• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.79-84
• /
• 2021

A feature extraction method capable of reflecting features well while mainaining the properties of data is required in order to process high-dimensional data. The principal component analysis method that converts high-level data into low-dimensional data and express high-dimensional data with fewer variables than the original data is a representative method for feature extraction of data. In this study, we propose a principal component analysis method based on adaptive correlation when selecting principal component variables in principal component analysis for data feature extraction when the data is high-dimensional. The proposed method analyzes the principal components of the data by adaptively reflecting the correlation based on the correlation between the input data. I want to exclude them from the candidate list. It is intended to analyze the principal component hierarchy by the eigen-vector coefficient value, to prevent the selection of the principal component with a low hierarchy, and to minimize the occurrence of data duplication inducing data bias through correlation analysis. Through this, we propose a method of selecting a well-presented principal component variable that represents the characteristics of actual data by reducing the influence of data bias when selecting the principal component variable.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.861-866
• /
• 2022

Seoul introduced the shared bicycle system, "Seoul Public Bike" in 2015 to help reduce traffic volume and air pollution. Hence, to solve various problems according to the supply and demand of the shared bicycle system, "Seoul Public Bike," several studies are being conducted. Most of the research is a strategic "Bicycle Rearrangement" in regard to the imbalance between supply and demand. Moreover, most of these studies predict demand by grouping features such as weather or season. In previous studies, demand was predicted by time-series-analysis. However, recently, studies that predict demand using deep learning or machine learning are emerging. In this paper, we can show that demand prediction can be made a little better by discovering new features or ordering the importance of various features based on well-known feature-patterns. In this study, by ordering the selection of new features or the importance of the features, a better coefficient of determination can be obtained even if the well-known deep learning or machine learning or time-series-analysis is exploited as it is. Therefore, we could be a better one for demand prediction.

• Animal Bioscience
• /
• v.36 no.9
• /
• pp.1327-1335
• /
• 2023

Objective: When evaluating individuals with the same parent and no phenotype by pedigree best linear unbiased prediction (BLUP), it is difficult to explain carcass grade difference and select individuals because they have the same value in pedigree BLUP (PBLUP). However, single step GBLUP (ssGBLUP), which can estimate the breeding value suitable for the individual by adding genotype, is more accurate than the existing method. Methods: The breeding value and accuracy were estimated with pedigree BLUP and ssGBLUP using pedigree and genotype of 408 Hanwoo cattle from 16 families with the same parent among siblings produced by fertilized egg transplantation. A total of 14,225 Hanwoo cattle with pedigree, genotype and phenotype were used as the reference population. PBLUP obtained estimated breeding value (EBV) using the pedigree of the test and reference populations, and ssGBLUP obtained genomic EBV (GEBV) after constructing and H-matrix by integrating the pedigree and genotype of the test and reference populations. Results: For all traits, the accuracy of GEBV using ssGBLUP is 0.18 to 0.20 higher than the accuracy of EBV obtained with PBLUP. Comparison of EBV and GEBV of individuals without phenotype, since the value of EBV is estimated based on expected values of alleles passed down from common ancestors. It does not take Mendelian sampling into consideration, so the EBV of all individuals within the same family is estimated to be the same value. However, GEBV makes estimating true kinship coefficient based on different genotypes of individuals possible, so GEBV that corresponds to each individual is estimated rather than a uniform GEBV for each individual. Conclusion: Since Hanwoo cows bred through embryo transfer have a high possibility of having the same parent, if ssGBLUP after adding genotype is used, estimating true kinship coefficient corresponding to each individual becomes possible, allowing for more accurate estimation of breeding value.

