• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.3
• /
• pp.369-374
• /
• 2008

This paper presents the evaluation procedures and the estimation method for the estimation of optimal rebate level for EE(Energy Efficiency) programs. The penetration amount of each appliance is estimated by applying price function to preferred diffusion model resulted from model compatibility test. To estimate the optimal rebate level, two objective functions which express the maximum energy saving and operation benefit are introduced and by multi-objective function which can simultaneously consider two objective functions the optimal rebate level of each appliance is estimated. And then, using the decided rebate level and each penetration amount, the priority order for reasonable investment of each high-efficiency appliance is estimated compared to the results of conventional method. Finally, using a benefit/cost analysis based on California standard practice manual, the economic analysis is implemented for the four perspectives such as participant, ratepayer impact measure, program administrator cost and total resource cost.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.12
• /
• pp.1640-1648
• /
• 2014

This paper proposes a switching frequency reduction method for MMC (Modular Multilevel Converter) utilizing redundancy operation of sub-module, which can offer reduction of voltage harmonics and switching loss. The feasibility of proposed method was verified through computer simulations with PSCAD/EMTDC software. Based on simulation analysis, a hardware scaled-model of 10kVA, DC-1000V MMC was designed and manufactured in the lab. Various experiments were conducted to verify the feasibility of proposed method in the actual hardware system. The hardware scaled-model can be effectively utilized for analyzing the performance of MMC according to the modulation scheme and redundancy operation.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2005.11a
• /
• pp.591-594
• /
• 2005

Concrete structure that has been constructed in real field is on multi-axial stress state condition. After placing of concrete, hydration heat and shrinkage of concrete can cause various stress conditions with respect to the restraint level and condition. So, to predict the early age behavior of concrete structure, multi-axial material model is required and microplane model is acceptable. Recently, many studies have been performed on the microplane model, but the model developed up to now has been related to hardened concrete that material property is constant with concrete age. So, it is inappropriate to apply this model immediately to analyze the early age behavior of concrete. In this study, microplane model that can predict early age behavior of concrete was developed and cracking analysis using that was performed to describe cracking behavior for massive concrete sturucture.

• Human Ecology Research
• /
• v.57 no.3
• /
• pp.341-352
• /
• 2019

This study examined the effect of maternal positive parenting attitudes on school adjustment among multi-cultural adolescents in Korea and investigated if multi-cultural adolescents' ego-resiliency mediates the relationship between maternal positive parenting attitudes and school adjustment. We used panel data from the fifth wave (2015) of the Multicultural Adolescents Panel Study (MAPS) collected by the National Youth Policy Institute. Participants were 1,297 multi-cultural adolescents (639 boys, 658 girls) who are second-year middle school students and have foreign mothers. SPSS 25.0 performed descriptive statistical analysis and correlation analysis. The structural equation model (SEM) was estimated with Mplus 5.12. The results of this study were as follows. First, a higher level of maternal positive parenting attitudes were related to higher level of ego-resiliency and school adjustment for multi-cultural adolescents. Second, maternal positive parenting attitudes had an indirect effect on school adjustment for multi-cultural adolescents via ego-resiliency. The results of this study indicate that maternal positive parenting behaviors would help improve the school adjustment of multi-cultural adolescents by increasing the level of ego-resiliency. In addition, the results of this study suggest that improving ego-resiliency for multi-cultural adolescents can be an effective method to help in school adjustment, as well as education for maternal parenting attitude.

• School Mathematics
• /
• v.15 no.2
• /
• pp.289-314
• /
• 2013

Achievement profile by attribute in Korean students' mathematics was analyzed by applying cognitive diagnostic model, which is the newest measurement theory, to 2011 NAEA(National Assessment of Educational Assessment) results. The results are as follows. As the level of school is higher from 6th grade, 9th grade to 11th grade, the percentage of students mastering cognitive attribute 9(expressions using picture, table, graph, formula, symbol, writing, etc) drastically declined from 78%, 35% to 26%. It is necessary to have learning strategies to reinforce their abilities of expressing table, graph, etc. that higher graders in mathematics are more vulnerable to. Next, the property of mastering cognitive attributes according to gender, multi-cultural family was analyzed. In terms of mathematics, the percentage of girls mastering most of the attribute generally is higher than that of boys from 6th grade to 9th grade, however, boys show higher mastery in almost attributes than girls in the 11th grade. Compared to boys, the part where girls have the most trouble is attribute 9 in mathematics(expressions using picture, table, graph, formula, symbol, writing, etc). As international marriage, influx of foreign workers, etc. increase, the number of students from Korea's multi-cultural families is expected to be higher, therefore, identifying the characteristics of their educational achievement is significant in reinforcing Korea's basic achievement. In mathematics, gap of mastery level of attributes between multi-cultural group and ordinary group is more severe in higher grade and the type of multi-cultural group that needs supports for improving achievement most urgently changed in 6th grade, 9th grade and 11th grade respectively. In the 6th and 11th grade, migrant students from North Korea show the lowest level of mastering attributes, however, in the 9th grade, the mastery rate of immigrant students is lowest. Therefore, there is an implication that supporting plans for improving achievement of students from multi-cultural family should establish other strategies based on the characteristics of school level.

