• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.380-382
• /
• 2022

Extracting informative representation of molecules using graph neural networks(GNNs) is crucial in AI-driven drug discovery. Recently, the graph research community has been trying to replicate the success of self supervised in natural language processing, with several successes claimed. However, we find the benefit brought by self-supervised learning on applying varitional auto-encoders can be potentially effective on molecular data.

• 한국전산유체공학회:학술대회논문집
• /
• 2009.11a
• /
• pp.77-83
• /
• 2009

In this study, we conducted resistance and propulsion performance test of ship composed of the Resistance Test, Propeller Open Water Test and Self Propulsion Test using the CFD(Computational Fluid Dynamics). We used commercial RANS(Reynolds Averaged Navier Stokes equation) solver, as a calculating tool. The unstructured grids were used in a bow and stern of ship, having complex shape, for a convenience of generating grids, and the structured grids were adopted in a central hull and rest of hull having a relatively simple shape which is called hybrid grid method. In addition, The sliding mesh method was adopted to rotate a propeller directly in the Propeller Open Water and Self Propulsion Test. The Resistance Test and Self Propulsion Test were calculated using Volume of Fluid (VOF) model and considering a free surface. And all The three cases were applied realizable k-epsilon model as the turbulence model. The results of calculations were verified for the suitability of calculations by comparing MOERI's EFD results.

• Journal of the Korea Institute of Building Construction
• /
• v.14 no.6
• /
• pp.623-629
• /
• 2014

The purpose of this study is to analyze user requirements of photovoltaic generating facilities for detached houses. For the analysis, 202 households that installed photovoltaic generating facilities to conduct a survey. According to the survey results, users mainly demanded 'Reduction in self-burden amount' and 'Maintenance Services.' In addition, when conducting 'Education for photovoltaic generating facilities', they highly wanted to participated in it. Results on the installation status of photovoltaic generating facilities are as follows: Of locations where photovoltaic generating facilities are installed, the most households installed them on the roof, 54%. As for the angle in which photovoltaic module is installed, the range of $25{\sim}35^{\circ}$ was the most common and in the case of installation direction, southern exposure accounted for the rate of 93%. The monthly average generation of households surveyed is approximately 320kWh. Research on technology and policy to address user requirements shown in this study is deemed necessary in the future.

• Journal of The Korean Association For Science Education
• /
• v.29 no.8
• /
• pp.861-873
• /
• 2009

This study investigated the types of analogies generated by science-gifted students, mapping errors on the chromatography, and the perceptions on generating analogy. The subjects were science-gifted eighth-graders (N=68) enrolled at four gifted-education centers in Seoul. Analyses of the results revealed that most science-gifted students represented the analogies using verbal and pictorial forms based on concrete and everyday experiences, and they elaborately explained them including the functional attributes and the causal relationships of the target concept. Science-gifted students selected the analogies having rich similarities or similar structure and principle between the target concept and the analogy as the best of the self-generated analogies. And they used mainly their 'school life' as analogy materials. The results of the mapping test showed that many science-gifted students had mapping errors such as 'failure to map' and 'overmapping'. They were found to have the positive perceptions on generating analogy. The present study will provide the basic information to develop an instructional model in generating analogy in an education program for science-gifted students.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.128-135
• /
• 2006

This paper proposes the control method of fuzzy based sensor fusion by using the self localization of environment, position data by dead reckoning of the encoder and world map from sonic sensors. The proposed fuzzy based sensor fusion system recognizes the object and extracts features such as edge, distance and patterns for generating the world map and self localization. Therefore, this paper has developed fuzzy based control of mobile robot with experimentations in a corridor environment.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• pp.226-232
• /
• 2001

The ability to efficiently and robustly recover accurate 3D terrain models from sets of stereoscopic images is important to many civilian and military applications. To develop an effective and practical terrain modeling system, we propose a new multi-image stereo method which detect unreliable elevations in DEM(Digital Elevation Map), and fuse several DEMs from multiple sources into an accurate and reliable results. This paper focuses on two key factors for generating robust 3D terrain models: the ability to detect unreliable elevation estimates and the ability to fuse the reliable elevations into a single optimal terrain model. We apply the self-consistency methodology to reconstruct accurate DEM from multi-image and show the method is more effective than the conventional stereo image 3D reconstruction method. Using photo-realistic simulator, four synthetic image are generated from ground truth DEM and orthoimage to evaluate the accuracy of the proposed method quantitatively.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.5B no.4
• /
• pp.331-336
• /
• 2005

With increasing emphasis on non-conventional energy systems and autonomous power generation, development of improved and appropriate generating systems has recently taken on greater significance. This paper describes the performance analysis of a single phase self-excited induction generator (SEIG), suitable for autonomous/standby power systems. The system is also appropriate for wind energy systems and small portable systems. Both windings of the induction machine, the main and the auxiliary, are utilized. One winding will be devoted to the supply excitation current only, by being connected to the excitation capacitor, while the load is connected across the other winding. As the design of excitation, the minimum of self-excited capacitor connected auxiliary winding is determined as the suitable value using a circuit equation of auxiliary winding. For the steady state analysis, the equivalent circuit of the single-phase induction generators is used as a basis for modeling using the double-revolving field theory. The validity of the designed generator system is confirmed by experimental and computed results.

• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.195-196
• /
• 2012

A self-organizing map (SOM) can be seen as an analytical tool to discover some underlying rules in the given data set. Based on such distinctive nature called topology-preserving projection, a new method for generating intermediate patterns was proposed. Then, following to this method, producing animation as a series of backward-projected patterns just like a flip book is tried in this article.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.938-940
• /
• 2004

With increased emphasis on non-conventional energy system and autonomous power generation, development of improved and appropriate generating system has assumed signification. This paper describes the performance analysis of 2-phase self-excited induction generators. The minimum capacitance of self-excited capacitor connected auxiliary winding is determined the suitable value using circuit equations of auxiliary winding. For the steady state analysis, the equivalent circuit of 2-phase induction generators is used as circuit modeling using the double-revolving field theory. The validity of designed generator system will be confirmed by experimental and computed results.

• Journal of the Korea Society of Computer and Information
• /
• v.1 no.1
• /
• pp.159-170
• /
• 1996

In this paper, we propose a generating method for the optimal rules for the nonlinear control system using evolution algorithms and fuzzy controller. With the aid of evolution algorithms optimal rules of fuzzy logic system can be automatic designed without human expert's priori experience and. knowledge. and ran be intelligent control. The approachpresented here generating rules by self-tuning the parameters of membership functions and searchs the optimal control rules based on a fitness value which Is tile defined performance criterion. Computer simulations demonstrates the usefulness of the proposed method In non -linear systems.