• Journal of Korean Society of Forest Science
• /
• v.107 no.2
• /
• pp.193-204
• /
• 2018

This study was carried out to select the optimal method of competition index computation according to the competitor selection methods and distant-dependent competition index models, and to analyze the characteristics of competition indices in terms of thinning intensity and tree density targeting Pinus densiflora, Pinus koraiensis, and Larix kaempferi, which are the major coniferous species in Korea. Data was the re-investigated tree information from 240 permanent plots of 80 sites in the stands of P. densiflora, P. koraiensis, and L. kaempferi, which were located in the national forest of Gangwon and North Gyeongsang provinces. The number of subject trees with competition index calculated were 1126 trees for P. densiflora, 4093 trees for P. koraiensis, and 3399 trees for L. kaempferi. For the best competition index computation method, three kinds of competitor selection methods were considered: basal area factor, angle of height, angle of height to crown base. Also, six kinds of competition index models were compared: Lorimer, Martin-EK, Braathe, Heygi, Daniels, and Modified Daniels, which was developed in this study. Correlation coefficient was the best when the competitor selection method of basal area factor $4m^2/ha$ and the competition index model of Modified Daniels were used, and thus, it was selected as the best method for computing competition index. According to the best method by stand characteristics, competition index decreased in all species as thinning intensity was high and tree density was low.

• Journal of Korea Water Resources Association
• /
• v.50 no.3
• /
• pp.191-200
• /
• 2017

A robust parameter set (ROPS) selection framework for an unsteady flow model was developed by combining Pareto optimums obtained by outcomes of model calibration using multi-site observations with the minimax regret approach (MRA). The multi-site calibration problem which is a multi-objective problem was solved by using an aggregation approach which aggregates the weighted criteria related to different sites into one measure, and then performs a large number of individual optimization runs with different weight combinations to obtain Pareto solutions. Roughness parameter structure which can describe the variation of Manning's n with discharges and sub-reaches was proposed and the related coefficients were optimized as model parameters. By applying the MRA which is a decision criterion, the Pareto solutions were ranked based on the obtained regrets related to each Pareto solution, and the top-rated one due to the lowest aggregated regrets of both calibration and validation was determined as the only ROPS. It was found that the determination of variable roughness and the corresponding standardized RMSEs at the two gauging stations varies considerably depending on the combinations of weights on the two sites. This method can provide the robust parameter set for the multi-site calibration problems in hydrologic and hydraulic models.

• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.214-224
• /
• 2024

Valves play an essential role in a chemical plant such as regulating fluid flow and pressure. Therefore, optimal selection of the valve size and type is essential task. Valve size and type have been selected based on theoretical formulas about calculating valve sizing coefficient (Cv). However, this approach has limitations such as requiring expert knowledge and consuming substantial time and costs. Herein, this study developed a model for predicting valve sizes and types using machine learning. We developed models using four algorithms: ANN, Random Forest, XGBoost, and Catboost and model performances were evaluated using NRMSE & R² score for size prediction and F1 score for type prediction. Additionally, a case study was conducted to explore the impact of phases on valve selection, using four datasets: total fluids, liquids, gases, and steam. As a result of the study, for valve size prediction, total fluid, liquid, and gas dataset demonstrated the best performance with Catboost (Based on R², total: 0.99216, liquid: 0.98602, gas: 0.99300. Based on NRMSE, total: 0.04072, liquid: 0.04886, gas: 0.03619) and steam dataset showed the best performance with RandomForest (R²: 0.99028, NRMSE: 0.03493). For valve type prediction, Catboost outperformed all datasets with the highest F1 scores (total: 0.95766, liquids: 0.96264, gases: 0.95770, steam: 1.0000). In Engineering Procurement Construction industry, the proposed fluid-specific machine learning-based model is expected to guide the selection of suitable valves based on given process conditions and facilitate faster decision-making.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.23 no.3
• /
• pp.108-114
• /
• 1997