• Korean Journal of Agricultural Science
• /
• v.48 no.4
• /
• pp.1027-1037
• /
• 2021

This study aims to evaluate the performance of an electric multi-purpose cultivator through a simulation analysis. The simulation model was developed using commercial software, Simulation X, by applying the specifications of certain parts, such as an electric motor, a battery, and so on. The input parameter of the simulation was the engine load data according to the rotary tillage level using a conventional multi-purpose cultivator. The data were collected by configuring a load measurement system, and the load cycle was developed by repeating the data collection process under the most severe conditions. The average output engine torque values of conventional multi-purpose cultivator were 10.7, 13.0, 9.4, and 11.2 Nm in the D1P1, D1P2, D2P1, and D2P2 conditions, respectively. As a result of the simulation, the maximum values of the motor torque, rotational speed, and power of the electric multi-purpose cultivator were 16.8 Nm, 2,033.3 rpm, and 3.3 kW, respectively, and the motor was driven in sections within 70, 68, and 45% of the maximum output range. The rate of decrease of the battery state of charge (SOC) level per minute was approximately 0.6%, and it was possible to supply electric power to the motor for 9,550 sec. In the future study, research to verify and improve simulation models of electric multi-purpose cultivators should be conducted.

• Industrial Engineering and Management Systems
• /
• v.14 no.4
• /
• pp.347-371
• /
• 2015

A hybrid procedure based on multi-Criteria Satisfaction Analysis (MUSA) and a Network Data Envelopment Analysis (NDEA) is proposed to evaluate the relative efficiency of customer services in bank branches. First, a three-stage process including sub-processes such as customer expectations, customer satisfaction, and customer loyalty, is defined to model the banking customer services. Then, fulfillment of customer expectations, customer loyalty level, and the customer satisfaction degree are measured and quantified through a multi-dimensional questionnaire based on customers' perceptions analysis and MUSA method, respectively. The customer services scores and the other criteria such as mean of employee evaluation score, operation costs, assets, deposits, loans, number of accounts are considered in network three-stage DEA model. The proposed NDEA model is formed based on multipliers perspective, output-oriented, and constant return to scale assumptions. The proposed NDEA model quantifies and assesses the total efficiency of main process and assigns the efficiency to customer expectations, customer satisfactions, and customer loyalties sub-processes in bank branches. The whole procedure is applied on 30 bank branches in IRAN. The proposed approach can be used in other organizations such as airports, airline agencies, urban transportation systems, railway organizations, chain stores, chain restaurants, public libraries, and entertainment centers.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2004.11a
• /
• pp.221-232
• /
• 2004

Paper process is complex and multivariable system. Identification of a paper process model is imperative for the development of predictive control method. 13-level Pseudo-Random Sequence Signals were used to identify the plant model in which the neural network model was considered model as a real paper process. Results of simulations for identification using 13-level PRS signals and Prediction Error Method are compared with plant operation data. From the comparison, we can see that the dynamics of the model show good agreement with those of real plant.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.4
• /
• pp.21-35
• /
• 2016

This study is to evaluate the applicability of SWAT (Soil and Water Assessment Tool) model for multi-purpose dams and multi-function weirs operation in Namhan river basin ($12,577km^2$) of South Korea. The SWAT was calibrated (2005 ~ 2009) and validated (2010 ~ 2014) considering of 4 multi-purpose dams and 3 multi-function weirs using daily observed dam inflow and storage, evapotranspiration, soil moisture, and groundwater level data. Firstly, the dam inflow was calibrated by the five steps; (step 1) the physical rate between total runoff and evapotranspiration was controlled by ESCO, (step 2) the peak runoff was calibrated by CN, OV_N, and CH_N, (step 3) the baseflow was calibrated by GW_DELAY, (step 4) the recession curve of baseflow was calibrated by ALPHA_BF, (step 5) the flux between lateral flow and return flow was controlled by SOL_AWC and SOL_K, and (step 6) the flux between reevaporation and return flow was controlled by REVAPMN and GW_REVAP. Secondly, for the storage water level calibration, the SWAT emergency and principle spillway were applied for water level from design flood level to restricted water level for dam and from maximum to management water level for weir respectively. Finally, the parameters for evapotranspiration (ESCO), soil water (SOL_AWC) and groundwater level fluctuation (GWQMN, ALPHA_BF) were repeatedly adjusted by trial error method. For the dam inflow, the determination coefficient $R^2$ was above 0.80. The average Nash-Sutcliffe efficiency (NSE) was from 0.59 to 0.88 and the RMSE was from 3.3 mm/day to 8.6 mm/day respectively. For the water balance performance, the PBIAS was between 9.4 and 21.4 %. For the dam storage volume, the $R^2$ was above 0.63 and the PBIAS was between 6.3 and 13.5 % respectively. The average $R^2$ for evapotranspiration and soil moisture at CM (Cheongmicheon) site was 0.72 and 0.78, and the average $R^2$ for groundwater level was 0.59 and 0.60 at 2 YP (Yangpyeong) sites.