• 한국도로학회논문집
• /
• 제16권5호
• /
• pp.173-182
• /
• 2014

PURPOSES : The purpose of the study is to a) explore the operating speed of trucks on rural highways affected by road geometry, and thereby b) develop a predictive model for the operating speed of trucks on rural highways. METHODS : Considering that most of the existing studies have focused on cars, the current study aimed to predict the operating speed of trucks by conducting linear regression analysis on the speed data of trucks operating on the linear-curved-linear portions of the road as a single set. RESULTS : The operating speed in the plane curve portion increased with the length of the curve, and decreased with a lower vertical grade and a smaller curve radius. In the straight plane portion, the operating speed increased with a larger curve radius(upstream), and decreased with an increase in the change of the vertical grade, depending on the length of the vertical curve. CONCLUSIONS : This study developed estimation models of truck for operational speed and evaluated the degree of safety for horizontal and vertical alignments simultaneous. In order to represent whole area of the rural highway, the models should be ew-analyzed with vast data related with road alignment factor in the near future.

• 한국환경복원기술학회지
• /
• 제19권6호
• /
• pp.19-30
• /
• 2016

The projection of climate-related range shift is critical information for conservation planning of Korean fir (Abies koreana E. H. Wilson). We first modeled the distribution of Korean fir under current climate condition using five single-model species distribution models (SDMs) and the pre-evaluation weighted ensemble method and then predicted the distributions under future climate conditions projected with HadGEM2-AO under four $CO_2$ emission scenarios, the Representative Concentration Pathways (RCP) 2.6, 4.5, 6.0 and 8.5. We also investigated the predictive uncertainty stemming from five individual algorithms and four $CO_2$ emission scenarios for better interpretation of SDM projections. Five individual algorithms were Generalized linear model (GLM), Generalized additive model (GAM), Multivariate adaptive regression splines (MARS), Generalized boosted model (GBM) and Random forest (RF). The results showed high variations of model performances among individual SDMs and the wide range of diverging predictions of future distributions of Korean fir in response to RCPs. The ensemble model presented the highest predictive accuracy (TSS = 0.97, AUC = 0.99) and predicted that the climate habitat suitability of Korean fir would increase under climate changes. Accordingly, the fir distribution could expand under future climate conditions. Increasing precipitation may account for increases in the distribution of Korean fir. Increasing precipitation compensates the negative effects of increasing temperature. However, the future distribution of Korean fir is also affected by other ecological processes, such as interactions with co-existing species, adaptation and dispersal limitation, and other environmental factors, such as extreme weather events and land-use changes. Therefore, we need further ecological research and to develop mechanistic and process-based distribution models for improving the predictive accuracy.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.786-796
• /
• 2014

This paper presents a new approach to design a robust tracking controller for linear time-invariant systems with uncertain time-delay. By introducing the model following control (MFC) structure which consists of two loops in nature, we show that the controller is capable of having a predictive control action and effectively tracking the reference output with a desired transient response as well. Three design techniques to achieve good tracking performance are suggested. It is also analytically shown that the tracking performance of the proposed scheme is more robust than that of typical single-loop feedback structure. An illustrative example is given to compare the tracking performances of the proposed methods with a single loop method.

• Industrial Engineering and Management Systems
• /
• 제1권1호
• /
• pp.73-78
• /
• 2002

In this paper, we propose a constrained optimization model for conjoint analysis (a preference decomposition technique) to improve parameter estimation by restricting the relative importance of the attributes to an extent as decided by the respondents. Quite simply, respondents are asked to provide some pairwise attribute comparisons that are then incorporated as additional constraints in a linear programming model that estimates the partial preference values. This data collection method is typical in the analytic hierarchy process. Results of a simulation study show the new model can improve the predictive accuracy in partial value estimation by ordinal east squares (OLS) regression.

• Animal Bioscience
• /
• 제37권4호
• /
• pp.622-630
• /
• 2024

Objective: Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP). Methods: Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip. Results: The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits. Conclusion: This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

