• Current Photovoltaic Research
• /
• v.11 no.1
• /
• pp.27-33
• /
• 2023

In this paper, a machine learning model by using a regression algorithm is proposed to estimate the power generation performance of the BIPV system. The physical model formula for estimating the generation performance and the proposed model were compared and analyzed. For the physical model formula, simple efficiency model, temperature correction model, and regressive physics model for changing an irradiance were used. As a result, when comparing the regressive physics model for changing an irradiance and the proposed model with the actual generation measured data, the respective RMSE values are 0.1497 kW, 0.0451 kW and the accuracy values are 86.44%, and 96.56%. Therefore, the proposed model implemented in this experiment can be useful in estimating power generation.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.23-31
• /
• 2023

Research and interest in sustainable printing are increasing in the packaging printing industry. Currently, predicting the amount of ink required for each work is based on the experience and intuition of field workers. Suppose the amount of ink produced is more than necessary. In this case, the rest of the ink cannot be reused and is discarded, adversely affecting the company's productivity and environment. Nowadays, machine learning models can be used to figure out this problem. This study compares the ink usage prediction machine learning models. A simple linear regression model, Multiple Regression Analysis, cannot reflect the nonlinear relationship between the variables required for packaging printing, so there is a limit to accurately predicting the amount of ink needed. This study has established various prediction models which are based on CART (Classification and Regression Tree), such as Decision Tree, Random Forest, Gradient Boosting Machine, and XGBoost. The accuracy of the models is determined by the K-fold cross-validation. Error metrics such as root mean squared error, mean absolute error, and R-squared are employed to evaluate estimation models' correctness. Among these models, XGBoost model has the highest prediction accuracy and can reduce 2134 (g) of wasted ink for each work. Thus, this study motivates machine learning's potential to help advance productivity and protect the environment.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.218-233
• /
• 2022

The long-term (1986~2020) predictability of the number of days of heat and cold damages for each growth stage of soybean is evaluated using the daily maximum and minimum temperature (Tmax and Tmin) data produced by Pusan National University Coupled General Circulation Model (PNU CGCM)-Weather Research and Forecasting (WRF). The Predictability evaluation methods for the number of days of damages are Normalized Standard Deviations (NSD), Root Mean Square Error (RMSE), Hit Rate (HR), and Heidke Skill Score (HSS). First, we verified the simulation performance of the Tmax and Tmin, which are the variables that define the heat and cold damages of soybean. As a result, although there are some differences depending on the month starting with initial conditions from January (01RUN) to May (05RUN), the result after a systematic bias correction by the Variance Scaling method is similar to the observation compared to the bias-uncorrected one. The simulation performance for correction Tmax and Tmin from March to October is overall high in the results (ENS) averaged by applying the Simple Composite Method (SCM) from 01RUN to 05RUN. In addition, the model well simulates the regional patterns and characteristics of the number of days of heat and cold damages by according to the growth stages of soybean, compared with observations. In ENS, HR and HSS for heat damage (cold damage) of soybean have ranged from 0.45~0.75, 0.02~0.10 (0.49~0.76, -0.04~0.11) during each growth stage. In conclusion, 01RUN~05RUN and ENS of PNU CGCM-WRF Chain have the reasonable performance to predict heat and cold damages for each growth stage of soybean in South Korea.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.111-125
• /
• 2011

