• 한국가금학회지
• /
• 제44권2호
• /
• pp.103-111
• /
• 2017

The quail (Coturnix japonica) has been used as a model animal in many research fields and its application is still expanding in other fields. Compared to the chicken, the quail is quicker to reach sexually maturity, has short generation intervals, is easy to handle, requires less space and feed, and is sturdy. In addition, it produces many eggs and the research tools developed for chicken can be applied directly to quail or with some modifications. Due to recent advances in next-generation sequencing, abundant sequence data for the quail genome and transcripts have been generated. These sequence data are valuable sources for studying functional genomics using quail, which is one of the model animal used to investigate gene function and networks. Although there are some obstacles to be removed, the quail is the best optimized model to study the functional genomics of poultry. In many research fields, functional genomics study using the quail model will provide the best opportunity to understand the phenomena and principles of life. We review why, among many other birds, the quail is the best model for studying poultry functional genomics.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 가을 학술발표회 논문집
• /
• pp.439-446
• /
• 1998

One of the most important roles in the nonlinear dynamic structural analysis is to select a proper ground excitation, which dominates the response of a structure. Because of the lack of recorded accelerograms in Korea, a stochastic model of ground excitation with various dynamic properties rather than recorded accelerograms is necessarily required. If all information is not available at site, the information from other sites with similar features can be used by the procedure of seismic hazard analysis. Eliopoulos and Wen identified the parameters of the ground motion model by the empirical relations or expressions developed by Trifunac and Lee. Because the relations used in the parameter identification are largely empirical, it is required to apply the artificial neural networks instead of the empirical model. Additionally, neural networks have the advantage of the empirical model that it can continuously re-train the new recorded data, so that it can adapt to the change of the enormous data. Based on the redefined traditional processes, three neural-networks-based models (FAS_NN, PSD_NN and INT_NN) are proposed to individually substitute the Fourier amplitude spectrum, the parameter identification of power spectral density function and intensity function. The paper describes the first half of the research for the development of Neural-Networks-based model for the generation of an Artificial earthquake and a Response Spectrum(NNARS).

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.355-357
• /
• 2022

본 논문에서는 딥러닝 네트워크인 순환신경망(RNN) 모델을 사용해 이동 중인 객체의 이동 경로의 예측을 위한 포지셔닝 기술로서 실내 환경에서 지역 경로 내의 이동 중인 차량의 경로 예측에 연속적인 위치 정보를 이용하여 현재 위치 결정의 오류를 낮출 수 있는 이동 경로 생성 기법을 제안한다. GPS 정보를 사용할 수 없는 실내 환경의 경우 RNN 모델을 적용하기 위해서는 데이터 세트가 연속적이고 순차적이어야 한다. 그러나 Wi-Fi 전파 지문 데이터는 수집 시점의 특정 위치에 대한 특징 정보로서 연속성이 보장되지 않기 때문에 RNN 데이터로 사용할 수 없다. 따라서 RNN 모델에 필요한 순차적 위치의 연속성을 부여하여 실내 환경의 지역 경로를 이동하는 차량의 이동 경로 생성 기법을 제안한다.

• 품질경영학회지
• /
• 제51권2호
• /
• pp.315-327
• /
• 2023

Purpose: Recently, research has continued to predict the time of failure of the facility through measurement data obtained by attaching a sensor to the facility. However, depending on the facility, it may be difficult to attach a sensor. The purpose of this study is to propose a power generation maintenance plan system based on failure record data obtained from Continuous Ship Unloader, one of the facilities that is difficult to attach sensors. Methods: This study uses data collected from 2012 to 2022 from the 'CSU-1B' model among Continuous Ship Unloader operated by Korea Midland Power Co., LTD. By fitting fault record data to the Weibull distribution, appropriate maintenance cycles and ranges for each target facility subsystem are derived. In addition, maintenance group between subsystems is selected through Euclidean distance, a metric often used for time series data similarity. Through this, a system for establishing an maintenance plan for power generation facilities is proposed. Results: The results of this study are as follows. For the 17 subsystems of the Continuous Ship Unloader, proper maintenance cycles and ranges were determined, and a total of four maintenance groups were chosen. This resulted in the creation of an power generation maintenance plan system and the establishment of an maintenance plan. Conclusion: This study is a case study of power generation facilities. We proposed a maintenance plan system for Continuous Ship Unloader among power generation facilities.

• 환경영향평가
• /
• 제17권5호
• /
• pp.321-330
• /
• 2008

Methane is a potent greenhouse gas and methane emissions from landfills have been linked to global warming. In this study, LandGEM (Landfill Gas Emission Model) was applied to predict landfill gas quantity over time, and then this result was compared with the data surveyed on the site, Cheongju Megalo Landfill. LandGEM allows the input of site-specific values for methane generation rate (k) and potential methane generation capacity $L_o$, but in this study, k value of 0.05/yr and $L_o$ value of $170m^3/Mg$ were considered to be most appropriate for reflecting non-arid temperate region conventional landfilling, Cheongju Megalo Landfill. High discrepancies between the surveyed data and the predicted data about landfill gas seems to be derived from insufficient compaction of daily soil-cover, inefficient recovery of landfill gas and banning of direct landfilling of food garbage waste in 2005. This study can be used for dissemination of information and increasing awareness about the benefits of recovering and utilizing LFG (landfill gas) and mitigating greenhouse gas emissions.

