• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.1-7
• /
• 2021

In this paper, we propose a feature selection technique for multi-label classification. Many existing feature selection techniques have selected features by calculating the relation between features and labels such as a mutual information scale. However, since the mutual information measure requires a joint probability, it is difficult to calculate the joint probability from an actual premise feature set. Therefore, it has the disadvantage that only a few features can be calculated and only local optimization is possible. Away from this regional optimization problem, we propose a feature selection technique that constructs a low-rank space in the entire given feature space and selects features with sparsity. To this end, we designed a regression-based objective function using Nuclear norm, and proposed an algorithm of gradient descent method to solve the optimization problem of this objective function. Based on the results of multi-label classification experiments on four data and three multi-label classification performance, the proposed methodology showed better performance than the existing feature selection technique. In addition, it was showed by experimental results that the performance change is insensitive even to the parameter value change of the proposed objective function.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.221-229
• /
• 2020

This study aims to find out predictors of a movie's eventual box office, focusing on a movie's box office rank on an opening day. For an empirical analysis, I use data of 794 commercial movies released in the Korean theatrical exhibition market during the recent five years(2013~2017). The regression analysis shows that being box office number one on an opening day has statistically significant impact on a movie's final box office. A movie's quality, measured by audience's review, does not give significant impact on top1 movie's final success. Indexes such as increase of showing number on Sunday are strongly related to a movie's economic success. The additional analysis on box office number one movie on an opening day, totally 158 movies, finds that box office growth rate on a second week is strongly related to a movie's final success. Lastly, correlation coefficient of a movie's opening day box office and final box office does not show consistent growth when the coefficient is compared yearly. This study might have meaning in that it proposes new box office predictors and shows the relation of the indexes and a movie's final performance empirically.

• Asian-Australasian Journal of Animal Sciences
• /
• v.11 no.4
• /
• pp.363-367
• /
• 1998

This study has objectives of to estimate the genetic and phenotypic trend for growth in a closed herd of Landrace $\times$ desi crossbreds. The possibility of early selection of boars was also investigated in order to reduce generation interval and thus, to enhance response per year in selection programmes. The data originated from Livestock Production Research (Pigs), Indian Veterinary Research Institute (IVRI), Izatnagar (UP), India - a unit of All India Coordinated research Project on Pigs (AICRP on Pigs). Data consisted of 891 crossbred piglets, progeny of 29 boars. The piglets were born in 132 parities of 72 sows between 8 years from 1987 to 1994. Records on weight at birth, at 2 weeks interval upto 8 weeks of age (Wl, W2, ${\cdots}\;{\cdots}$ W8) and at 16th week (W16) were used in this investigation. BLLTP estimates of the sires were computed. Breeding value of each sire was estimated as twice of sire and sire group solutions. Phenotypic trend was estimated as regression of weight performance on year. Genetic trend was computed by estimating regression of breeding value of sires on time. Average body weights ranged from 0.92 kg (W1) to 18.95 kg (W16) and showed a continuous increase over age. Heritabilities of the weight at 4th and 6th week were medium (0.29 and 0.14). Rest of the weights were highly heritable. The product moment and rank, both correlations were high between breeding value for W6 and W16 (0.68 and 0.70). This shows that sire selection for W6 can be successfully implemented in order to achieve sufficient genetic improvement in growth. Phenotypic trend was positive at all ages. The phenotypic regression coefficient ranged from 0.02 kg at birth to 0.40 kg at 16 weeks. Genetic trend was also positive. The regression coefficients of average breeding value of sires on time showed a range of 1.471 kg (0.021 to 1.492 kg) for different weights. These coefficients were significant and higher than their corresponding phenotypic regression coefficient.

• Journal of Korean Public Health Nursing
• /
• v.15 no.2
• /
• pp.225-238
• /
• 2001