Clustering is a process of grouping similar or relevant documents into a cluster and assigning a meaningful concept to the cluster. By this process, clustering facilitates fast and correct search for the relevant documents by narrowing down the range of searching only to the collection of documents belonging to related clusters. For effective clustering, techniques are required for identifying similar documents and grouping them into a cluster, and discovering a concept that is most relevant to the cluster. One of the problems often appearing in this context is the detection of a complex concept that overlaps with several simple concepts at the same hierarchical level. Previous clustering methods were unable to identify and represent a complex concept that belongs to several different clusters at the same level in the concept hierarchy, and also could not validate the semantic hierarchical relationship between a complex concept and each of simple concepts. In order to solve these problems, this paper proposes a new clustering method that identifies and represents complex concepts efficiently. We developed the Hierarchical Overlapping Clustering (HOC) algorithm that modified the traditional Agglomerative Hierarchical Clustering algorithm to allow overlapped clusters at the same level in the concept hierarchy. The HOC algorithm represents the clustering result not by a tree but by a lattice to detect complex concepts. We developed a system that employs the HOC algorithm to carry out the goal of complex concept detection. This system operates in three phases; 1) the preprocessing of documents, 2) the clustering using the HOC algorithm, and 3) the validation of semantic hierarchical relationships among the concepts in the lattice obtained as a result of clustering. The preprocessing phase represents the documents as x-y coordinate values in a 2-dimensional space by considering the weights of terms appearing in the documents. First, it goes through some refinement process by applying stopwords removal and stemming to extract index terms. Then, each index term is assigned a TF-IDF weight value and the x-y coordinate value for each document is determined by combining the TF-IDF values of the terms in it. The clustering phase uses the HOC algorithm in which the similarity between the documents is calculated by applying the Euclidean distance method. Initially, a cluster is generated for each document by grouping those documents that are closest to it. Then, the distance between any two clusters is measured, grouping the closest clusters as a new cluster. This process is repeated until the root cluster is generated. In the validation phase, the feature selection method is applied to validate the appropriateness of the cluster concepts built by the HOC algorithm to see if they have meaningful hierarchical relationships. Feature selection is a method of extracting key features from a document by identifying and assigning weight values to important and representative terms in the document. In order to correctly select key features, a method is needed to determine how each term contributes to the class of the document. Among several methods achieving this goal, this paper adopted the $x^2$�� statistics, which measures the dependency degree of a term t to a class c, and represents the relationship between t and c by a numerical value. To demonstrate the effectiveness of the HOC algorithm, a series of performance evaluation is carried out by using a well-known Reuter-21578 news collection. The result of performance evaluation showed that the HOC algorithm greatly contributes to detecting and producing complex concepts by generating the concept hierarchy in a lattice structure.

• Journal of Chest Surgery
• /
• v.32 no.2
• /
• pp.124-129
• /
• 1999

Background: Ventricular septal defect(VSD) that causes pulmonary hypertension increase right ventricular workload. Echocardiographic assessment of right ventricular systolic time interval (RVSTI) has been used to predict pulmonary artery pressure in various cardiopulmonary diseases. This study was undertaken in infants with simple VSD to observe the alteration of the right ventricular workload through the changes of RVSTI after repair of VSD. Material and Method: We evaluated heart rate, the ratio of the left atrium/aortic root diameter (LA/Ao), right ventricular pre-ejection period(RVPEP), right ventricular ejection time(RVET), and its ratio(RVPEP/RVET) as a predictor of right ventricular workload in 12 children with simple VSD. These were measured three times at the preoperative period, at the 3 month and between 6 month and 1 year(average 9.5${\pm}$1.8month) after repair of VSD by M-mode & Doppler echocardiograph from the pulmonic valve echogram. Result: Heart rate was decreased significantly after repair(137.1${\pm}$13.7 vs 114.4${\pm}$21.1 and 104.1${\pm}$10.2, p<0.01). LA/Ao ratio was decreased significantly after repair(1.71${\pm}$0.32 vs 1.47${\pm}$0.33 and 1.39${\pm}$0.23, p<0.05). RVPEP/RVET were decreased after repair (0.38${\pm}$0.09 vs 0.32${\pm}$0.08 and 0.29${\pm}$0.09, p<0.01). Heart rate corrected RVPEP/RVET were significantly decreased only after 6 months(0.32${\pm}$0.03 vs 0.30${\pm}$0.05 and 0.28${\pm}$0.06, p<0.05). Conclusion: We found elevated right ventricular workload was progressively decreased until more than 6 months after repair and the RVSTI may serve a useful guide in postoperative care for children with VSD.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.24 no.2
• /
• pp.213-230
• /
• 2008

