• 한국전자거래학회지
• /
• 제23권2호
• /
• pp.33-47
• /
• 2018

도시가스 배관은 지중에 매설되어 있기 때문에 세부 관리가 어렵고 다양한 위험에 노출되어 있다. 본 연구에서는 도시가스 배관압력 실시간 데이터를 분석해 배관압력 이상을 예측하고 전문가의 의사결정을 돕는 모델을 제안한다. 국내 도시가스 공급업체들 중 하나인 중부도시가스사의 정압기에서 수집하는 실시간 배관압력 데이터와 시간변수, 외부환경변수를 통합해 분석 데이터로 사용한다. 아산시와 천안시에 위치하는 11개 정압기를 분석 대상으로 하며 분 단위 배관압력 예측모델을 구현한다. Random forest, support vector regression(SVR), long-short term memory(LSTM) 알고리즘을 사용해 회귀모델을 구현한 결과 LSTM 모델에서 우수한 성능을 보인다. 아산시 배관압력 예측모델의 경우 LSTM 모델에서 RMSE가 0.011, MAPE가 0.494이며, 천안시 배관압력 예측모델의 경우 LSTM 모델에서 평균제곱근오차(root mean square error, RMSE)가 0.015, 절대평균백분율오차(mean absolute percentage error, MAPE)가 0.668로 가장 낮은 오류율을 보인다.

• 한국공간구조학회논문집
• /
• 제23권3호
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• 한국해양공학회지
• /
• 제34권3호
• /
• pp.167-179
• /
• 2020

Recently, the increasing importance of artificial intelligence (AI) technology has led to its increased use in various fields in the shipbuilding and marine industries. For example, typical scenarios for AI include production management, analyses of ships on a voyage, and motion prediction. Therefore, this study was conducted to predict a response amplitude operator (RAO) through AI technology. It used a neural network based on one of the types of AI methods. The data used in the neural network consisted of the properties of the vessel and RAO values, based on simulating the in-house code. The learning model consisted of an input layer, hidden layer, and output layer. The input layer comprised eight neurons, the hidden layer comprised the variables, and the output layer comprised 20 neurons. The RAO predicted with the neural network and an RAO created with the in-house code were compared. The accuracy was assessed and reviewed based on the root mean square error (RMSE), standard deviation (SD), random number change, correlation coefficient, and scatter plot. Finally, the optimal model was selected, and the conclusion was drawn. The ultimate goals of this study were to reduce the difficulty in the modeling work required to obtain the RAO, to reduce the difficulty in using commercial tools, and to enable an assessment of the stability of medium/small vessels in waves.

• Journal of Animal Science and Technology
• /
• 제64권3호
• /
• pp.531-538
• /
• 2022

In Italy, buffalo mozzarella is a largely sold and consumed dairy product. The fraudulent adulteration of buffalo milk with cheaper and more available milk of other species is very frequent. In the present study, Fourier transform infrared spectroscopy (FTIR), in combination with multivariate analysis by partial least square (PLS) regression, was applied to quantitatively detect the adulteration of buffalo milk with cow milk by using a fully automatic equipment dedicated to the routine analysis of the milk composition. To enhance the heterogeneity, cow and buffalo bulk milk was collected for a period of over three years from different dairy farms. A total of 119 samples were used for the analysis to generate 17 different concentrations of buffalo-cow milk mixtures. This procedure was used to enhance variability and to properly randomize the trials. The obtained calibration model showed an R² ≥ 0.99 (R² cal. = 0.99861; root mean square error of cross-validation [RMSEC] = 2.04; R² val. = 0.99803; root mean square error of prediction [RMSEP] = 2.84; root mean square error of cross-validation [RMSECV] = 2.44) suggesting that this method could be successfully applied in the routine analysis of buffalo milk composition, providing rapid screening for possible adulteration with cow's milk at no additional cost.

• Asian-Australasian Journal of Animal Sciences
• /
• 제30권4호
• /
• pp.546-553
• /
• 2017

Objective: An experiment was conducted to determine digestible energy (DE) and metabolizable energy (ME) of different byproduct feed ingredients fed to growing pigs, and to generate prediction equations for the DE and ME in feed ingredients. Methods: Twelve barrows with an initial mean body weight of 31.8 kg were individually housed in metabolism crates that were equipped with a feeder and a nipple drinker. A $12{\times}10$ incomplete Latin square design was employed with 12 dietary treatments, 10 periods, and 12 animals. A basal diet was prepared to mainly contain the corn and soybean meal (SBM). Eleven additional diets were formulated to contain 30% of each test ingredient. All diets contained the same proportion of corn:SBM ratio at 4.14:1. The difference procedure was used to calculate the DE and ME in experimental ingredients. The in vitro dry matter disappearance for each test ingredient was determined. Results: The DE and ME values in the SBM sources were greater (p<0.05) than those in other ingredients except high-protein distillers dried grains. However, DE and ME values in tapioca distillers dried grains (TDDG) were the lowest (p<0.05). The most suitable regression equations for the DE and ME concentrations (kcal/kg on the dry matter [DM] basis) in the test ingredients were: $DE=5,528-(156{\times}ash)-(32.4{\times}neutral\;detergent\;fiber\;[NDF])$ with root mean square error = 232, $R^2=0.958$, and p<0.001; $ME=5,243-(153 ash)-(30.7{\times}NDF)$ with root mean square error = 277, $R^2=0.936$, and p<0.001. All independent variables are in % on the DM basis. Conclusion: The energy concentrations were greater in the SBM sources and were the least in the TDDG. The ash and NDF concentrations can be used to estimate the energy concentrations in the byproducts from oil-extraction and distillation processes.

• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.242-247
• /
• 2009

지능형 추천 시스템은 사용자의 요청에 응답하는 수동적인 시스템이 아닌 사용자가 원하는 서비스를 제안하는 시스템으로서 최근 콘텐츠 서비스 분야에 많이 개발되고 있다. 이러한 지능형 추천 시스템은 콘텐츠 개인화 서비스에 응용되고 있으며 대표적인 추천기법으로 내용기반과 협업적 필터링 기법이 있다. 본 연구에서는 협업적 필터링 및 퍼지 시스템을 이용하여 추천 시스템의 기반 기술인 예측 시스템을 제안하였다. 제안한 예측 시스템은 사용자의 과거 영화평가 정보를 바탕으로 영화에 대한 평가점수를 예측한다. 영화평가 예측시스템의 성능은 영화 평가점수의 실제값과 예측값의 오차를 RMSE(root mean square error) 방법으로 계산한 후 기존의 영화평가 시스템 RMSE 값과 비교하여 평가하였다. 본 연구를 통해 제안한 영화평가 예측시스템이 추천 시스템의 기반 기술로서 활용이 가능하고 다른 멀티미디어 컨텐츠 서비스 추천에도 응용이 가능할 것으로 기대한다.

• 한국공간구조학회논문집
• /
• 제23권4호
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• 한국환경과학회지
• /
• 제31권7호
• /
• pp.555-567
• /
• 2022

With the introduction of the tele-monitoring system (TMS) in South Korea, monitoring of the concentration of pollutants discharged from nationwide water quality TMS attachments is possible. In addition, the Ministry of Environment is implementing a smart sewage system program that combines ICT technology with wastewater treatment plants. Thus, many institutions are adopting the automatic operation technique which uses process operation factors and TMS data of sewage treatment plants. As a part of the preliminary study, a multilayer perceptron (MLP) analysis method was applied to TMS data to identify predictability degree. TMS data were designated as independent variables, and each pollutant was considered as an independent variables. To verify the validity of the prediction, root mean square error analysis was conducted. TMS data from two public sewage treatment plants in Chungnam were used. The values of RMSE in SS, T-N, and COD predictions (excluding T-P) in treatment plant A showed an error range of 10%, and in the case of treatment plant B, all items showed an error exceeding 20%. If the total amount of data used MLP analysis increases, the predictability of MLP analysis is expected to increase further.

• 터널과지하공간
• /
• 제31권6호
• /
• pp.508-519
• /
• 2021

본 연구에서는 발파 시 사람과 주변 환경에 영향을 끼치는 발파진동(peak particle velocity, PPV)을 예측하는 모델을 개발하였다. PPV를 예측하기 위해 kNN(k-nearest neighbors), CART(classification and regression tree), SVR(support vector regression), PSO(particle swarm optimization)-SVR 알고리즘을 이용한 4가지 머신러닝 모델을 개발하고 상호 비교하였다. 머신러닝 모델을 훈련하기 위해 경상남도 창원시에 있는 욕망산을 연구지역으로 선정하고 1048개의 발파 데이터를 획득하였다. 발파 데이터는 천공장, 저항선, 공간격, 최대지발장약량, 비장약량, 총공수, 에멀전비율, 이격거리, PPV로 구성되었다. 훈련된 모델들의 성능을 평가하기 위한 지표 값으로 MAE(mean absolute error), MSE(mean squared error), RMSE(root mean squared error)를 사용하였다. 평가결과 PSO-SVR 모델이 MAE, MSE, RMSE가 각각 0.0348, 0.0021, 0.0458으로 가장 우수한 예측 성능을 나타냈다. 마지막으로 개발된 머신러닝 모델을 이용하여 주변 환경에 영향을 끼치는 정도를 예측하는 방법을 제시하였다.

• 한국전자통신학회논문지
• /
• 제18권6호
• /
• pp.1151-1156
• /
• 2023

본 논문은 초기 리튬이온 배터리의 충·방전 데이터를 활용하여 리튬이온 배터리의 잔존 수명을 예측할 수 있는 딥러닝 모델을 제시한다. PNP(Positive and Negative Perceptron) 모델을 사용하여 DMP(Deep learning Model using PNP model)를 구축하였으며, DMP의 성능을 증명하기 위해 LSTM 모델을 사용하여 DML(Deep learning Model using LSTM model)을 구성하였다. DMP와 DML의 리튬이온 배터리의 잔존 수명 예측 성능을 비교하며, 오차 측정 방법은 RMSE(Root Mean Square Error)와 RMSPE(Root Mean Square Percentage Error)이다. 시험 데이터로 오차를 측정한 결과 DMP와 DML의 RMSE 차이는 144.62[Cycle]이며, RMSPE 차이는 3.37[%]로 DMP의 오차가 낮게 측정되었다. 이를 통해 우리는 DMP의 성능이 높은 것으로 증명하였으며, 이는 리튬이온 배터리 분야에서 PNP 모델이 LSTM 모델보다 성능이 뛰어남을 나타내었다.