• 한국융합학회논문지
• /
• 제13권1호
• /
• pp.13-21
• /
• 2022

최근 딥러닝 기반의 자연어처리 연구는 사전 훈련된 언어 모델을 통해 대부분의 자연어처리 분야에서 우수한 성능을 보인다. 특히 오토인코더 (auto-encoder) 기반의 언어 모델은 다양한 한국어 이해 분야에서 뛰어난 성능과 쓰임을 증명하고 있다. 그러나 여전히 디코더 (decoder) 기반의 한국어 생성 모델은 간단한 문장 생성 과제에도 어려움을 겪고 있으며, 생성 모델이 가장 일반적으로 쓰이는 대화 분야에서의 세부 연구와 학습 가능한 데이터가 부족한 상황이다. 따라서 본 논문은 한국어 생성 모델을 위한 멀티턴 대화 데이터를 구축하고 전이 학습을 통해 생성 모델의 대화 능력을 개선하여 성능을 비교 분석한다. 또한, 검색 모델을 통해 외부 지식 정보에서 추천 응답 후보군을 추출하여 모델의 부족한 대화 생성 능력을 보완하는 방법을 제안한다.

• 대기
• /
• 제34권2호
• /
• pp.177-185
• /
• 2024

As increasing global interest in renewable energy due to the ongoing climate crisis, there is a growing need for efficient technologies to manage such resources. This study focuses on the predictive skill of daily solar power generation using weather observation and forecast data. Meteorological data from the Korea Meteorological Administration and solar power generation data from the Korea Power Exchange were utilized for the period from January 2017 to May 2023, considering both inland (Daejeon) and coastal (Busan) regions. Temperature, wind speed, relative humidity, and precipitation were selected as relevant meteorological variables for solar power prediction. All data was preprocessed by removing their systematic components to use only their residuals and the residual of solar data were further processed with weighted adjustments for homoscedasticity. Four models, MLR (Multiple Linear Regression), RF (Random Forest), DNN (Deep Neural Network), and RNN (Recurrent Neural Network), were employed for solar power prediction and their performances were evaluated based on predicted values utilizing observed meteorological data (used as a reference), 1-day-ahead forecast data (referred to as fore1), and 2-day-ahead forecast data (fore2). DNN-based prediction model exhibits superior performance in both regions, with RNN performing the least effectively. However, MLR and RF demonstrate competitive performance comparable to DNN. The disparities in the performance of the four different models are less pronounced than anticipated, underscoring the pivotal role of fitting models using residuals. This emphasizes that the utilized preprocessing approach, specifically leveraging residuals, is poised to play a crucial role in the future of solar power generation forecasting.

• 방송공학회논문지
• /
• 제26권4호
• /
• pp.390-397
• /
• 2021

디지털 트윈 기술을 다양한 산업 분야에 응용함에 따라 대용량 데이터를 효과적으로 처리하기 위한 기술들이 필요하다. 본 논문에서는 지하 공동구 관리를 위한 대용량 데이터를 고속 검색하고 효과적인 전달을 위한 맞춤형 서비스 방안에 대해 논한다. 제안하는 방안은 크게 두 가지로 방대한 데이터를 효율적으로 검색하고 축약해서 보여주기 위한 고속 검색 데이터 생성 방법과 맞춤형 정보 서비스 분할 방법에 대해 제안한다. 고속 검색 데이터 생성에서는 지하 공동구 내 센서들에 의해 수집되는 시계열 분석을 위한 동기화 과정에 대해 구성과 데이터 축약에 따른 부가정보 방안에 대해서 논한다. 사용자 맞춤형 서비스 방법에서는 평상시와 재난 시의 사용자 유형을 정의하고 그에 따른 서비스하는 방법에 대해 논한다. 본 연구를 통해 재난 상황에서 대용량 데이터를 효과적으로 검색하고 서비스 받을 수 있는 지하 공동구 관리를 위한 데이터 생성과 서비스 모델에 대한 체계성을 갖출 수 있을 것으로 예상된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 추계학술대회 논문집 학회본부
• /
• pp.87-91
• /
• 1988

For the electric power system operation, the information to monitor the operation status of power plants and transmission lines is very important factor in the view point of system security and economic operation. This paper presents the logical and physical structures of database used by KEPCO's EMS. The adopted DataBase Management System (DBMS) of a relational model type offers many advantages such as easy maintenance of database. In addition, this paper briefly introduces the data exchange system between application programs and database.

• 한국BIM학회 논문집
• /
• 제11권4호
• /
• pp.53-62
• /
• 2021

The successful implementation of Scan-to-BIM automation depends on the entire process from scanning of buildings, including indoor facilities and furniture, to generating BIM models. However, the conventional Scan-to-BIM process requires a lot of time, manpower, and cost for the manual generation of BIM models including indoor objects. To solve this problem, this study applied a Scan-to-BIM automation process using a deep learning model and parametric algorithm to an existing building, Kangwon Fire Service Academy. To improve the accuracy of the BIM model, after object data was extracted from the scan data, the data was corrected according to actual object-specific conditions. As a result, the accuracy of the BIM model created by the proposed Scan-to-BIM automation process was 91% compared to the actual area of the construction drawings. In addition, it was confirmed that the BIM objects were automatically generated for 10 object classes.