The aim of this study was to analyze the initial movement and the stress distribution of each tooth and periodontal ligament during the lingual lever-arm retraction of 6 maxillary incisors using FEA. Two kinds of finite element models were produced: 2-properties model (simple model) and 24-properties model (multi model) according to the material property assignment. The subject was an adult male of 23 years old. The DICOM images through the CT of the patient were converted into the 3D image model of a skull using the Mimics (version 10.11, Materialise's interactive Medical Image Control System, Materialise, Belgium). After series of calculating, remeshing, exporting, importing process and volume mesh process was performed, FEA models were produced. FEA models are consisted of maxilla, maxillary central incisor, lateral incisor, canine, periodontal ligaments and lingual traction arm. The boundary conditions fixed the movements of posterior, sagittal and upper part of the model to the directions of X, Y, Z axis respectively. The model was set to be symmetrical to X axis. Through the center of resistance of maxilla complex, a retraction force of 200g was applied horizontally to the occlusal plane. Under this conditions, the initial movements and stress distributions were evaluated by 3D FEA. In the result, the amount of posterior movement was larger in the multi model than in the simple model as well as the amount of vertically rotation. The pattern of the posterior movement in the central incisors and lateral incisors was controlled tipping movement, and the amount was larger than in the canine. But the amount of root movement of the canine was larger than others. The incisor rotated downwardly and the canines upwardly around contact points of lateral incisor and canine in the both models. The values of stress are similar in the both simple and multi model.

• Journal of Korean Society of Steel Construction
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2010

According to the capacity design concept which forms the basis of the current steel seismic codes, the braces in concentrically braced frames (CBFs) should dissipate seismic energy through cyclic tension yielding and cyclic compression buckling while the beams and the columns should remain elastic. Brace buckling in inverted V-braced frames induces unbalanced vertical forces which, in turn, impose the additional beam moments and column axial forces. However, due to difficulty in predicting the location of buckling stories, the most conservative approach implied in the design code is to estimate the column axial forces by adding all the unbalanced vertical forces in the upper stories. One alternative approach, less conservative and recommended by the current code, is to estimate the column axial forces based on the amplified seismic load expected at the mechanism-level response. Both are either too conservative or lacking technical foundation. In this paper, three combination rules for a rational estimation of the column axial forces were proposed. The idea central to the three methods is to detect the stories of high buckling potential based on pushover analysis and dynamic behavior. The unbalanced vertical forces in the stories detected as high buckling potential are summed in a linear manner while those in other stories are combined by following the SRSS(square root of sum of squares) rule. The accuracy and design advantage of the three methods were validated by comparing extensive inelastic dynamic analysis results. The mode-shape based method(MSBM), which is both simple and accurate, is recommended as the method of choice for practicing engineers among the three.

• Spatial Information Research
• /
• v.22 no.1
• /
• pp.55-63
• /
• 2014

Near surface air temperature data which are one of the essential factors in hydrology, meteorology and climatology, have drawn a substantial amount of attention from various academic domains and societies. Meteorological observations, however, have high spatio-temporal constraints with the limits in the number and distribution over the earth surface. To overcome such limits, many studies have sought to estimate the near surface air temperature from satellite image data at a regional or continental scale with simple regression methods. Alternatively, we applied various Kriging methods such as ordinary Kriging, universal Kriging, Cokriging, Regression Kriging in search of an optimal estimation method based on near surface air temperature data observed from automatic weather stations (AWS) in South Korea throughout 2010 (365 days) and MODIS land surface temperature (LST) data (MOD11A1, 365 images). Due to high spatial heterogeneity, auxiliary data have been also analyzed such as land cover, DEM (digital elevation model) to consider factors that can affect near surface air temperature. Prior to the main estimation, we calculated root mean square error (RMSE) of temperature differences from the 365-days LST and AWS data by season and landcover. The results show that the coefficient of variation (CV) of RMSE by season is 0.86, but the equivalent value of CV by landcover is 0.00746. Seasonal differences between LST and AWS data were greater than that those by landcover. Seasonal RMSE was the lowest in winter (3.72). The results from a linear regression analysis for examining the relationship among AWS, LST, and auxiliary data show that the coefficient of determination was the highest in winter (0.818) but the lowest in summer (0.078), thereby indicating a significant level of seasonal variation. Based on these results, we utilized a variety of Kriging techniques to estimate the surface temperature. The results of cross-validation in each Kriging model show that the measure of model accuracy was 1.71, 1.71, 1.848, and 1.630 for universal Kriging, ordinary Kriging, cokriging, and regression Kriging, respectively. The estimates from regression Kriging thus proved to be the most accurate among the Kriging methods compared.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.4
• /
• pp.238-249
• /
• 2019