The skin permeation study has two meanings in cosmetics. One is how to promote the skin permeation of active meterials for improving their bioavailabilities and the other is how to decrease it of irritants for reducing their skin side effects. In this study, we selected methyl paraben, one of the preservatives, as a model irritant and tried to reduce the skin irritation by the decrease of skin permeation. Furthermore, the relationship between skin permeation and skin primary irritation was discussed. For in vitro skin permeation experiments, Franz type diffusion cells and the excised skin of female hairless mouse from 8 weeks old were used. The donor compartment was charged with oil only or O/W emulsion containing 0.3% MP. We selected 19 oils, including esters, triglycerides, plant oils, hydrocarbons, and alchols, which are broadly used in cosmetics. We evaluated with female guinea pig. The skin permeahility of MP from the oils showed following order: ester oils > triglycerides > plant oils > hydrocarbons > alcohols. We considered that this result was based on the different effect of each oil on the barrier function of stratum corneum. In O/W emulsion containing each oil, the skin permeability of MP decreased as the oil/water partition coefficient of MP increased. The skin primary irritation increased as the skin permeability of MP increased. In conclusion, we suggest that the skin irritation could be reduced by the decrease of skin permeability of MP, which may be obtained by the good selection of oils in cosmetic preparations.

• Journal of Korean Academy of Nursing
• /
• v.41 no.3
• /
• pp.313-324
• /
• 2011

Purpose: The study was done to develop a dignified dying scale for Korean adults. Methods: The process included construction of a conceptual framework, generation of initial items, verification of content validity, selection of secondary items, preliminary study, and extraction of final items. The participants were 428 adults who lived in one of 3 Korean metropolitan cities: Seoul, Daegu, and Busan. Item analysis, factor analysis, criterion related validity, and internal consistency were used to analyze the data. Data collection was done from March to June 2010. Results: Thirty items were selected for the final scale, and categorized into 5 factors explaining 54.5% of the total variance. The factors were labeled as maintaining emotional comfort (10 items), arranging social relationship (9 items), avoiding suffering (3 items), maintaining autonomous decision making (4 items), and role preservation (4 items). The scores for the scale were significantly correlated with personal meanings of death scale. Cronbach's alpha coefficient for the 30 items was .92. Conclusion: The above findings indicate that the dignified dying scale has a good validity and reliability when used with Korean adults.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.22 no.3
• /
• pp.366-375
• /
• 2016

Purpose: This study was conducted to identify factors which influence suicidal ideation in students in girls' high schools. Methods: The participants were 202 students attending a girls' high school and a specialized girls' high school in D city. Data were collected from October 8 to December 23, 2013. Research tools were suicidal ideation, existential spiritual well-being, interpersonal relations, and depression. Data were analyzed using t-test, one-way ANOVA with Scheffe-test, Pearson's correlation coefficient, and multiple regression by stepwise selection with SPSS/WIN 12.0. Results: Suicidal ideation was negatively correlated with existential spiritual well-being, interpersonal relations, and positively correlated with depression. Effective variables were depression (${\beta}=0.54$, p<.001), existential spiritual well-being (${\beta}=-0.22$, p=.001), and grades (${\beta}=-0.10$, p=.042). These variables explained 52% of the variance in suicidal ideation. Conclusion: Based on the outcomes of this study, it is necessary to design an intervention program that teachers and community mental health nurses can use to increase existential spiritual well-being and decrease the depression and suicidal ideation for students in girls' high schools.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.23 no.2
• /
• pp.165-174
• /
• 2017

Purpose: This study was done to develop and to evaluate an integrative palliative care scale for cancer patients. Methods: The process included construction of a conceptual framework, generation of initial items, verification of content validity, selection of secondary items, preliminary study, and extraction of final items. The participants were 173 cancer patients in Daegu and Gyeongbuk. Item analysis, factor analysis, criterion related validity, and internal consistency were used to analyze the data. Results: Eighteen items were selected for the final scale, and categorized into 3 factors explaining 58.3% of total variance. The factors were labeled as social/environmental palliative care (9 items), psychological palliative care (4 items), and physical palliative care (3 items), and spiritually palliative care (2 items). The scores for the scale were significantly correlated with the quality of life of cancer patients. Cronbach's alpha coefficient for the 18 items was .88. Conclusion: The above findings indicate that the integrative palliative care scale has good validity and reliability when used for cancer patients.