• 한국전산구조공학회논문집
• /
• 제36권6호
• /
• pp.391-398
• /
• 2023

본 논문에서는 기저 스크리닝 기반 크리깅 모델(BSKM: Basis Screening based Kriging Model) 생성의 정확도를 높이기 위해 페널티를 적용한 최대 우도 평가 방법(PMLE : Penalized Maximum Likelihood Estimation)에 대해서 소개한다. BSKM에서 사용하는 기저함수의 최대 차수와 종류는 그 중요도에 따라서 결정하게 되며, 이때 중요도의 지표는 기저함수에 대한 교차 검증 오차(CVE : Cross Validation Error)로 택한다. 크리깅 모델(KM : Kriging Model) 구성시 최적의 기저함수 조합은 우선 최대 기저함수 차수를 선택하고 개별 기저함수의 중요도를 평가를 하게 된다. 최적 기저함수 조합은 크리깅 모델의 CVE가 최소가 될 때까지 개별 기저함수의 중요도가 높은 순으로 기저함수를 하나씩 추가하며 찾는다. 이 과정에서 KM은 반복적으로 생성해야 하며, 동시에 데이터 사이의 상관관계를 나타내는 하이퍼 매개변수(Hyper-parameters)도 최대 우도 평가방법을 통해 계산하여야 한다. 하이퍼 매개변수의 값에 따라 선택되는 최적의 기저함수 조합이 달라지기 때문에 KM의 정확도에 막대한 영향을 미치게 된다. 정확한 하이퍼 매개변수를 계산하기 위해서 PMLE 방법을 적용하였으며, Branin-Hoo 함수 문제에 적용하여 BSKM 의 정확성이 개선될 수 있음을 확인하였다.

• Journal of Applied Biological Chemistry
• /
• 제59권4호
• /
• pp.289-298
• /
• 2016

FK506 hyper-yielding mutant, called the TCM8594 strain, was made from Streptomyces tsukubaensis NRRL 18488 by mutagenesis using N-methyl-N'-nitro-N-nitrosoguanidine, ultraviolet irradiation, and FK506 sequential resistance selection. FK506 production by the TCM8594 strain improved 45.1-fold ($505.4{\mu}g/mL$) compared to that of S. tsukubaensis NRRL 18488 ($11.2{\mu}g/mL$). Among the five substrates, wheat bran was selected as the best solid substrate to produce optimum quantities of FK506 ($382.7{\mu}g/g$ substrate) under solid-state fermentation, and the process parameters affecting FK506 production were optimized. Maximum FK506 yield ($897.4{\mu}g/g$ substrate) was achieved by optimizing process parameters, such as wheat bran with 5 % (w/w) dextrin and yeast extract as additional nutrients, 70 % (v/w) initial solid substrate moisture content, initial medium pH of 7.2, $30^{\circ}C$ incubation temperature, inoculum level that was 10 % (v/w) of the cell mass equivalent, and a 10 day incubation. The results showed an overall 234 % increase in FK506 production after optimizing the process parameters.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.251-258
• /
• 2023

안정적으로 전력을 공급하고 전력계통을 운영하기 위해서는 최대전력을 정확히 예측해야 한다. 특히, 최대전력이 높게 발생하는 겨울과 여름에는 그 중요성이 매우 커진다. 최대전력을 실제 수요보다 높게 예측하면 발전소 기동 비용이 증가하여 경제적 손실이 발생하고, 최대전력을 실제 수요보다 낮게 예측하면 기동이 가능한 발전소가 부족하여 정전이 발생할 수 있다. 최대전력의 예측 오차를 최소화함으로써 경제적 손실과 정전을 예방할 수 있다. 본 논문에서는 최대전력 예측의 오차를 최소화하기 위하여 최신 딥러닝 모델인 TCN을 이용한다. 딥러닝 모델은 하이퍼 파라미터를 어떻게 설정하느냐에 따라 성능 차이가 발생하므로, TCN의 하이퍼 파라미터를 최적화하는 방법을 제안한다. 2006년부터 2021년까지의 데이터를 입력하여 모델을 훈련하고, 2022년의 데이터를 이용하여 예측 오차를 실험하였다. 실험을 수행한 결과 본 논문에서 제안한 최적화 방법을 이용한 TCN 모델의 성능이 다른 딥러닝 모델보다 성능이 우수한 것을 확인하였다.

• ETRI Journal
• /
• 제40권5호
• /
• pp.664-676
• /
• 2018

Given the rapidly increasing market penetration of photovoltaic (PV) systems in many fields, including construction and housing, the effective maintenance of PV systems through remote monitoring at the panel level has attracted attention to quickly detect faults that cause reductions in yearly PV energy production, and which can reduce the whole-life cost. A key point of PV monitoring at the panel level is cost-effectiveness, as the installation of the massive PV panels that comprise PV systems is showing rapid growth in the market. This paper proposes an implementation method that involves the use of a panel-level wireless PV monitoring module (WPMM), and which assesses the cost-effectiveness of this approach. To maximize the cost-effectiveness, the designed WPMM uses a voltage-divider scheme for voltage metering and a shunt-resistor scheme for current metering. In addition, the proposed method offsets the effect of element errors by extracting calibration parameters. Furthermore, a design method is presented for portable and user-friendly PV monitoring, and demonstration results using a commercial 30-kW PV system are described.