The purpose of this study is to examine public health nurses for their morale, test the effect of each factor on the morale, determine the variables affecting the morale, and thereby, provide for some basic data useful to the development of personnel affair administration for nurses. The survey on the nurses for public health centers was conducted for 10 days from April 23 to May 2, 2001; 96 nurses from Pusan, 101 from Kyonggi-do and 108 from Kangwon-do. The results of the study are as follows; 1. For the demographic variables, those aged between 31 and 39 accounted for the majority $(50.2\%)$ of the sample. $90.8\%$ was married, and $67.9\%$ of the sample graduated from junior colleges. $29.6\%$ of them had worked for 10-14 years and $62.5\%$ was of the seventh rank. $62.3\%$ of the nurses was recruited, and $59.4\%$ had chosen the public job for its guaranteed status. Half the nurses were working for the county population of which was more than 260 thousands, and $53\%$ of the nurses was serving the public health centers with 11-15 members. $47.3\%$ of them perceived that their living standard is middle or lower. 2. The degree of the moral was found as mean score. 2.65, which is interpreted as low. It has 11 factors. The rank of mean score of the factors is job satisfaction (3.36), sense of belonging (3.36), sense of recognition (3.30), stress due to supervision (3.13), degree of participation (3.05) and self-achievement (3.04), while those scoring lower points were assurance of status (2.58), pay level (2.53), working conditions (2.35) and promotion opportunity (2.31). 3. The degree of moral depending on the demographic variables was significantly affected by such variables as age. academic background, career, rank, employment method, motive for the job, size of the population served and living standards. 4. The result of the Stepwise multiple regression analysis for the morale factors, it was found that self-achievement accounted for $61\%$ of the total variance of the degree of morale, followed by stable status $(18\%)$, working conditions $(8\%)$, job requirements $(4\%)$ and promotion opportunities $(2\%)$; these five factors explained about $94.6\%$ of total variance of the degree of nurses' morale. On the other hand. age $(8\%)$ and academic background $(2\%)$ accounted for $10\%$ of the total variance of the degree of morale. 5. The factors affecting nurses' job life was economic need $(26.7\%)$, personnel management $(17.5\%)$, sense of recognition $(13.2\%)$, human relationship $(11.0\%)$, stable status and personal development in rank. On the other hand, the factors influencing on their possible resignation were children's bringing-up $(27.8\%)$, poor personnel management and promotion $(13.3\%)$, workload $(11.1\%)$ and little personal development $(8.9\%)$, Since such morale factors as promotion opportunity, working condition. pay level and stable status scored lower, it is required to reconsider those factors to improve nurses' morale.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.4
• /
• pp.35-43
• /
• 2023

This study is aiming to analyze the relevance of rating criteria and these criteria may have effects on policy purpose of 'Construction Skilled Workers' Rank System', that are inflow of new comer, improvement of job performance, and decrease job-change. Closely related systems, electronic card system and prevailing wage system, are considered by assuming three scenarios, although they are not introduced yet. Empirical survey shows that the relevance is above average. The empirical result of regression also predicts that policy target might be mostly satisfied. Policy purpose is regressed on rating criteria, they are career, qualification, education and training, award. Career and award have positive impact on inflow of new comer. All four criteria have significant impacts on improvement of job performance. Award has strong effects on decreasing job-change. Especially, when electronic card system and prevailing wage system are adopted simultaneously with 'Construction Skilled Workers' Rank System', the level of satisfaction of policy purpose would be higher.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.27 no.3
• /
• pp.51-73
• /
• 2016

This study analyzes on the perception of public librarians about lifelong education tasks in public library using Mann Whitney U-test, Spearman rank-order correlation coefficient, Multiple regression analysis. At the same time, analysis about re-education needs using Analytic Hierarchy Process is conducted. As result, at first, 87% of respondents feel moderate or difficult about lifelong education tasks, especially on planning task. At second, librarians who have qualification about lifelong educator feel easier (P=0.04) than others, in detail, task about lecturer liaison (P=0.04) and planning (P=0.05). Adding that, the career experience and the job difficulty of librarians has negative relationship (R=-0.217). Especially scheduling (R=-0.33) and progressing (R=-0.22) tasks show statistically meaningful. At third, as the result of Multiple regression analysis, tasks about planning (P=0.04) and library marketing (P=0.05) are selected as meaningful elements which effect overall difficulty of life long education job. As final, 91% of librarian need retraining for life long education function, as result of spearman (R=-0.210), the more librarians feels difficult about life long education jobs, the more they need retraining. Anyway, as the result of priority of retraining subjects through AHP technique, user communication (CU P=0.310), planning (PL P=0.246), library marketing (LM P=0.173) are in weight order. CR ratio shows 0.146 with permissible degree.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.5
• /
• pp.604-608
• /
• 1997

Ten selected soybean genotypes, consisting of nine from a pedigree breeding programme and one recommended variety, were evaluated in nine different locations and over two years for stability of yield performance. Variance component analysis revealed that soybean regional yield trials should be performed at more locations rather than in more years. Five stability parameters, which were coefficient of variability, regression coefficient, deviation parameter, variance component for genotype$\times$environment interaction, and ecovalence, were employed in the evaluation. Significant genotype$\times$environment interaction was present with respect to soybean yield. The highest average yield over nine locations and two years was shown in Suwon 145, which was considered to be stable in all stability statistics. In rank correlation among stability parameters, there were highly significant correlations among stability parameters derived from three Eberhart and Russell's, Plaisted's, and Wricke's methods. Due to the different ranking of genotypes by different stability parameters, a comprehensive method should be employed to identify the promising genotype as well as to characterize the relationship between genotype and environment.