The evapotranspiration is estimated based on weather factors such as temperature, wind speed and humidity, and the Hargreaves equation is a simple equation for calculating evapotranspiration using temperature data. However, the Hargreaves equation tends to be underestimated in areas with wind speeds above 3 m s^-1 and overestimated in areas with high relative humidity. The study was conducted to determine Hargreaves equation coefficient in 82 regions in Korea by comparing evapotranspiration determined by modified Hargreaves equation and the Penman-Monteith equation for the time period of 2008~2018. The modified Hargreaves coefficients for 50 inland areas were estimated to be 0.00173~0.00232(average 0.00196), which is similar to or lower than the default value 0.0023. On the other hand, there are 32 coastal areas, and the modified coefficients ranged from 0.00185 to 0.00303(average 0.00234). The east coastal area was estimated to be similar to or higher than the default value, while the west and south coastal areas showed large deviations by area. As results of estimating the evapotranspiration by the modified Hargreaves coefficient, root mean square error(RMSE) is reduced from 0.634~1.394(average 0.857) to 0.466~1.328(average 0.701), and Nash-Sutcliffe Coefficient(NSC) increased from -0.159~0.837(average 0.647) to -0.053~0.910(average 0.755) compared with original Hargreaves equation. Therefore, we confirmed that the Hargreaves equation can be overestimated or underestimated compared to the Penman-Monteith equation, and expected that it will be able to calculate the high accuracy evapotranspiration using the modified Hargreaves equation. This study will contribute to water resources planning, irrigation schedule, and environmental management.

• Korean Journal of Medicinal Crop Science
• /
• v.2 no.1
• /
• pp.7-13
• /
• 1994

This study was conducted to investigate the relationships between yearly variations of climatic factors and yearly variations of productivity in Alisma plantago L. In addition, correlation coefficients among yield and yield components were estimated. The data of yield and yield components were collected from the Statistical Year Book of Seungju province, Reserach Report of Seungju Extension Station of Rural Development Administration, and farmers for 10 years from 1983 to 1992. The meteorological data gathered at the Seungju Weather Station for the same period were used to find out the relationships between climatic factors and productivity. Yearly variation of the amount of precipitation in October and the minimum temperature in November were large with coefficients of variation(C.V.) of 106.44, 144.08%, respectively, but the variation of the average temperature, maximum temperature, minimum temperature from July to September were relatively small. Fresh weight and dry weight of roots vary greatly with C. V. of 30.62, 31.85%, respectivly. Plant height and stem length show more or less small C. V. of 5.51, 6. 26%, respectively and leaf width, leaf length, number of stems and root diameter show still less variation. Correlation coefficients between maximum temperature in November and plant height, stem diamter, number of stems, root diamter and dry weight of roots are positively significant at the 5% level. There are high signficant positive correlations observed, between yield and yield components. The maximum temperature would be used as a predictive variable for the estimation of dry weight of roots and number of stems. Simple linear regression equations by the least square method are estimated for number of stems $(Y_1)$ and the maximum temperature in November(X) as $Y_1=4.7114+0.5333\;X\;(R^2=0.4410)$, and for dry weight of roots$(Y_2)$ and the maximum temperature in November(X) as $Y_2=55.0405+14.3233\;X\;(R^2=0.4511)$