• 한국공간구조학회논문집
• /
• 제21권1호
• /
• pp.79-86
• /
• 2021

Control performance of a smart tuned mass damper (TMD) mainly depends on control algorithms. A lot of control strategies have been proposed for semi-active control devices. Recently, machine learning begins to be applied to development of vibration control algorithm. In this study, a reinforcement learning among machine learning techniques was employed to develop a semi-active control algorithm for a smart TMD. The smart TMD was composed of magnetorheological damper in this study. For this purpose, an 11-story building structure with a smart TMD was selected to construct a reinforcement learning environment. A time history analysis of the example structure subject to earthquake excitation was conducted in the reinforcement learning procedure. Deep Q-network (DQN) among various reinforcement learning algorithms was used to make a learning agent. The command voltage sent to the MR damper is determined by the action produced by the DQN. Parametric studies on hyper-parameters of DQN were performed by numerical simulations. After appropriate training iteration of the DQN model with proper hyper-parameters, the DQN model for control of seismic responses of the example structure with smart TMD was developed. The developed DQN model can effectively control smart TMD to reduce seismic responses of the example structure.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.45-49
• /
• 2022

The fourth industrial revolution, internet of things, and the expansion of online web services have increased an exponential growth and deployment in the number of cloud data centers (CDC). The cloud is emerging as new paradigm for delivering the Internet-based computing services. Due to the dynamic and non-linear workload and availability of the resources is a critical problem for efficient workload and resource management. In this paper, we propose the particle swarm optimization (PSO) based gated recurrent unit (GRU) neural network for efficient prediction the future value of the CPU and memory usage in the cloud data centers. We investigate the hyper-parameters of the GRU for better model to effectively predict the cloud resources. We use the Google Cluster traces to evaluate the aforementioned PSO-GRU prediction. The experimental shows the effectiveness of the proposed algorithm.

• Wind and Structures
• /
• 제36권6호
• /
• pp.355-366
• /
• 2023

Although machine learning (ML) techniques have been widely used in various fields of engineering practice, their applications in the field of wind engineering are still at the initial stage. In order to evaluate the feasibility of machine learning algorithms for prediction of wind loads on high-rise buildings, this study took the exposure category type, wind direction and the height of local wind force as the input features and adopted four different machine learning algorithms including k-nearest neighbor (KNN), support vector machine (SVM), gradient boosting regression tree (GBRT) and extreme gradient (XG) boosting to predict wind force coefficients of CAARC standard tall building model. All the hyper-parameters of four ML algorithms are optimized by tree-structured Parzen estimator (TPE). The result shows that mean drag force coefficients and RMS lift force coefficients can be well predicted by the GBRT algorithm model while the RMS drag force coefficients can be forecasted preferably by the XG boosting algorithm model. The proposed machine learning based algorithms for wind loads prediction can be an alternative of traditional wind tunnel tests and computational fluid dynamic simulations.

• 수산해양기술연구
• /
• 제60권1호
• /
• pp.87-99
• /
• 2024

This study deals with the application of an artificial neural network (ANN) model to predict power consumption for utilizing seawater source heat pumps of recirculating aquaculture system. An integrated dynamic simulation model was constructed using the TRNSYS program to obtain input and output data for the ANN model to predict the power consumption of the recirculating aquaculture system with a heat pump system. Data obtained from the TRNSYS program were analyzed using linear regression, and converted into optimal data necessary for the ANN model through normalization. To optimize the ANN-based power consumption prediction model, the hyper parameters of ANN were determined using the Bayesian optimization. ANN simulation results showed that ANN models with optimized hyper parameters exhibited acceptably high predictive accuracy conforming to ASHRAE standards.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.247-253
• /
• 2011

A sustainability of electricity supply has emerged as a critical issue for low carbon green growth in South Korea. Wind power is the fastest growing source of renewable energy. However, due to its own intermittency and volatility, the power supply generated from wind energy has variability in nature. Hence, accurate forecasting of wind speed and power plays a key role in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. This paper presents a short-term wind speed prediction method based on support vector regression. Moreover, particle swarm optimization is adopted to find an optimum setting of hyper-parameters in support vector regression. An illustration is given by real-world data and the effect of model regularization by particle swarm optimization is discussed as well.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.510-513
• /
• 2018

본 논문은 다양한 워드 임베딩 모델(word embedding model)들과 하이퍼 파라미터(hyper parameter)들을 조합하였을 때 특정 영역에 어떠한 성능을 보여주는지에 대한 연구이다. 3 가지의 워드 임베딩 모델인 Word2Vec, FastText, Glove의 차원(dimension)과 윈도우 사이즈(window size), 최소 횟수(min count)를 각기 달리하여 총 36개의 임베딩 벡터(embedding vector)를 만들었다. 각 임베딩 벡터를 Fast and Accurate Dependency Parser 모델에 적용하여 각 모들의 성능을 측정하였다. 모든 모델에서 차원이 높을수록 성능이 개선되었으며, FastText가 대부분의 경우에서 높은 성능을 내는 것을 알 수 있었다.