• The Journal of Engineering Geology
• /
• v.17 no.3
• /
• pp.393-404
• /
• 2007

The purpose of this study is to capture the essentials in survey and evaluation scheme which are able to assess the hazard of a rock slope systematically. Statistical analysis are performed on slope instability parameters related to failure of the rock slope. As the slope instability parameters, twelve survey items are considered such as tension crack, surface deformation, deformation of retaining structures, volume of existing failures, angles between strike of discontinuity and strike of cut slope face, angles between dip of discontinuity and dip of cut slope face, discontinuity condition, cut slope angle, rainfall or ground water level, excavation condition, drainage condition, reinforcement. A total of 233 road cut slopes located in Gyeongnam were considered. The stability of the road cut slopes were evaluated by estimating the slope instability index(SII) and corresponding stability rank. 126 rock slopes were selected to analyze statistical relation between SII and slope instability parameters. The multiple regression analysis was applied to derive statistical models which are able to predict the SII and corresponding slope stability rank. Also, its applicability was explored to predict the slope failures using the variables of slope instability parameters. The results obtained in this study clearly show that the methodology given in this paper have strong capabilities to evaluate the failures of the road cut slope effectively.

• Journal of Sasang Constitutional Medicine
• /
• v.33 no.3
• /
• pp.127-137
• /
• 2021

Objectives The purpose of this study was to identify the effects of personality by each Sasang constitution on sleep using Positive Affect and Negative Affect Schedule(PANAS) and NEO-personality inventory(NEO-PI). Methods The subjects of this study were 2,078 people who had information on Sasang constitutional type and personality(PANAS, NEO-PI) among the data established at the Korean Medicine Data Center. Sleep time and sleep quality were investigated through self-written questionnaires. Sleep time was collected by hand-writing, and sleep quality was checked on a 4 point Likert scale. Pearson correlation analysis was conducted to see the correlation between personality and sleep in each constitutional type. Logistic regression was performed using personality as independent variables to find out how much personality affects sleep time. In order to find out how much personality affects sleep quality, regression analysis was performed using personality as independent variables. Results & Conclusions Sleep time was hardly affected by personality. As a result of Pearson correlation analysis, sleep time in all subjects did not show a significant correlation with personality. In logistic regression on sleep time as the dependent variable, no statistically significant results were obtained except for the Negative Affect(NA) in Taeeumin. Sleep quality showed a statistically significant correlation with the negative affect(NA), neuroticism(N), extraversion(E), Physical Component Summary(PCS) and Mental Component Summary(MCS). As a result of regression analysis on sleep quality as the dependent variable, neuroticism(N), negative affect(NA), positive affect(PA), and extraversion(E) were found in the factors affecting sleep quality. Besides, how much personality affected sleep quality might differ in each constitution. In all constitutions, sleep quality was affected by N, but the rank of N was different in each constitution. The sleep quality of Soyangin was not affected by E, and the sleep quality of Taeeumin was specifically affected by O.

• Journal of Korean Clinical Health Science
• /
• v.1 no.1
• /
• pp.9-17
• /
• 2013

Purpose. This study is to find the degree of variations and trends of hospital services utilization for hypertensive disease, and have done the comparative analysis of the factors affecting occurring some variations. For this, this study uses the data for patients-survey and health-survey of a regional society by Korea Institute for Heath and Social Affairs in 2008; The regional units are classified into 160 of medium size medical service areas. Methods. I understand the level of variation by using index of Extremal Quotient(EQ) and Coefficient Variation(CV), and analyze critical factors influencing some differences in hospital services utilization by using multi-regression model. Results. The main results are followed:The first, in case of rate of hospital services utilization according to standarization of sex and age by small area, I find the variations of EQ 5.3 and CV 0.3; In Ho-nam, especially, the variation of high rank of 10 of age shows higher distribution. The second, the results analyzing the factors influencing on hospital services utilization by multi regression model are that a number of bed hospitals is significant positive relationship and EQ-5D of health behavior is significant negative one. Conclusions. To increase equity of hospital services utilization for hypertensive disease, this study requests the appropriate supply management of bed hospitals by region, efficient allocation of resources, and revitalization of the health promotion program.