• Child Health Nursing Research
• /
• 제16권1호
• /
• pp.84-92
• /
• 2010

Purpose: One of the main reasons why mothers quit breast feeding is that the volume of breast milk is inadequate due to insufficiency in suckling. We believe suckling experience may be a factor affecting nipple confusion. So an alternative feeding method, namely cup, spoon, finger, or nasogastric tube feeding may be needed to prevent nipple confusion. The purpose of this study was to construct a predictive model for demand for alternative feeding education by nurses. Methods: A descriptive design with structured self-report questionnaires was used for this study. Data from 175 nurses working in hospitals in Busan were collected between April 1 and 15, 2009. Data were analyzed by decision tree method, one of the data mining techniques using SAS 9.1 and Enterprise Miner 4.3 program. Results: Of the nurses, 81.1% demanded alternative feeding education and 5 factors showed that most of them expressed intention to pay, desire to know about alternative feeding, age, and learning experience. From these results, the derived model is considered appropriative for explaining and predicting demand for alternative feeding education. Conclusion: This confirms that knowledge and compliance in alternative breast feeding for newborn babies should be correct and any inaccuracies or insufficient information should be supplemented.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.84-92
• /
• 2021

Care services are a significant asset in human life. Care in its overall nature focuses on human needs and covers several aspects such as health care, homes, personal care, and education. In fact, care deals with many dimensions: physical, psychological, and social interconnections. Very little information is available on estimating the cost of care services that provided to orphans and abandoned children. Prediction of the cost of the care system delivered by governmental or non-governmental organizations to support orphans and abandoned children is increasingly needed. The purpose of this study is to analyze the care cost for orphanage organizations in Saudi Arabia to forecast the cost as well as explore the most influence factor on the cost. By using business analytic process that applied statistical and machine learning techniques, we proposed a model includes simple linear regression, Naive Bayes classifier, and Random Forest algorithms. The finding of our predictive model shows that Naive Bayes has addressed the highest accuracy equals to 87% in predicting the total care cost. Our model offers predictive approach in the perspective of business analytics.

• 한국지리정보학회지
• /
• 제24권1호
• /
• pp.92-111
• /
• 2021

미세먼지는 질병, 산업·경제에 부정적인 영향을 미치고 있어 국민들은 미세먼지에 대해 예민하게 반응하고 있다. 따라서 미세먼지의 발생을 예측할 수 있다면, 미리 대응책을 마련할 수 있어 생활과 경제에 도움이 될 수 있다. 미세먼지의 발생은 기상과 미세먼지 배출원의 밀집 정도에 영향을 받는다. 산업부문은 미세먼지 배출량이 가장 많으며, 그 중에 산단은 공장들이 미세먼지 배출원이 되어 더 많은 미세먼지를 배출하는 문제가 있다. 본 연구는 지방도시에서 노후산업단지가 있는 지역을 선정하여, 미세먼지를 일으키는 요인을 탐색하고, 미세먼지 발생을 예측할 수 있는 예측모형을 개발하고자 한다. 기상 데이터와 미세먼지 관련 데이터를 활용하였고, 다중회귀분석을 통해 미세먼지 발생에 영향을 미치는 변수를 추출하였다. 이를 토대로 머신러닝 회귀학습기 모형으로 학습하여 예측력이 높은 모형을 추출하였고, 검증용 데이터를 이용하여 예측 모형의 성능을 검증하였다. 그 결과, 예측력이 높은 모형은 선형회귀모형, 가우스 과정 회귀모형, 서포트 벡터 머신으로 나타났으며, 훈련용 데이터의 비율과 예측력은 비례하지 않은 것으로 나타났다. 또한 예측치와 실측치 차이의 평균치는 크지 않지만, 미세먼지 실측치가 높을 때, 예측력이 다소 떨어지는 것으로 나타났다. 본 연구의 결과는 지자체 데이터 허브를 통해 기상데이터와 관련 도시 빅데이터를 결합함으로써 보다 체계적이고 정밀한 미세먼지 예측 서비스로 개발이 가능할 것이며, 스마트산단의 발전을 촉진하는 계기가 될 것이다.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4042-4051
• /
• 2021

In this work, we applied a multilevel modeling technique to estimate the diametral creep in the pressure tubes of Korean Canada Deuterium Uranium (CANDU) units. Data accumulated from in-service inspections were used to develop the model. To confirm the strength of the multilevel models, a 2-level multilevel model considering the relationship between channels for a CANDU unit was compared with existing linear models. The multilevel model exhibited a very robust prediction accuracy compared to the linear models with different data pooling methods. A 3-level multilevel model, which considered individual bundles, channels, and units, was also implemented. The influence of the channel installation direction was incorporated into the three-stage multilevel model. For channels that were previously measured, the developed 3-level multilevel model exhibited a very good predictive power, and the prediction interval was very narrow. However, for channels that had never been measured before, the prediction interval widened considerably. This model can be sufficiently improved by the accumulation of more data and can be applied to other CANDU units.