltage and the logarithm of particle number approximately satisfy the linear relationship. With the increase of the DC component in applied voltage, the breakdown voltage of contaminated insulating oil decreases. The simulation results show that the particle collides with the electrode more frequently with more DC component contained in the applied voltage, which will trigger more discharge and decrease the breakdown voltage of insulating oil.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.55 no.1
• /
• pp.6-12
• /
• 2006

A popular method used by primary protection for power transformer is current ratio differential relaying (RDR) with 2nd harmonic restraints. In modern power transformer due to the use of low-loss amorphous material, the 2nd harmonic component during inrush is significantly reduced. The higher the capacitance of the high voltage status and underground distribution, the more the differential current includes the 2nd harmonic component during internal fault. Thus the conventional method may not operate properly. This paper proposes an advanced relaying algorithm and the prototype IED hardware design and it's real-time experimental results. To evaluate performance of the proposed algorithm, the study is well constructed power system model including power transformer utilizing the EMTP software and the testing is made through simulation of various cases. The proposed relaying that is well constructed using DSP chip and microprocessor etc. has been developed and the prototype IED has been verified through on-line testing. The results show that an advanced relaying based prototype IED never mis-operated and correctly identified all the faults and that inrushes that are applied.